Merge master into draw-sprite-max-sprites-guard.

Resolve batching_test.odin by keeping master tests and the MAX_SPRITES guard test.

.github/issues/add-configurable-internal-render-scale.md

@@ -1,208 +0,0 @@
-# Add configurable internal render scale to improve fill-bound FPS
-
-## Summary
-
-Complete-frame benchmarks show that the current sprite renderer is primarily
-pixel/fill bound on Vulkan/Lavapipe, not CPU draw-preparation bound. Rendering
-the world into a smaller offscreen color target and nearest-blitting it to the
-native swapchain produced the largest measured FPS improvement.
-
-This should be an opt-in render-quality setting with a native-resolution
-fallback. For pixel art, a 50% scale is especially useful because it maps to an
-exact 2× nearest-neighbor upscale.
-
-## Evidence
-
-Environment:
-
-- Commit `dc66203259e92ce39291556f7b6c26c8dd999b84`
-- Odin `dev-2026-05-nightly:ea5175d`
-- `-debug -o:speed`
-- SDL 3.4.12, Vulkan/Lavapipe, immediate present
-- 800×600 swapchain
-- Five 150-frame trials per invocation after 50 warm-up frames
-- Order-balanced baseline/candidate invocations
-- GPU idle wait included before stopping each trial timer
-
-### Fill and overdraw scaling
-
-The committed `perf-frame` harness produced:
-
-| Workload | Median frame time | Median FPS |
-| --- | ---: | ---: |
-| 1 visible sprite | 0.592 ms | 1,690 |
-| 24 visible sprites | 2.249 ms | 445 |
-| 64 visible sprites | 4.017 ms | 249 |
-| 128 visible sprites | 6.255 ms | 160 |
-| 128 stacked sprites | 7.692 ms | 130 |
-
-Stacking the same 128 sprites increased frame time by approximately 23%,
-confirming that overdraw matters.
-
-With one centered sprite, render-target scaling produced:
-
-| Window size | Pixels | Median frame time |
-| --- | ---: | ---: |
-| 400×300 | 120,000 | 0.268 ms |
-| 800×600 | 480,000 | 0.545 ms |
-| 1600×1200 | 1,920,000 | 2.075 ms |
-
-The near-linear increase at larger sizes is further evidence of a pixel-bound
-workload.
-
-### Internal render-scale prototype
-
-The temporary candidate kept the physical swapchain at 800×600, rendered
-sprites into a smaller `COLOR_TARGET | SAMPLER` texture, and used
-`BlitGPUTexture` with nearest filtering to upscale into the swapchain.
-
-Aggregate medians across ten trials per mode:
-
-| Workload | Native | 75% scale | 50% scale |
-| --- | ---: | ---: | ---: |
-| 128 spread sprites | 6.082 ms / 164 FPS | 4.082 ms / 245 FPS | 3.082 ms / 325 FPS |
-| 128 stacked sprites | 7.912 ms / 126 FPS | 5.116 ms / 195 FPS | 3.034 ms / 330 FPS |
-
-Compared with native resolution:
-
-- 75% reduced frame time by 33–35% and increased FPS by 49–55%.
-- 50% reduced frame time by 49–62% and increased FPS by 97–161%.
-
-A visual smoke test confirmed that the 50% path rendered the complete scene at
-the correct orientation and 800×600 output size. It was visibly coarser, as
-expected. A 75% scale at 800×600 does not produce an integer upscale and can
-create uneven pixel sizing with nearest filtering.
-
-## Reproduction harness
-
-Native spread and stacked workloads:
-
-```bash
-make perf-frame \
-	PERF_FRAME_SCENARIO=0 \
-	PERF_FRAME_SPRITES=128 \
-	PERF_FRAME_WIDTH=800 \
-	PERF_FRAME_HEIGHT=600
-
-make perf-frame \
-	PERF_FRAME_SCENARIO=3 \
-	PERF_FRAME_SPRITES=128 \
-	PERF_FRAME_WIDTH=800 \
-	PERF_FRAME_HEIGHT=600
-```
-
-Run the same commands on the candidate branch with internal render scale set to
-75% and 50%. Keep every `PERF_FRAME_*` value unchanged between comparisons.
-
-## Suggested fix
-
-Add explicit logical/output and internal-render dimensions to `App`:
-
-```odin
-Render_Scale :: enum {
-	Native,
-	Three_Quarter,
-	Half,
-}
-
-App :: struct {
-	// Existing swapchain fields remain the logical/output dimensions.
-	swapchain_texture: ^sdl.GPUTexture,
-	swapchain_w:       u32,
-	swapchain_h:       u32,
-
-	render_scale:   Render_Scale,
-	scene_texture:  ^sdl.GPUTexture,
-	scene_w:        u32,
-	scene_h:        u32,
-}
-```
-
-Create the offscreen target with the swapchain format and both usages required
-by SDL's blit path:
-
-```odin
-app.scene_texture = sdl.CreateGPUTexture(
-	app.device,
-	{
-		type = .D2,
-		format = sdl.GetGPUSwapchainTextureFormat(app.device, app.window),
-		usage = {.COLOR_TARGET, .SAMPLER},
-		width = app.scene_w,
-		height = app.scene_h,
-		layer_count_or_depth = 1,
-		num_levels = 1,
-		sample_count = ._1,
-	},
-)
-```
-
-Render the sprite pass into `scene_texture`. Continue using the logical
-swapchain dimensions for camera and clip-space calculations so world layout
-does not change with render scale:
-
-```odin
-color_info := sdl.GPUColorTargetInfo {
-	texture = app.scene_texture,
-	clear_color = app.clear_color,
-	load_op = .CLEAR,
-	store_op = .STORE,
-	cycle = true,
-}
-```
-
-After ending the render pass, upscale into the full swapchain:
-
-```odin
-blit := sdl.GPUBlitInfo {
-	source = {
-		texture = app.scene_texture,
-		w = app.scene_w,
-		h = app.scene_h,
-	},
-	destination = {
-		texture = app.swapchain_texture,
-		w = app.swapchain_w,
-		h = app.swapchain_h,
-	},
-	load_op = .DONT_CARE,
-	filter = .NEAREST,
-}
-sdl.BlitGPUTexture(app.cmd, blit)
-```
-
-Use the existing direct-to-swapchain path at native scale to avoid an
-unnecessary blit. Recreate the offscreen texture whenever the swapchain size,
-format, or render-scale setting changes. If native-resolution UI or text is
-added later, render it after the world blit in a separate swapchain pass.
-
-## Rejected experiment: fragment alpha discard
-
-Approximately 49.7% of pixels inside the baked frame rectangles have exact
-alpha zero. A temporary fragment shader discarded those texels:
-
-```glsl
-vec4 texel = texture(u_tex, v_uv);
-if (texel.a == 0.0) {
-    discard;
-}
-out_color = texel;
-```
-
-Despite the high transparent coverage, this regressed frame time by roughly
-5–6% in both spread and stacked workloads. Do not add alpha discard without
-contradictory hardware-GPU evidence.
-
-## Acceptance criteria
-
-- Native, 75%, and 50% internal render-scale settings are available.
-- Native scale retains the current direct-to-swapchain path.
-- The scene target is recreated safely on resize, format change, or scale
-  change and released during shutdown.
-- Camera/world coordinates remain stable when render scale changes.
-- Nearest filtering is used for pixel-art output.
-- Add screenshot-based checks for output orientation, viewport coverage, and
-  stable sprite placement at every scale.
-- Benchmark spread and stacked scenarios on at least one hardware GPU.
-- Document the quality tradeoff and recommend integer upscale ratios for pixel
-  art.

.github/issues/add-deterministic-sprite-performance-benchmark.md

@@ -1,218 +0,0 @@
-# Add deterministic CPU and frame benchmarks for sprite rendering
-
-## Summary
-
-The current `make flame` workflow is valuable for finding call stacks, but it
-does not provide a reproducible performance metric:
-
-- `examples/crowd` draws only 24 sprites.
-- `MAX_SPRITES` limits the renderer to 128 sprites.
-- Recording starts an interactive application and asks the user to play for
-  10–20 seconds before quitting.
-- The two checked-in reports contain only 499 and 469 samples.
-- CPU queue construction and GPU submission are combined in one profile.
-- The profiler currently builds unoptimized code.
-
-These limitations make it difficult to tell whether a change made
-`draw_sprite` faster, changed driver behavior, or merely changed sampling noise.
-
-## Evidence
-
-A temporary deterministic benchmark exposed two very different results:
-
-1. CPU-only `draw_sprite`, two million calls and seven trials:
-   - `-debug`: median 192.560 ns/draw
-   - `-debug -o:speed`: median 19.154 ns/draw
-2. Full 128-sprite frames through SDL GPU on Lavapipe, 1,000 measured frames
-   and five trials:
-   - `-debug`: median 2.486 ms/frame
-   - `-debug -o:speed`: median 2.447 ms/frame
-
-At the current cap, optimized CPU queue construction is approximately 3.2
-microseconds for 128 sprites. The full software-rendered frame is around 2.45
-milliseconds, so optimizing `draw_sprite` cannot materially improve that
-specific end-to-end workload. A hardware GPU or a larger future sprite limit
-may have a different balance.
-
-This split also explains why percentages from the current unoptimized
-flamegraphs overstate small helper functions.
-
-### Follow-up enhancement benchmarks
-
-Six proposed renderer changes were implemented temporarily and measured before
-being discarded. Full-frame tests used:
-
-- Odin `dev-2026-05-nightly:ea5175d`
-- `-debug -o:speed`
-- SDL 3.4.12 with Vulkan/Lavapipe
-- 128 animated sprites using real baked toad metadata and textures
-- Warm-up before measurement
-- Paired baseline/change samples on the same device with alternating order
-- Ten 400-frame samples per mode, except culling, which used seven 750-frame
-  samples per mode
-
-Each row is a separate paired run, so absolute frame times should only be
-compared within that row.
-
-| Enhancement | Baseline median | Changed median | Result |
-| --- | ---: | ---: | ---: |
-| Viewport culling, all visible | 4.845 ms | 4.822 ms | 0.5% faster |
-| Viewport culling, 50% offscreen | 2.856 ms | 2.878 ms | 0.8% slower |
-| SDL transfer and vertex buffer cycling | 4.869 ms | 4.834 ms | 0.7% faster |
-| Contiguous vertex queue and one upload-side copy | 4.793 ms | 4.809 ms | 0.3% slower |
-| Four-vertex indexed quads | 4.745 ms | 4.830 ms | 1.8% slower |
-| GPU instancing with 32-byte instance records | 5.527 ms | 5.467 ms | 1.1% faster |
-| Texture sorting, including sort cost, 128 runs to 2 | 5.765 ms | 5.654 ms | 1.9% faster |
-
-Interpretation:
-
-- Viewport culling is neutral at the current cap. The GPU already clips
-  offscreen triangles, and the sprites remain in one batched draw.
-- SDL buffer cycling is a small performance improvement and is also the
-  documented way to avoid overwriting resources still bound by prior frames.
-- Repacking the CPU queue does not help at 128 sprites; extra dynamic-array
-  work offsets the saved small-copy loop.
-- Indexed quads regress performance despite reducing dynamic vertex data.
-- Instancing reduces per-sprite upload data from 96 to 32 bytes, but the 1.1%
-  gain does not justify a second pipeline and shader path at the current cap.
-- Texture sorting has the largest full-frame gain, but unrestricted sorting can
-  change alpha compositing. It is only safe within compatible layer/order
-  groups.
-
-The recommended order is:
-
-1. Profile optimized builds and establish the deterministic benchmark.
-2. Apply the clip-space math simplification documented in the related issue.
-3. Enable SDL buffer cycling for correct cross-frame resource reuse.
-4. Consider layer-aware texture grouping if a 1.9% workload-specific gain is
-   worth the ordering complexity.
-5. Defer culling, queue repacking, indexed quads, and instancing until the
-   sprite limit or measured workload grows substantially.
-
-These results are from a software Vulkan backend. Hardware drivers may have a
-different balance, which is another reason to keep the benchmark reproducible
-and report backend details.
-
-## Suggested fix
-
-Add a non-interactive benchmark target with two explicitly separate workloads.
-
-The committed harnesses are:
-
-```make
-PERF_ODIN_FLAGS ?= -debug -o:speed
-
-perf-draw:
-	odin run benchmarks/draw_sprite \
-		-collection:pkg=. \
-		$(PERF_ODIN_FLAGS) \
-		-define:PERF_ITERATIONS=$(PERF_DRAW_ITERATIONS)
-
-perf-frame:
-	odin run benchmarks/sprite_frame \
-		-collection:pkg=. \
-		$(PERF_ODIN_FLAGS) \
-		-define:PERF_FRAMES=$(PERF_FRAME_FRAMES) \
-		-define:PERF_SCENARIO=$(PERF_FRAME_SCENARIO)
-```
-
-Run the standard workloads with:
-
-```bash
-# CPU-only draw preparation.
-make perf-draw
-
-# Complete frame: 128 visible sprites sharing one texture.
-make perf-frame PERF_FRAME_SCENARIO=0
-
-# Complete frame: every second sprite is fully offscreen.
-make perf-frame PERF_FRAME_SCENARIO=1
-
-# Complete frame: 128 sprites alternate between two texture objects.
-make perf-frame PERF_FRAME_SCENARIO=2
-```
-
-Every invocation prints the Git commit, Odin version, compiler flags, workload
-configuration, every trial, and the median. `perf-frame` waits for GPU idle
-after warm-up and after each measured frame batch so outstanding work is
-included.
-
-### CPU queue benchmark
-
-- Construct `App`, `Character_Data`, and `Sprite` with real baked metadata.
-- Use safe fake non-null GPU handles; `draw_sprite` only checks/stores these.
-- Preallocate the draw list.
-- Clear the queue whenever it reaches `MAX_SPRITES`.
-- Vary sprite position between calls so the compiler cannot hoist the work.
-- Warm up before timing.
-- Run at least one million calls and report nanoseconds per draw.
-- Build with `-o:speed` by default.
-
-The measured loop should clear the queue at its cap, vary input to prevent
-compiler hoisting, and report time per draw:
-
-```odin
-PERF_ITERATIONS :: #config(PERF_ITERATIONS, 2_000_000)
-
-start := sdl.GetTicksNS()
-for i in 0 ..< PERF_ITERATIONS {
-	if len(app.draw_list) == eng.MAX_SPRITES {
-		clear(&app.draw_list)
-	}
-	sprite.position.x = f32(i & 1023)
-	eng.draw_sprite(&app, &sprite)
-}
-elapsed := sdl.GetTicksNS() - start
-
-fmt.printfln(
-	"%.3f ns/draw",
-	f64(elapsed) / f64(PERF_ITERATIONS),
-)
-```
-
-### Full-frame benchmark
-
-- Use a real SDL GPU device and baked texture.
-- Warm up before timing.
-- Run a fixed number of frames without interactive input.
-- Report milliseconds per frame and sprites per second.
-- Record GPU backend, present mode, compiler version, compiler flags, and sprite
-  count.
-
-Use a fixed frame count rather than an interactive quit time:
-
-```odin
-PERF_FRAMES :: #config(PERF_FRAMES, 1_000)
-
-for _ in 0 ..< 100 {
-	draw_benchmark_frame(&app, sprites[:]) // warm-up
-}
-
-start := sdl.GetTicksNS()
-for _ in 0 ..< PERF_FRAMES {
-	draw_benchmark_frame(&app, sprites[:])
-}
-elapsed := sdl.GetTicksNS() - start
-
-fmt.printfln(
-	"%.3f ms/frame",
-	f64(elapsed) / f64(PERF_FRAMES) / 1_000_000.0,
-)
-```
-
-The CPU benchmark should be available without a display or GPU. The full-frame
-benchmark may remain opt-in where a suitable GPU backend is unavailable.
-
-Do not add a strict CI regression threshold initially; hosted runner variance
-will make a single threshold flaky. CI can still compile the benchmark and
-verify that it completes.
-
-## Acceptance criteria
-
-- A Makefile target runs the optimized CPU benchmark non-interactively.
-- Results include compiler flags, iteration count, median, and per-trial values.
-- CPU queue time is reported separately from complete frame time.
-- Sprite positions or frames vary during the measured loop.
-- The draw list never silently exceeds `MAX_SPRITES`.
-- The benchmark has documented commands for repeatable local comparison.
-- `make check` and `make test` continue to pass.

.github/issues/add-order-safe-texture-batching.md

@@ -1,116 +0,0 @@
-# Add opt-in order-safe texture batching
-
-## Summary
-
-`end_frame` batches only consecutive sprites that use the same texture.
-Alternating two textures therefore produces one sampler bind and draw call per
-sprite even when some sprites could safely be regrouped.
-
-Globally sorting transparent sprites by texture is not correct: overlapping
-sprites may blend differently when submission order changes. Batching should
-therefore be opt-in within explicit groups whose members are safe to reorder.
-
-## Evidence
-
-A temporary paired benchmark used:
-
-- Odin `dev-2026-05-nightly:ea5175d` with `-debug -o:speed`
-- SDL 3.4.12 and Vulkan/Lavapipe
-- 128 animated sprites alternating between two equivalent textures
-- Sorting cost included in the measured frame
-- Ten order-alternated samples of 400 frames per mode
-
-| Mode | Texture runs | Median frame time |
-| --- | ---: | ---: |
-| Submission order | 128 | 5.765 ms |
-| Texture grouped | 2 | 5.654 ms |
-
-Sorting and grouping improved median frame time by approximately **1.9%**.
-Hardware drivers with higher draw-call overhead may show a different result.
-
-## Reproduction harness
-
-Run the committed alternating-texture workload on the baseline and candidate
-commits:
-
-```bash
-make perf-frame \
-	PERF_FRAME_SCENARIO=2 \
-	PERF_ODIN_FLAGS="-debug -o:speed"
-```
-
-Keep all `PERF_FRAME_*` values unchanged. The baseline should produce one
-texture run per sprite; the candidate should reduce runs only inside explicit
-reorder-safe groups. Compare `median_ms_per_frame` and verify rendered output.
-
-## Suggested fix
-
-Add an explicit batch group to queued sprites. Group `0` keeps strict submission
-order; nonzero groups may be reordered only when the caller guarantees that
-their members are order-independent.
-
-```odin
-Queued_Sprite :: struct {
-	texture:     ^sdl.GPUTexture,
-	verts:       [SPRITE_VERT_COUNT]Vertex,
-	batch_group: u32, // 0 = strict order; nonzero = caller permits regrouping
-}
-```
-
-Sort each contiguous, nonzero group by texture immediately before upload:
-
-```odin
-group_texture_runs :: proc(list: []Queued_Sprite) {
-	start := 0
-	for start < len(list) {
-		group := list[start].batch_group
-		if group == 0 {
-			start += 1
-			continue
-		}
-
-		end := start + 1
-		for end < len(list) && list[end].batch_group == group {
-			end += 1
-		}
-
-		// Stable insertion sort is sufficient while MAX_SPRITES is 128.
-		for i in start + 1 ..< end {
-			item := list[i]
-			j := i
-			for j > start {
-				if uintptr(list[j - 1].texture) <= uintptr(item.texture) {
-					break
-				}
-				list[j] = list[j - 1]
-				j -= 1
-			}
-			list[j] = item
-		}
-		start = end
-	}
-}
-```
-
-Call it after all sprites are queued and before the transfer-buffer copy:
-
-```odin
-group_texture_runs(app.draw_list[:])
-```
-
-Expose batching through a separate API or explicit parameter so existing
-`draw_sprite` calls remain strict-order by default:
-
-```odin
-draw_sprite_batched(&app, &sprite, batch_group = 1)
-```
-
-## Acceptance criteria
-
-- Existing `draw_sprite` behavior preserves exact submission order.
-- Reordering requires an explicit nonzero batch group.
-- Sorting never moves a sprite across a strict-order entry or group boundary.
-- Add tests for strict order, group boundaries, stable same-texture ordering,
-  and reduced texture-run count.
-- Add a visual overlap test confirming default alpha compositing is unchanged.
-- Benchmark sorting cost and draw-call reduction on a hardware GPU.

.github/issues/enable-sdl-gpu-buffer-cycling.md

@@ -1,83 +0,0 @@
-# Enable SDL GPU buffer cycling for per-frame sprite uploads
-
-## Summary
-
-`end_frame` overwrites the same transfer buffer and vertex buffer every frame,
-but both SDL calls currently pass `cycle = false`:
-
-```odin
-sdl.MapGPUTransferBuffer(app.device, app.transfer_buffer, false)
-sdl.UploadToGPUBuffer(copy_pass, src, dst, false)
-```
-
-SDL documents cycling as the mechanism that rotates to an unbound internal
-resource when the previous frame still references the current one. Enabling it
-avoids an unnecessary resource dependency and makes the overwrite pattern
-explicitly safe.
-
-## Evidence
-
-A temporary paired benchmark used:
-
-- Odin `dev-2026-05-nightly:ea5175d` with `-debug -o:speed`
-- SDL 3.4.12 and Vulkan/Lavapipe
-- 128 animated sprites
-- Ten order-alternated samples of 400 frames per mode
-
-| Mode | Median frame time |
-| --- | ---: |
-| Cycling disabled | 4.869 ms |
-| Cycling enabled | 4.834 ms |
-
-Cycling improved median frame time by approximately **0.7%**. This is a small
-performance change, but it also follows SDL's documented resource-reuse model.
-
-## Reproduction harness
-
-Run the committed full-frame harness on the baseline commit and candidate
-commit:
-
-```bash
-make perf-frame \
-	PERF_FRAME_SCENARIO=0 \
-	PERF_ODIN_FLAGS="-debug -o:speed"
-```
-
-Keep all `PERF_FRAME_*` values unchanged. Compare `median_ms_per_frame`; the
-harness waits for GPU idle before stopping each trial timer.
-
-## Suggested fix
-
-Cycle both resources that are fully overwritten each frame:
-
-```odin
-map_ptr := sdl.MapGPUTransferBuffer(
-	app.device,
-	app.transfer_buffer,
-	true, // rotate if the previous frame still binds this transfer buffer
-)
-
-// Write the complete [0, n * SPRITE_VERTS_SIZE) range, then unmap.
-sdl.UnmapGPUTransferBuffer(app.device, app.transfer_buffer)
-
-copy_pass := sdl.BeginGPUCopyPass(cmd)
-sdl.UploadToGPUBuffer(
-	copy_pass,
-	src,
-	dst,
-	true, // rotate the destination vertex buffer if it is still bound
-)
-sdl.EndGPUCopyPass(copy_pass)
-```
-
-Cycling makes previous contents undefined, so this remains correct only because
-the renderer writes the complete vertex range used by the frame before drawing.
-Do not enable cycling for partial updates that depend on untouched data.
-
-## Acceptance criteria
-
-- Both `MapGPUTransferBuffer` and `UploadToGPUBuffer` use `cycle = true`.
-- The complete submitted vertex range is rewritten every frame.
-- Existing engine tests and examples continue to pass.
-- A full-frame benchmark confirms no regression on a hardware GPU backend.
-- Add a comment explaining why cycling is safe for this full-overwrite path.

.github/issues/profile-optimized-sprite-builds.md

@@ -1,98 +0,0 @@
-# Profile optimized sprite builds instead of unoptimized debug code
-
-## Summary
-
-`make flame-build` currently compiles the selected example with `-debug` but
-without an optimization mode:
-
-```make
-odin build examples/$(FLAME_EXAMPLE) -collection:pkg=. -out:$(FLAME_BIN) -debug
-```
-
-This makes the flamegraph useful for debugging but misleading for performance
-decisions. The current profiles largely describe code that will disappear or
-be inlined in an optimized build.
-
-## Evidence
-
-The two checked-in `crowd` profiles were captured from this unoptimized binary.
-They report:
-
-- `engine::draw_sprite`: 9.56% and 12.22% self time
-- `engine::to_clip`: 5.33% and 5.51% self time
-- `engine::sprite_feet_quad`: 3.98% and 3.30% self time
-- Additional time in string hashing/map lookup, bounds checks, and dynamic
-  array append helpers
-
-A CPU-only benchmark using the real `draw_sprite`, real baked toad metadata,
-preallocated draw list, changing sprite positions, and two million draws per
-trial produced:
-
-| Build | Median time per draw | Trials |
-| --- | ---: | ---: |
-| `-debug` (current Makefile behavior) | 192.560 ns | 7 |
-| `-debug -o:speed` | 19.154 ns | 7 |
-
-The optimized build is about **10.1x faster** without an engine code change.
-
-An end-to-end 128-sprite benchmark on SDL 3.4.12 with Lavapipe showed only a
-small full-frame difference (median 2.486 ms debug versus 2.447 ms optimized)
-because software GPU/driver work dominated. This does not invalidate the CPU
-result; it shows why CPU queue time and full-frame time must be reported
-separately.
-
-Environment:
-
-- Odin `dev-2026-05-nightly:ea5175d` (the version pinned by CI)
-- SDL 3.4.12
-- Linux x86-64
-
-## Suggested fix
-
-Compile profiling binaries with optimization while retaining symbols:
-
-```make
-FLAME_ODIN_FLAGS ?= -debug -o:speed
-
-flame-build:
-	odin build examples/$(FLAME_EXAMPLE) \
-		-collection:pkg=. \
-		-out:$(FLAME_BIN) \
-		$(FLAME_ODIN_FLAGS)
-```
-
-Keeping the flags configurable allows an explicitly unoptimized diagnostic run
-without making it the performance default.
-
-Example usage:
-
-```bash
-# Representative performance profile: optimized code with debug symbols.
-make flame FLAME_EXAMPLE=crowd
-
-# Explicitly profile unoptimized code when investigating debug-only behavior.
-make flame FLAME_EXAMPLE=crowd FLAME_ODIN_FLAGS="-debug -o:none"
-```
-
-Reproduce the isolated build-mode comparison with the committed CPU harness:
-
-```bash
-make perf-draw PERF_ODIN_FLAGS="-debug -o:none"
-make perf-draw PERF_ODIN_FLAGS="-debug -o:speed"
-```
-
-Both runs print the Git commit, Odin version, compiler flags, every trial, and
-the median nanoseconds per draw.
-
-Consider applying an explicit optimization mode to performance-oriented example
-runs as well. Plain `odin run` currently uses Odin's unoptimized default.
-
-## Acceptance criteria
-
-- `make flame-build` produces an optimized binary with debug symbols.
-- `FLAME_ODIN_FLAGS` can override the default for diagnostic builds.
-- `make check` and `make test` continue to pass.
-- A new `crowd` profile records the exact compiler flags in its report or
-  accompanying documentation.
-- Performance conclusions distinguish CPU `draw_sprite` cost from complete
-  frame/GPU submission cost.

.github/issues/prototype-instanced-sprite-rendering.md

@@ -1,139 +0,0 @@
-# Prototype instanced sprite rendering for larger batches
-
-## Summary
-
-The renderer currently generates and uploads six complete vertices per sprite:
-
-```text
-6 vertices × (position float2 + UV float2) = 96 bytes/sprite/frame
-```
-
-Instancing can keep one immutable six-corner unit quad on the GPU and upload one
-rectangle/UV record per sprite:
-
-```text
-clip rectangle float4 + UV rectangle float4 = 32 bytes/sprite/frame
-```
-
-This reduces dynamic upload volume by two thirds, but requires another pipeline
-and backend-specific vertex shader. At the current 128-sprite cap, the measured
-gain is too small to justify enabling it unconditionally.
-
-## Evidence
-
-A complete temporary instanced path was implemented with:
-
-- A static six-corner vertex buffer
-- A 32-byte per-instance buffer
-- Vertex-rate and instance-rate pipeline inputs
-- One instanced draw per texture run
-- Validated SPIR-V and SDL's debug GPU device
-
-The paired benchmark used ten order-alternated samples of 400 frames:
-
-| Mode | Median frame time |
-| --- | ---: |
-| Six dynamic vertices per sprite | 5.527 ms |
-| 32-byte instance per sprite | 5.467 ms |
-
-Instancing improved median frame time by approximately **1.1%** on
-Vulkan/Lavapipe with 128 sprites.
-
-## Reproduction harness
-
-Run the committed visible full-frame workload on baseline and candidate commits:
-
-```bash
-make perf-frame \
-	PERF_FRAME_SCENARIO=0 \
-	PERF_FRAME_SPRITES=128 \
-	PERF_ODIN_FLAGS="-debug -o:speed"
-```
-
-Keep all other `PERF_FRAME_*` values unchanged and compare
-`median_ms_per_frame`. To test 512 or more sprites, first raise the engine's
-`MAX_SPRITES` and associated buffer capacities on the candidate branch, then
-set `PERF_FRAME_SPRITES` to the same value.
-
-## Suggested fix
-
-Treat this as a prototype gated by larger sprite counts or a demonstrated
-hardware bottleneck, not as an immediate replacement.
-
-Define the compact instance payload:
-
-```odin
-Sprite_Instance :: struct {
-	clip_rect: [4]f32, // left, top, right, bottom
-	uv_rect:   [4]f32, // u0, v0, u1, v1
-}
-```
-
-Queue one record after the existing quad and UV calculations:
-
-```odin
-instance := Sprite_Instance {
-	clip_rect = {p0.x, p0.y, p2.x, p2.y},
-	uv_rect   = {u0, v0, u1, v1},
-}
-append(&app.instance_list, instance)
-```
-
-Use a static unit quad:
-
-```odin
-UNIT_QUAD := [6]Vec2 {
-	{0, 0}, {1, 0}, {1, 1},
-	{0, 0}, {1, 1}, {0, 1},
-}
-```
-
-The instanced vertex shader reconstructs position and UV:
-
-```glsl
-#version 450
-
-layout(location = 0) in vec2 in_corner;
-layout(location = 1) in vec4 in_clip_rect;
-layout(location = 2) in vec4 in_uv_rect;
-
-layout(location = 0) out vec2 v_uv;
-
-void main() {
-    vec2 position = mix(in_clip_rect.xy, in_clip_rect.zw, in_corner);
-    v_uv = mix(in_uv_rect.xy, in_uv_rect.zw, in_corner);
-    gl_Position = vec4(position, 0.0, 1.0);
-}
-```
-
-Configure slot 0 as vertex-rate and slot 1 as instance-rate, then draw each
-texture run with six vertices and `run` instances:
-
-```odin
-vb_descs := [2]sdl.GPUVertexBufferDescription {
-	{slot = 0, pitch = u32(size_of(Vec2)), input_rate = .VERTEX},
-	{slot = 1, pitch = u32(size_of(Sprite_Instance)), input_rate = .INSTANCE},
-}
-
-sdl.DrawGPUPrimitives(
-	app.render_pass,
-	6,        // unit-quad vertices
-	u32(run), // sprite instances in this texture run
-	0,
-	0,
-)
-```
-
-Keep the current path as a fallback until the instanced implementation exists
-for Vulkan, D3D12, and Metal and demonstrates a meaningful hardware win.
-
-## Acceptance criteria
-
-- Benchmark at 128, 512, 2,048, and 10,000 sprites or the highest supported
-  counts.
-- Report CPU queue time, bytes uploaded, and complete frame time separately.
-- Require a meaningful hardware improvement before changing the default path.
-- Supply equivalent Vulkan, D3D12, and Metal shaders.
-- Preserve texture-run batching and sprite flip/trim behavior.
-- Add visual equivalence tests for position, UVs, animation frames, and flip.
-- Retain the existing six-vertex path as a fallback during evaluation.

.github/issues/simplify-draw-sprite-clip-math.md

@@ -1,130 +0,0 @@
-# Reduce repeated clip-space work in `draw_sprite`
-
-## Summary
-
-`draw_sprite` calls `to_clip` four times for an axis-aligned quad:
-
-```odin
-p0 := to_clip(x0_px, y0_px, sw, sh)
-p1 := to_clip(x1_px, y0_px, sw, sh)
-p2 := to_clip(x1_px, y1_px, sw, sh)
-p3 := to_clip(x0_px, y1_px, sw, sh)
-```
-
-This repeats the same divisions and converts duplicate x/y coordinates. An
-axis-aligned sprite has only two unique x values and two unique y values.
-
-This is a measurable optimization, but it is low priority at the current
-128-sprite limit because the absolute saving is small.
-
-## Evidence
-
-The checked-in unoptimized profiles report `engine::to_clip` at 5.33% and 5.51%
-self time. Those percentages are inflated by the unoptimized profiling build,
-so the change was also measured with `-debug -o:speed`.
-
-A temporary benchmark used the real baked toad metadata, changed sprite
-position on every iteration, preallocated the queue, and performed two million
-draws per mode over seven trials:
-
-| Mode | Median time per draw |
-| --- | ---: |
-| Current `draw_sprite` | 25.128 ns |
-| Precomputed clip scale and reused coordinates | 21.531 ns |
-| Same math plus cached `Frame_Def` | 21.778 ns |
-
-Simplifying the math improved isolated draw time by approximately **14.3%**.
-Caching the resolved frame did not provide an additional benefit and should not
-be included without new evidence.
-
-At `MAX_SPRITES == 128`, the measured math saving is only about 0.46
-microseconds per completely full frame. GPU/driver work dominated the
-end-to-end benchmark, so this should follow the profiling and deterministic
-benchmark improvements.
-
-Follow-up paired full-frame experiments at the 128-sprite cap found no larger
-renderer-architecture win: buffer cycling improved median frame time by 0.7%,
-GPU instancing by 1.1%, and texture sorting by 1.9%, while culling, queue
-repacking, and indexed quads were neutral or slower. The clip-space change
-therefore remains the strongest measured optimization specifically inside
-`draw_sprite`, although its absolute frame impact is still small.
-
-Environment:
-
-- Odin `dev-2026-05-nightly:ea5175d`
-- Optimized with `-debug -o:speed`
-- Linux x86-64
-
-## Reproduction harness
-
-Run the committed CPU harness on the baseline commit and again after applying
-the suggested fix:
-
-```bash
-make perf-draw PERF_ODIN_FLAGS="-debug -o:speed"
-```
-
-Keep `PERF_DRAW_ITERATIONS`, `PERF_DRAW_WARMUP`, and `PERF_DRAW_TRIALS`
-unchanged between commits. Compare `median_ns_per_draw`.
-
-## Suggested fix
-
-Compute clip scaling once and construct corners from the unique coordinates:
-
-```odin
-sprite_quad_to_clip :: proc(x0, y0, x1, y1, sw, sh: f32) -> [4]Vec2 {
-	sx := 2.0 / sw
-	sy := 2.0 / sh
-
-	left   := x0 * sx - 1
-	right  := x1 * sx - 1
-	top    := 1 - y0 * sy
-	bottom := 1 - y1 * sy
-
-	return {
-		{left, top},
-		{right, top},
-		{right, bottom},
-		{left, bottom},
-	}
-}
-
-points := sprite_quad_to_clip(x0_px, y0_px, x1_px, y1_px, sw, sh)
-p0, p1, p2, p3 := points[0], points[1], points[2], points[3]
-```
-
-Keep `to_clip` for general callers and its existing tests; this change only
-specializes quad construction inside `draw_sprite`.
-
-Add an equivalence test before replacing the current calls:
-
-```odin
-@(test)
-sprite_quad_clip_math_matches_to_clip :: proc(t: ^testing.T) {
-	x0, y0 := f32(125), f32(80)
-	x1, y1 := f32(325), f32(280)
-	sw, sh := f32(800), f32(600)
-
-	expected := [4]Vec2 {
-		to_clip(x0, y0, sw, sh),
-		to_clip(x1, y0, sw, sh),
-		to_clip(x1, y1, sw, sh),
-		to_clip(x0, y1, sw, sh),
-	}
-	actual := sprite_quad_to_clip(x0, y0, x1, y1, sw, sh)
-
-	for i in 0 ..< 4 {
-		testing.expect_value(t, actual[i], expected[i])
-	}
-}
-```
-
-## Acceptance criteria
-
-- Existing sprite geometry, camera, UV, and batching tests pass.
-- Add or extend a test that compares all four generated corners against
-  `to_clip` for representative viewport and sprite coordinates.
-- Flipped and unflipped sprites produce identical vertices to the current code.
-- An optimized deterministic benchmark shows at least a 10% improvement in
-  isolated `draw_sprite` time under comparable conditions.
-- Do not add a per-sprite frame cache as part of this issue.

Makefile

@@ -1,6 +1,5 @@
 .PHONY: shaders-vulkan shaders-d3d12 shaders-metal shaders-all bake toad hello_sprite crowd camera_sandbox clips check test help
 .PHONY: flame flame-build flame-record flame-svg flame-report flame-tools
-.PHONY: perf-draw perf-frame
 
 # Flamegraph profiling (needs: pacman -S perf). Example: make flame  or  make flame FLAME_EXAMPLE=toad
 FLAME_EXAMPLE ?= crowd
@@ -13,19 +12,6 @@ FLAME_STAMP := $(shell date +%Y%m%d-%H%M%S)
 endif
 FLAME_PREFIX := $(FLAME_OUT_DIR)/$(FLAME_EXAMPLE)-$(FLAME_STAMP)
 
-PERF_DRAW_ITERATIONS ?= 2000000
-PERF_DRAW_WARMUP ?= 10000
-PERF_DRAW_TRIALS ?= 7
-PERF_ODIN_FLAGS ?= -debug -o:speed
-PERF_FRAME_SPRITES ?= 128
-PERF_FRAME_FRAMES ?= 400
-PERF_FRAME_WARMUP ?= 100
-PERF_FRAME_TRIALS ?= 10
-# 0=visible, 1=half offscreen, 2=alternating textures, 3=stacked
-PERF_FRAME_SCENARIO ?= 0
-PERF_FRAME_WIDTH ?= 800
-PERF_FRAME_HEIGHT ?= 600
-
 help:
 	@echo "Targets:"
 	@echo "  bake             Bake all characters under content/characters/"
@@ -41,12 +27,10 @@ help:
 	@echo "  camera_sandbox   Pan camera / Space toggles follow"
 	@echo "  clips            Keys 1/2 switch idle/walk"
 	@echo "  flame            Build+record+SVG+JPG+text report (FLAME_EXAMPLE=$(FLAME_EXAMPLE))"
-	@echo "  flame-build      Debug binary only ($(FLAME_BIN))"
+	@echo "  flame-build      Optimized debug binary ($(FLAME_BIN))"
 	@echo "  flame-record     perf record (play, then quit)"
 	@echo "  flame-svg        Convert perf.data -> $(FLAME_PREFIX).svg/.jpg"
 	@echo "  flame-report     Convert perf.data -> $(FLAME_PREFIX)-report.txt"
-	@echo "  perf-draw        Deterministic CPU draw benchmark"
-	@echo "  perf-frame       Deterministic SDL GPU frame benchmark (scenario 0/1/2/3)"
 
 bake:
 	./scripts/bake_all.sh
@@ -73,28 +57,6 @@ check:
 	odin check examples/camera_sandbox -collection:pkg=.
 	odin check examples/clips -collection:pkg=.
 
-perf-draw:
-	@echo "git_commit=$$(git rev-parse HEAD)"
-	@echo "odin_version=$$(odin version)"
-	@echo "odin_flags=$(PERF_ODIN_FLAGS)"
-	odin run benchmarks/draw_sprite -collection:pkg=. $(PERF_ODIN_FLAGS) \
-		-define:PERF_ITERATIONS=$(PERF_DRAW_ITERATIONS) \
-		-define:PERF_WARMUP=$(PERF_DRAW_WARMUP) \
-		-define:PERF_TRIALS=$(PERF_DRAW_TRIALS)
-
-perf-frame:
-	@echo "git_commit=$$(git rev-parse HEAD)"
-	@echo "odin_version=$$(odin version)"
-	@echo "odin_flags=$(PERF_ODIN_FLAGS)"
-	odin run benchmarks/sprite_frame -collection:pkg=. $(PERF_ODIN_FLAGS) \
-		-define:PERF_SPRITES=$(PERF_FRAME_SPRITES) \
-		-define:PERF_FRAMES=$(PERF_FRAME_FRAMES) \
-		-define:PERF_WARMUP_FRAMES=$(PERF_FRAME_WARMUP) \
-		-define:PERF_TRIALS=$(PERF_FRAME_TRIALS) \
-		-define:PERF_SCENARIO=$(PERF_FRAME_SCENARIO) \
-		-define:PERF_WIDTH=$(PERF_FRAME_WIDTH) \
-		-define:PERF_HEIGHT=$(PERF_FRAME_HEIGHT)
-
 toad:
 	odin run examples/toad -collection:pkg=.
 
@@ -117,7 +79,7 @@ flame-tools:
 	fi
 
 flame-build:
-	odin build examples/$(FLAME_EXAMPLE) -collection:pkg=. -out:$(FLAME_BIN) -debug
+	odin build examples/$(FLAME_EXAMPLE) -collection:pkg=. -out:$(FLAME_BIN) -debug -o:speed
 
 flame-record: flame-build
 	@echo ">>> Profiling ./$(FLAME_BIN) — play for ~10–20s under load, then quit the window."

benchmarks/draw_sprite/main.odin

@@ -1,102 +0,0 @@
-package main
-
-import "core:fmt"
-import "core:os"
-import eng "pkg:engine"
-import sdl "vendor:sdl3"
-
-PERF_ITERATIONS :: #config(PERF_ITERATIONS, 2_000_000)
-PERF_WARMUP     :: #config(PERF_WARMUP, 10_000)
-PERF_TRIALS     :: #config(PERF_TRIALS, 7)
-
-@(private)
-median :: proc(values: []f64) -> f64 {
-	for i in 1 ..< len(values) {
-		value := values[i]
-		j := i
-		for j > 0 {
-			if values[j - 1] <= value do break
-			values[j] = values[j - 1]
-			j -= 1
-		}
-		values[j] = value
-	}
-
-	middle := len(values) / 2
-	if len(values) & 1 == 1 do return values[middle]
-	return (values[middle - 1] + values[middle]) / 2
-}
-
-@(private)
-run_draws :: proc(app: ^eng.App, sprite: ^eng.Sprite, iterations: int) -> u64 {
-	clear(&app.draw_list)
-	start := sdl.GetTicksNS()
-	for i in 0 ..< iterations {
-		if len(app.draw_list) >= eng.MAX_SPRITES {
-			clear(&app.draw_list)
-		}
-
-		// Vary an input so optimized builds cannot hoist the draw calculations.
-		sprite.position.x = f32(i & 1023)
-		eng.draw_sprite(app, sprite)
-	}
-	return sdl.GetTicksNS() - start
-}
-
-main :: proc() {
-	#assert(PERF_ITERATIONS > 0)
-	#assert(PERF_WARMUP > 0)
-	#assert(PERF_TRIALS > 0)
-
-	file_data, err := os.read_entire_file(
-		"assets_baked/characters/toad/toad.char.json",
-		context.allocator,
-	)
-	if err != nil {
-		fmt.eprintfln("benchmark asset read failed: %v", err)
-		return
-	}
-	defer delete(file_data)
-
-	def, ok := eng.parse_char_def(file_data)
-	if !ok do return
-
-	data := eng.Character_Data {
-		def     = def,
-		texture = cast(^sdl.GPUTexture)uintptr(1),
-		width   = 1911,
-		height  = 1526,
-	}
-	app := eng.App {
-		cmd               = cast(^sdl.GPUCommandBuffer)uintptr(1),
-		swapchain_texture = cast(^sdl.GPUTexture)uintptr(2),
-		swapchain_w       = 800,
-		swapchain_h       = 600,
-		camera             = eng.camera_default(),
-		draw_list          = make(
-			[dynamic]eng.Queued_Sprite,
-			0,
-			eng.MAX_SPRITES,
-		),
-	}
-	defer delete(app.draw_list)
-
-	sprite := eng.spawn_sprite(&data, {400, 400}, "walk", 4)
-	_ = run_draws(&app, &sprite, PERF_WARMUP)
-
-	samples: [PERF_TRIALS]f64
-	fmt.printfln(
-		"benchmark=draw_sprite iterations=%d warmup=%d trials=%d sprites_per_queue=%d",
-		PERF_ITERATIONS,
-		PERF_WARMUP,
-		PERF_TRIALS,
-		eng.MAX_SPRITES,
-	)
-	for trial in 0 ..< PERF_TRIALS {
-		elapsed := run_draws(&app, &sprite, PERF_ITERATIONS)
-		samples[trial] = f64(elapsed) / f64(PERF_ITERATIONS)
-		fmt.printfln("trial=%d ns_per_draw=%.3f", trial + 1, samples[trial])
-	}
-
-	fmt.printfln("median_ns_per_draw=%.3f", median(samples[:]))
-}

benchmarks/sprite_frame/main.odin

@@ -1,174 +0,0 @@
-package main
-
-import "core:fmt"
-import eng "pkg:engine"
-import sdl "vendor:sdl3"
-
-PERF_SPRITES      :: #config(PERF_SPRITES, 128)
-PERF_FRAMES       :: #config(PERF_FRAMES, 400)
-PERF_WARMUP_FRAMES :: #config(PERF_WARMUP_FRAMES, 100)
-PERF_TRIALS       :: #config(PERF_TRIALS, 10)
-PERF_SCENARIO     :: #config(PERF_SCENARIO, 0)
-PERF_WIDTH        :: #config(PERF_WIDTH, 800)
-PERF_HEIGHT       :: #config(PERF_HEIGHT, 600)
-
-Scenario :: enum {
-	Visible,
-	Half_Offscreen,
-	Alternating_Textures,
-	Stacked,
-}
-
-@(private)
-median :: proc(values: []f64) -> f64 {
-	for i in 1 ..< len(values) {
-		value := values[i]
-		j := i
-		for j > 0 {
-			if values[j - 1] <= value do break
-			values[j] = values[j - 1]
-			j -= 1
-		}
-		values[j] = value
-	}
-
-	middle := len(values) / 2
-	if len(values) & 1 == 1 do return values[middle]
-	return (values[middle - 1] + values[middle]) / 2
-}
-
-@(private)
-scenario_name :: proc(scenario: Scenario) -> string {
-	switch scenario {
-	case .Visible:
-		return "visible"
-	case .Half_Offscreen:
-		return "half_offscreen"
-	case .Alternating_Textures:
-		return "alternating_textures"
-	case .Stacked:
-		return "stacked"
-	}
-	return "unknown"
-}
-
-@(private)
-present_mode_name :: proc(app: ^eng.App) -> string {
-	if sdl.WindowSupportsGPUPresentMode(app.device, app.window, .IMMEDIATE) {
-		return "immediate"
-	}
-	if sdl.WindowSupportsGPUPresentMode(app.device, app.window, .MAILBOX) {
-		return "mailbox"
-	}
-	return "vsync"
-}
-
-@(private)
-draw_frame :: proc(app: ^eng.App, sprites: []eng.Sprite) {
-	for &sprite in sprites {
-		eng.update_sprite(&sprite, 1.0 / 60.0)
-	}
-
-	eng.begin_frame(app)
-	for &sprite in sprites {
-		eng.draw_sprite(app, &sprite)
-	}
-	eng.end_frame(app)
-}
-
-main :: proc() {
-	#assert(PERF_SPRITES > 0)
-	#assert(PERF_SPRITES <= eng.MAX_SPRITES)
-	#assert(PERF_FRAMES > 0)
-	#assert(PERF_WARMUP_FRAMES > 0)
-	#assert(PERF_TRIALS > 0)
-	#assert(PERF_SCENARIO >= 0 && PERF_SCENARIO <= 3)
-	#assert(PERF_WIDTH > 0)
-	#assert(PERF_HEIGHT > 0)
-
-	scenario := Scenario(PERF_SCENARIO)
-
-	app: eng.App
-	if !eng.init(&app, "sprite frame benchmark", PERF_WIDTH, PERF_HEIGHT) {
-		return
-	}
-	defer eng.shutdown(&app)
-
-	path := "assets_baked/characters/toad/toad.char.json"
-	data_a, ok := eng.load_character_data(&app, path)
-	if !ok do return
-	defer eng.destroy_character_data(&app, &data_a)
-
-	data_b: eng.Character_Data
-	data_b, ok = eng.load_character_data(&app, path)
-	if !ok do return
-	defer eng.destroy_character_data(&app, &data_b)
-
-	sprites: [PERF_SPRITES]eng.Sprite
-	for i in 0 ..< PERF_SPRITES {
-		data := &data_a
-		if scenario == .Alternating_Textures && (i & 1) == 1 {
-			data = &data_b
-		}
-
-		position := eng.Vec2 {
-			f32(40 + (i % 16) * 48),
-			f32(120 + (i / 16) * 60),
-		}
-		if scenario == .Half_Offscreen && (i & 1) == 1 {
-			position = {-10_000, -10_000}
-		} else if scenario == .Stacked {
-			position = {f32(PERF_WIDTH / 2), f32(PERF_HEIGHT / 2)}
-		}
-		sprites[i] = eng.spawn_sprite(data, position, "walk", i % 17)
-	}
-
-	for _ in 0 ..< PERF_WARMUP_FRAMES {
-		draw_frame(&app, sprites[:])
-	}
-	if !sdl.WaitForGPUIdle(app.device) {
-		fmt.eprintfln("GPU wait failed after warm-up: %s", sdl.GetError())
-		return
-	}
-
-	fmt.printfln(
-		"benchmark=sprite_frame scenario=%s sprites=%d resolution=%dx%d frames=%d warmup=%d trials=%d backend=%v driver=%s present=%s",
-		scenario_name(scenario),
-		PERF_SPRITES,
-		PERF_WIDTH,
-		PERF_HEIGHT,
-		PERF_FRAMES,
-		PERF_WARMUP_FRAMES,
-		PERF_TRIALS,
-		app.shader.backend,
-		sdl.GetGPUDeviceDriver(app.device),
-		present_mode_name(&app),
-	)
-
-	samples: [PERF_TRIALS]f64
-	for trial in 0 ..< PERF_TRIALS {
-		start := sdl.GetTicksNS()
-		for _ in 0 ..< PERF_FRAMES {
-			draw_frame(&app, sprites[:])
-		}
-		if !sdl.WaitForGPUIdle(app.device) {
-			fmt.eprintfln("GPU wait failed after trial %d: %s", trial + 1, sdl.GetError())
-			return
-		}
-		elapsed := sdl.GetTicksNS() - start
-		samples[trial] = f64(elapsed) / f64(PERF_FRAMES) / 1_000_000.0
-		fmt.printfln(
-			"trial=%d ms_per_frame=%.3f fps=%.1f",
-			trial + 1,
-			samples[trial],
-			1_000.0 / samples[trial],
-		)
-	}
-
-	median_ms := median(samples[:])
-	fmt.printfln(
-		"median_ms_per_frame=%.3f median_fps=%.1f",
-		median_ms,
-		1_000.0 / median_ms,
-	)
-}

engine/animation_test.odin

@@ -118,6 +118,32 @@ set_sprite_clip_switch_and_guards :: proc(t: ^testing.T) {
 	testing.expect_value(t, sprite.time, f32(0.09))
 }
 
+@(test)
+set_sprite_clip_caches_clip_def :: proc(t: ^testing.T) {
+	data := make_test_character()
+	defer destroy_test_character(&data)
+
+	sprite := spawn_sprite(&data, {}, "idle", 0)
+	testing.expect(t, sprite.has_clip, "spawn should cache a valid clip")
+	testing.expect_value(t, sprite.clip, "idle")
+	testing.expect(t, sprite.clip_def.loop, "idle clip loops")
+	testing.expect_value(t, sprite.clip_def.fps, f32(10))
+	testing.expect_value(t, len(sprite.clip_def.frames), 3)
+
+	set_sprite_clip(&sprite, "once")
+	testing.expect(t, sprite.has_clip, "switch should refresh cache")
+	testing.expect_value(t, sprite.clip, "once")
+	testing.expect(t, !sprite.clip_def.loop, "once clip does not loop")
+	testing.expect_value(t, sprite.clip_def.fps, f32(10))
+	testing.expect_value(t, len(sprite.clip_def.frames), 3)
+
+	set_sprite_clip(&sprite, "nope")
+	testing.expect(t, sprite.has_clip, "bad clip must leave cache intact")
+	testing.expect_value(t, sprite.clip, "once")
+	testing.expect(t, !sprite.clip_def.loop, "cached once clip preserved")
+	testing.expect_value(t, len(sprite.clip_def.frames), 3)
+}
+
 @(test)
 spawn_sprite_valid_and_invalid :: proc(t: ^testing.T) {
 	data := make_test_character()

engine/app.odin

@@ -16,8 +16,15 @@ SPRITE_VERTS_SIZE :: SPRITE_VERT_COUNT * size_of(Vertex)
 VERTEX_BUFFER_SIZE :: MAX_SPRITES * SPRITE_VERTS_SIZE
 
 Queued_Sprite :: struct {
+	texture:     ^sdl.GPUTexture,
+	verts:       [SPRITE_VERT_COUNT]Vertex,
+	batch_group: u32, // 0 = strict order; nonzero = caller permits regrouping
+}
+
+Draw_Batch :: struct {
+	start:   int,
+	count:   int,
 	texture: ^sdl.GPUTexture,
-	verts:   [SPRITE_VERT_COUNT]Vertex,
 }
 
 App :: struct {
@@ -65,7 +72,7 @@ init :: proc(app: ^App, title: cstring, width, height: i32) -> bool {
 	}
 
 	requested: sdl.GPUShaderFormat = {.SPIRV, .DXIL, .MSL}
-	app.device = sdl.CreateGPUDevice(requested, true, nil)
+	app.device = sdl.CreateGPUDevice(requested, false, nil)
 	if app.device == nil {
 		fmt.eprintfln("CreateGPUDevice failed: %s", sdl.GetError())
 		return false
@@ -76,6 +83,10 @@ init :: proc(app: ^App, title: cstring, width, height: i32) -> bool {
 		return false
 	}
 
+	if !sdl.SetGPUAllowedFramesInFlight(app.device, 3) {
+		fmt.eprintfln("SetGPUAllowedFramesInFlight failed: %s", sdl.GetError())
+	}
+
 	// Prefer uncapped present for profiling; fall back if unsupported.
 	present := sdl.GPUPresentMode.VSYNC
 	if sdl.WindowSupportsGPUPresentMode(app.device, app.window, .IMMEDIATE) {
@@ -242,7 +253,11 @@ end_frame :: proc(app: ^App) {
 	}
 
 	n := len(app.draw_list)
+	batches: [dynamic]Draw_Batch
+	defer delete(batches)
 	if n > 0 {
+		prepare_draw_batches(app.draw_list[:], &batches)
+
 		map_ptr := sdl.MapGPUTransferBuffer(app.device, app.transfer_buffer, false)
 		if map_ptr == nil {
 			fmt.eprintfln("MapGPUTransferBuffer failed: %s", sdl.GetError())
@@ -286,26 +301,20 @@ end_frame :: proc(app: ^App) {
 	app.render_pass = sdl.BeginGPURenderPass(cmd, &color_info, 1, nil)
 	sdl.BindGPUGraphicsPipeline(app.render_pass, app.pipeline)
 
-	i := 0
-	for i < n {
-		run := texture_run_len(app.draw_list[:], i)
-		q0 := app.draw_list[i]
-
+	for batch in batches {
 		sampler_binding := sdl.GPUTextureSamplerBinding {
-			texture = q0.texture,
+			texture = batch.texture,
 			sampler = app.sampler,
 		}
 		sdl.BindGPUFragmentSamplers(app.render_pass, 0, &sampler_binding, 1)
 
 		vb_binding := sdl.GPUBufferBinding {
 			buffer = app.vertex_buffer,
-			offset = u32(i * SPRITE_VERTS_SIZE),
+			offset = u32(batch.start * SPRITE_VERTS_SIZE),
 		}
 		sdl.BindGPUVertexBuffers(app.render_pass, 0, &vb_binding, 1)
 
-		sdl.DrawGPUPrimitives(app.render_pass, u32(run * SPRITE_VERT_COUNT), 1, 0, 0)
-
-		i += run
+		sdl.DrawGPUPrimitives(app.render_pass, u32(batch.count * SPRITE_VERT_COUNT), 1, 0, 0)
 	}
 	sdl.EndGPURenderPass(app.render_pass)
 	app.render_pass = nil
@@ -454,3 +463,119 @@ texture_run_len :: proc(list: []Queued_Sprite, start: int) -> int {
 
 	return n
 }
+
+texture_run_count :: proc(list: []Queued_Sprite) -> int {
+	if len(list) == 0 do return 0
+	count := 0
+	i := 0
+	for i < len(list) {
+		run := texture_run_len(list, i)
+		count += 1
+		i += run
+	}
+	return count
+}
+
+prepare_draw_batches :: proc(list: []Queued_Sprite, batches: ^[dynamic]Draw_Batch) {
+	clear(batches)
+	group_texture_runs(list)
+	i := 0
+	for i < len(list) {
+		run := texture_run_len(list, i)
+		append(batches, Draw_Batch{start = i, count = run, texture = list[i].texture})
+		i += run
+	}
+}
+
+// Within each contiguous nonzero batch_group, stably sort by texture so
+// consecutive same-texture sprites become one draw. Group 0 and group
+// boundaries are never crossed.
+group_texture_runs :: proc(list: []Queued_Sprite) {
+	start := 0
+	for start < len(list) {
+		group := list[start].batch_group
+		if group == 0 {
+			start += 1
+			continue
+		}
+
+		end := start + 1
+		for end < len(list) && list[end].batch_group == group {
+			end += 1
+		}
+
+		stable_group_by_texture(list[start:end])
+		start = end
+	}
+}
+
+// Stably orders window by texture pointer. Fast path for 1–2 textures
+// (common); insertion sort for 3+.
+stable_group_by_texture :: proc(window: []Queued_Sprite) {
+	n := len(window)
+	if n <= 1 do return
+
+	already := true
+	for i in 1 ..< n {
+		if uintptr(window[i].texture) < uintptr(window[i - 1].texture) {
+			already = false
+			break
+		}
+	}
+	if already do return
+
+	first := uintptr(window[0].texture)
+	second: uintptr
+	has_second := false
+	third := false
+	for i in 1 ..< n {
+		t := uintptr(window[i].texture)
+		if t == first do continue
+		if !has_second {
+			second = t
+			has_second = true
+			continue
+		}
+		if t != second {
+			third = true
+			break
+		}
+	}
+
+	if !has_second do return
+
+	if third {
+		for i in 1 ..< n {
+			item := window[i]
+			j := i
+			for j > 0 {
+				if uintptr(window[j - 1].texture) <= uintptr(item.texture) {
+					break
+				}
+				window[j] = window[j - 1]
+				j -= 1
+			}
+			window[j] = item
+		}
+		return
+	}
+
+	lo, hi := first, second
+	if lo > hi do lo, hi = hi, lo
+
+	tmp: [MAX_SPRITES]Queued_Sprite
+	w := 0
+	for q in window {
+		if uintptr(q.texture) == lo {
+			tmp[w] = q
+			w += 1
+		}
+	}
+	for q in window {
+		if uintptr(q.texture) == hi {
+			tmp[w] = q
+			w += 1
+		}
+	}
+	copy(window, tmp[:w])
+}

engine/batching_test.odin

@@ -7,6 +7,18 @@ fake_tex :: proc(id: uintptr) -> ^sdl.GPUTexture {
 	return cast(^sdl.GPUTexture)id
 }
 
+queued :: proc(tex_id: uintptr, group: u32, marker: f32) -> Queued_Sprite {
+	q: Queued_Sprite
+	q.texture = fake_tex(tex_id)
+	q.batch_group = group
+	q.verts[0].pos = {marker, 0}
+	return q
+}
+
+marker_of :: proc(q: Queued_Sprite) -> f32 {
+	return q.verts[0].pos.x
+}
+
 @(test)
 texture_run_len_empty_or_oob :: proc(t: ^testing.T) {
 	testing.expect_value(t, texture_run_len(nil, 0), 0)
@@ -62,3 +74,356 @@ texture_run_len_all_different :: proc(t: ^testing.T) {
 	testing.expect_value(t, texture_run_len(list, 1), 1)
 	testing.expect_value(t, texture_run_len(list, 2), 1)
 }
+
+@(test)
+group_texture_runs_strict_order_unchanged :: proc(t: ^testing.T) {
+	// Group 0 alternates textures; sorting must not reorder (alpha order).
+	list := []Queued_Sprite {
+		queued(2, 0, 1),
+		queued(1, 0, 2),
+		queued(2, 0, 3),
+		queued(1, 0, 4),
+	}
+	before_runs := texture_run_count(list)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), before_runs)
+	testing.expect_value(t, marker_of(list[0]), f32(1))
+	testing.expect_value(t, marker_of(list[1]), f32(2))
+	testing.expect_value(t, marker_of(list[2]), f32(3))
+	testing.expect_value(t, marker_of(list[3]), f32(4))
+}
+
+@(test)
+group_texture_runs_reduces_runs_inside_group :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(2, 1, 1),
+		queued(1, 1, 2),
+		queued(2, 1, 3),
+		queued(1, 1, 4),
+	}
+	testing.expect_value(t, texture_run_count(list), 4)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 2)
+	testing.expect(t, list[0].texture == fake_tex(1), "lower texture pointer first")
+	testing.expect(t, list[1].texture == fake_tex(1), "same texture run")
+	testing.expect(t, list[2].texture == fake_tex(2), "second texture run")
+	testing.expect(t, list[3].texture == fake_tex(2), "second texture run cont")
+}
+
+@(test)
+group_texture_runs_stable_same_texture :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(2, 1, 10),
+		queued(1, 1, 20),
+		queued(2, 1, 30),
+		queued(1, 1, 40),
+	}
+	group_texture_runs(list)
+	// Same-texture relative order preserved (stable sort).
+	testing.expect_value(t, marker_of(list[0]), f32(20))
+	testing.expect_value(t, marker_of(list[1]), f32(40))
+	testing.expect_value(t, marker_of(list[2]), f32(10))
+	testing.expect_value(t, marker_of(list[3]), f32(30))
+}
+
+@(test)
+group_texture_runs_respects_group_boundaries :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(2, 1, 1),
+		queued(1, 1, 2),
+		queued(2, 0, 3), // strict barrier
+		queued(1, 2, 4),
+		queued(2, 2, 5),
+	}
+	group_texture_runs(list)
+	testing.expect_value(t, marker_of(list[2]), f32(3)) // barrier stays put
+	testing.expect(t, list[0].texture == fake_tex(1))
+	testing.expect(t, list[1].texture == fake_tex(2))
+	testing.expect(t, list[3].texture == fake_tex(1))
+	testing.expect(t, list[4].texture == fake_tex(2))
+	testing.expect_value(t, list[0].batch_group, u32(1))
+	testing.expect_value(t, list[1].batch_group, u32(1))
+	testing.expect_value(t, list[2].batch_group, u32(0))
+	testing.expect_value(t, list[3].batch_group, u32(2))
+	testing.expect_value(t, list[4].batch_group, u32(2))
+}
+
+@(test)
+group_texture_runs_does_not_merge_across_different_groups :: proc(t: ^testing.T) {
+	// Adjacent nonzero groups with different ids must not merge runs across.
+	list := []Queued_Sprite {
+		queued(1, 1, 1),
+		queued(2, 1, 2),
+		queued(1, 2, 3),
+		queued(2, 2, 4),
+	}
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 4)
+	testing.expect_value(t, list[0].batch_group, u32(1))
+	testing.expect_value(t, list[1].batch_group, u32(1))
+	testing.expect_value(t, list[2].batch_group, u32(2))
+	testing.expect_value(t, list[3].batch_group, u32(2))
+}
+
+@(test)
+group_texture_runs_empty :: proc(t: ^testing.T) {
+	list := []Queued_Sprite{}
+	testing.expect_value(t, texture_run_count(list), 0)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 0)
+}
+
+@(test)
+group_texture_runs_already_optimal :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(1, 1, 10),
+		queued(1, 1, 20),
+		queued(2, 1, 30),
+		queued(2, 1, 40),
+	}
+	testing.expect_value(t, texture_run_count(list), 2)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 2)
+	testing.expect_value(t, marker_of(list[0]), f32(10))
+	testing.expect_value(t, marker_of(list[1]), f32(20))
+	testing.expect_value(t, marker_of(list[2]), f32(30))
+	testing.expect_value(t, marker_of(list[3]), f32(40))
+}
+
+@(test)
+group_texture_runs_alternating_many_stable :: proc(t: ^testing.T) {
+	// Characterization: large alternating group must collapse to two runs
+	// while preserving same-texture submission order (markers).
+	N :: 64
+	list := make([]Queued_Sprite, N)
+	defer delete(list)
+	for i in 0 ..< N {
+		tex: uintptr = 2 if (i % 2) == 0 else 1
+		list[i] = queued(tex, 1, f32(i + 1))
+	}
+	testing.expect_value(t, texture_run_count(list), N)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 2)
+	testing.expect(t, list[0].texture == fake_tex(1))
+	testing.expect(t, list[N / 2 - 1].texture == fake_tex(1))
+	testing.expect(t, list[N / 2].texture == fake_tex(2))
+	testing.expect(t, list[N - 1].texture == fake_tex(2))
+	for i in 0 ..< N / 2 {
+		testing.expect_value(t, marker_of(list[i]), f32(2 * i + 2)) // odd markers: 2,4,...,N
+		testing.expect_value(t, marker_of(list[N / 2 + i]), f32(2 * i + 1)) // even markers: 1,3,...,N-1
+	}
+}
+
+@(test)
+group_texture_runs_three_textures_stable :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(3, 1, 1),
+		queued(1, 1, 2),
+		queued(2, 1, 3),
+		queued(3, 1, 4),
+		queued(1, 1, 5),
+		queued(2, 1, 6),
+	}
+	testing.expect_value(t, texture_run_count(list), 6)
+	group_texture_runs(list)
+	testing.expect_value(t, texture_run_count(list), 3)
+	testing.expect_value(t, marker_of(list[0]), f32(2))
+	testing.expect_value(t, marker_of(list[1]), f32(5))
+	testing.expect_value(t, marker_of(list[2]), f32(3))
+	testing.expect_value(t, marker_of(list[3]), f32(6))
+	testing.expect_value(t, marker_of(list[4]), f32(1))
+	testing.expect_value(t, marker_of(list[5]), f32(4))
+}
+
+@(test)
+group_texture_runs_noncontiguous_same_group_id :: proc(t: ^testing.T) {
+	// Same nonzero id split by group 0: each window regroups alone.
+	list := []Queued_Sprite {
+		queued(2, 1, 1),
+		queued(1, 1, 2),
+		queued(2, 0, 3),
+		queued(2, 1, 4),
+		queued(1, 1, 5),
+	}
+	group_texture_runs(list)
+	testing.expect_value(t, marker_of(list[2]), f32(3))
+	testing.expect(t, list[0].texture == fake_tex(1))
+	testing.expect(t, list[1].texture == fake_tex(2))
+	testing.expect_value(t, list[2].batch_group, u32(0))
+	testing.expect(t, list[3].texture == fake_tex(1))
+	testing.expect(t, list[4].texture == fake_tex(2))
+	testing.expect_value(t, list[0].batch_group, u32(1))
+	testing.expect_value(t, list[1].batch_group, u32(1))
+	testing.expect_value(t, list[3].batch_group, u32(1))
+	testing.expect_value(t, list[4].batch_group, u32(1))
+}
+
+make_test_draw_app :: proc() -> App {
+	app: App
+	app.cmd = cast(^sdl.GPUCommandBuffer)uintptr(1)
+	app.swapchain_texture = fake_tex(99)
+	app.swapchain_w = 800
+	app.swapchain_h = 600
+	app.camera = camera_default()
+	app.draw_list = make([dynamic]Queued_Sprite)
+	return app
+}
+
+destroy_test_draw_app :: proc(app: ^App) {
+	if app == nil do return
+	delete(app.draw_list)
+	app^ = {}
+}
+
+make_test_draw_character :: proc() -> Character_Data {
+	data: Character_Data
+	data.texture = fake_tex(42)
+	data.width = 100
+	data.height = 100
+	data.def.pivot = {0.5, 1.0}
+	data.def.clips = make(map[string]Clip_Def)
+	frames := make([]Frame_Def, 1)
+	frames[0] = Frame_Def {
+		rect        = {0, 0, 10, 10},
+		source_size = {10, 10},
+		trim_offset = {0, 0},
+	}
+	data.def.clips["idle"] = Clip_Def {
+		loop   = true,
+		fps    = 10,
+		frames = frames,
+	}
+	return data
+}
+
+destroy_test_draw_character :: proc(data: ^Character_Data) {
+	if data == nil do return
+	keys := make([dynamic]string, context.temp_allocator)
+	for key, clip in data.def.clips {
+		delete(clip.frames)
+		append(&keys, key)
+	}
+	for key in keys {
+		delete_key(&data.def.clips, key)
+	}
+	delete(data.def.clips)
+	data^ = {}
+}
+
+@(test)
+draw_sprite_stamps_batch_group_zero :: proc(t: ^testing.T) {
+	app := make_test_draw_app()
+	defer destroy_test_draw_app(&app)
+	data := make_test_draw_character()
+	defer destroy_test_draw_character(&data)
+
+	sprite := spawn_sprite(&data, {100, 200}, "idle", 0)
+	draw_sprite(&app, &sprite)
+
+	testing.expect_value(t, len(app.draw_list), 1)
+	testing.expect_value(t, app.draw_list[0].batch_group, u32(0))
+	testing.expect(t, app.draw_list[0].texture == data.texture)
+}
+
+@(test)
+draw_sprite_at_max_sprites_does_not_append :: proc(t: ^testing.T) {
+	app := make_test_draw_app()
+	defer destroy_test_draw_app(&app)
+	data := make_test_draw_character()
+	defer destroy_test_draw_character(&data)
+
+	for _ in 0 ..< MAX_SPRITES {
+		append(&app.draw_list, Queued_Sprite{texture = data.texture})
+	}
+	testing.expect_value(t, len(app.draw_list), MAX_SPRITES)
+
+	sprite := spawn_sprite(&data, {100, 200}, "idle", 0)
+	draw_sprite(&app, &sprite)
+
+	testing.expect_value(t, len(app.draw_list), MAX_SPRITES)
+}
+
+@(test)
+draw_sprite_batched_stamps_batch_group :: proc(t: ^testing.T) {
+	app := make_test_draw_app()
+	defer destroy_test_draw_app(&app)
+	data := make_test_draw_character()
+	defer destroy_test_draw_character(&data)
+
+	sprite := spawn_sprite(&data, {100, 200}, "idle", 0)
+	draw_sprite_batched(&app, &sprite, 7)
+
+	testing.expect_value(t, len(app.draw_list), 1)
+	testing.expect_value(t, app.draw_list[0].batch_group, u32(7))
+	testing.expect(t, app.draw_list[0].texture == data.texture)
+}
+
+@(test)
+draw_sprite_batched_guards_leave_list_unchanged :: proc(t: ^testing.T) {
+	app := make_test_draw_app()
+	defer destroy_test_draw_app(&app)
+	data := make_test_draw_character()
+	defer destroy_test_draw_character(&data)
+	sprite := spawn_sprite(&data, {100, 200}, "idle", 0)
+
+	app.cmd = nil
+	draw_sprite_batched(&app, &sprite, 1)
+	testing.expect_value(t, len(app.draw_list), 0)
+	app.cmd = cast(^sdl.GPUCommandBuffer)uintptr(1)
+
+	app.swapchain_texture = nil
+	draw_sprite_batched(&app, &sprite, 1)
+	testing.expect_value(t, len(app.draw_list), 0)
+	app.swapchain_texture = fake_tex(99)
+
+	draw_sprite_batched(&app, nil, 1)
+	testing.expect_value(t, len(app.draw_list), 0)
+
+	no_data := sprite
+	no_data.data = nil
+	draw_sprite_batched(&app, &no_data, 1)
+	testing.expect_value(t, len(app.draw_list), 0)
+
+	no_tex := sprite
+	tex_data := data
+	tex_data.texture = nil
+	no_tex.data = &tex_data
+	draw_sprite_batched(&app, &no_tex, 1)
+	testing.expect_value(t, len(app.draw_list), 0)
+}
+
+@(test)
+prepare_draw_batches_regroups_then_plans_runs :: proc(t: ^testing.T) {
+	list := []Queued_Sprite {
+		queued(2, 1, 1),
+		queued(1, 1, 2),
+		queued(2, 1, 3),
+		queued(1, 1, 4),
+		queued(3, 0, 5),
+		queued(1, 0, 6),
+	}
+	batches := make([dynamic]Draw_Batch)
+	defer delete(batches)
+
+	prepare_draw_batches(list, &batches)
+
+	testing.expect_value(t, len(batches), 4)
+	testing.expect_value(t, batches[0].start, 0)
+	testing.expect_value(t, batches[0].count, 2)
+	testing.expect(t, batches[0].texture == fake_tex(1))
+	testing.expect_value(t, batches[1].start, 2)
+	testing.expect_value(t, batches[1].count, 2)
+	testing.expect(t, batches[1].texture == fake_tex(2))
+	testing.expect_value(t, batches[2].start, 4)
+	testing.expect_value(t, batches[2].count, 1)
+	testing.expect(t, batches[2].texture == fake_tex(3))
+	testing.expect_value(t, batches[3].start, 5)
+	testing.expect_value(t, batches[3].count, 1)
+	testing.expect(t, batches[3].texture == fake_tex(1))
+
+	// Group 0 submission order preserved.
+	testing.expect_value(t, marker_of(list[4]), f32(5))
+	testing.expect_value(t, marker_of(list[5]), f32(6))
+	testing.expect_value(t, list[4].batch_group, u32(0))
+	testing.expect_value(t, list[5].batch_group, u32(0))
+}

engine/shader_backend_test.odin

@@ -27,6 +27,15 @@ choose_shader_runtime_prefers_msl :: proc(t: ^testing.T) {
 	testing.expect_value(t, rt.format, sdl.GPUShaderFormat{.MSL})
 }
 
+@(test)
+choose_shader_runtime_prefers_dxil_without_msl :: proc(t: ^testing.T) {
+	rt, ok := choose_shader_runtime_from_formats({.DXIL, .SPIRV})
+	testing.expect(t, ok, "should pick a runtime when DXIL is available")
+	testing.expect_value(t, rt.backend, Shader_Backend.DSD12_DXIL)
+	testing.expect_value(t, rt.shader_dir, "shaders/d3d12")
+	testing.expect_value(t, rt.format, sdl.GPUShaderFormat{.DXIL})
+}
+
 @(test)
 choose_shader_runtime_spirv_only :: proc(t: ^testing.T) {
 	rt, ok := choose_shader_runtime_from_formats({.SPIRV})

engine/sprite.odin

@@ -5,12 +5,14 @@ import sdl "vendor:sdl3"
 Vec2 :: [2]f32
 
 Sprite :: struct {
-	data:     ^Character_Data,
-	position: Vec2,
-	clip:     string,
-	frame:    int,
-	time:     f32,
-	flip_x:   bool,
+	data:      ^Character_Data,
+	position:  Vec2,
+	clip:      string,
+	clip_def:  Clip_Def,
+	has_clip:  bool,
+	frame:     int,
+	time:      f32,
+	flip_x:    bool,
 }
 
 spawn_sprite :: proc(
@@ -24,16 +26,14 @@ spawn_sprite :: proc(
 		position = position,
 	}
 	set_sprite_clip(&sprite, clip)
-	if frame != 0 {
-		c, ok := character_clip(sprite.data, sprite.clip)
-		if ok {
-			if frame < 0 {
-				sprite.frame = 0
-			} else if frame >= len(c.frames) {
-				sprite.frame = len(c.frames) - 1
-			} else {
-				sprite.frame = frame
-			}
+	if frame != 0 && sprite.has_clip {
+		c := sprite.clip_def
+		if frame < 0 {
+			sprite.frame = 0
+		} else if frame >= len(c.frames) {
+			sprite.frame = len(c.frames) - 1
+		} else {
+			sprite.frame = frame
 		}
 	}
 	return sprite
@@ -42,9 +42,9 @@ spawn_sprite :: proc(
 update_sprite :: proc(sprite: ^Sprite, dt: f32) {
 	if sprite == nil || sprite.data == nil do return
 	if dt <= 0 do return
+	if !sprite.has_clip do return
 
-	clip, ok := character_clip(sprite.data, sprite.clip)
-	if !ok do return
+	clip := sprite.clip_def
 
 	frame_count := len(clip.frames)
 	if frame_count <= 0 do return
@@ -82,7 +82,31 @@ to_clip :: proc(px, py, sw, sh: f32) -> [2]f32 {
 	}
 }
 
+// Axis-aligned quad: two unique x and y values, so scale once and reuse.
+sprite_quad_to_clip :: proc(x0, y0, x1, y1, sw, sh: f32) -> [4]Vec2 {
+	sx := 2.0 / sw
+	sy := 2.0 / sh
+
+	left := x0 * sx - 1
+	right := x1 * sx - 1
+	top := 1 - y0 * sy
+	bottom := 1 - y1 * sy
+
+	return {
+		{left, top},
+		{right, top},
+		{right, bottom},
+		{left, bottom},
+	}
+}
+
 draw_sprite :: proc(app: ^App, sprite: ^Sprite) {
+	draw_sprite_batched(app, sprite, 0)
+}
+
+// Nonzero batch_group lets end_frame regroup consecutive same-group sprites by
+// texture. Group 0 keeps exact submission order for correct alpha overlap.
+draw_sprite_batched :: proc(app: ^App, sprite: ^Sprite, batch_group: u32) {
 	if app.cmd == nil || app.swapchain_texture == nil {
 		return
 	}
@@ -92,12 +116,13 @@ draw_sprite :: proc(app: ^App, sprite: ^Sprite) {
 	if len(app.draw_list) >= MAX_SPRITES {
 		return
 	}
-
-	frame, ok := character_frame(sprite.data, sprite.clip, sprite.frame)
-	if !ok {
+	if !sprite.has_clip do return
+	if sprite.frame < 0 || sprite.frame >= len(sprite.clip_def.frames) {
 		return
 	}
 
+	frame := sprite.clip_def.frames[sprite.frame]
+
 	src_w := f32(frame.source_size[0])
 	src_h := f32(frame.source_size[1])
 	if src_w <= 0 do src_w = f32(frame.rect[2])
@@ -124,10 +149,8 @@ draw_sprite :: proc(app: ^App, sprite: ^Sprite) {
 
 	sw := f32(app.swapchain_w)
 	sh := f32(app.swapchain_h)
-	p0 := to_clip(x0_px, y0_px, sw, sh)
-	p1 := to_clip(x1_px, y0_px, sw, sh)
-	p2 := to_clip(x1_px, y1_px, sw, sh)
-	p3 := to_clip(x0_px, y1_px, sw, sh)
+	points := sprite_quad_to_clip(x0_px, y0_px, x1_px, y1_px, sw, sh)
+	p0, p1, p2, p3 := points[0], points[1], points[2], points[3]
 
 	tex_w := f32(sprite.data.width)
 	tex_h := f32(sprite.data.height)
@@ -142,18 +165,27 @@ draw_sprite :: proc(app: ^App, sprite: ^Sprite) {
 		{pos = p3, uv = {u0, v1}},
 	}
 
-	append(&app.draw_list, Queued_Sprite{texture = sprite.data.texture, verts = verts})
+	append(
+		&app.draw_list,
+		Queued_Sprite {
+			texture = sprite.data.texture,
+			verts = verts,
+			batch_group = batch_group,
+		},
+	)
 }
 
 set_sprite_clip :: proc(sprite: ^Sprite, clip: string) {
 	if sprite == nil || sprite.data == nil do return
 
-	if sprite.clip == clip do return
+	if sprite.clip == clip && sprite.has_clip do return
 
-	_, ok := character_clip(sprite.data, clip)
+	def, ok := character_clip(sprite.data, clip)
 	if !ok do return
 
 	sprite.clip = clip
+	sprite.clip_def = def
+	sprite.has_clip = true
 	sprite.frame = 0
 	sprite.time = 0
 }

examples/crowd/main.odin

@@ -1,9 +1,12 @@
 package main
 
+import "core:fmt"
 import eng "pkg:engine"
 
 // Many sprites sharing one Character_Data (Flyweight) — good batching demo.
-COUNT :: 24
+COUNT :: eng.MAX_SPRITES
+COLS :: 16
+FRAME_LOG_EVERY :: 60
 
 main :: proc() {
 	app: eng.App
@@ -16,25 +19,45 @@ main :: proc() {
 
 	sprites: [COUNT]eng.Sprite
 	for i in 0 ..< COUNT {
-		col := i % 8
-		row := i / 8
+		col := i % COLS
+		row := i / COLS
 		pos := eng.Vec2 {
-			f32(120 + col * 80),
-			f32(280 + row * 120),
+			f32(40 + col * 48),
+			f32(80 + row * 60),
 		}
 		clip := "idle" if (i % 2) == 0 else "walk"
 		sprites[i] = eng.spawn_sprite(&data, pos, clip, i % 5)
 	}
 
-	// Look at the middle of the grid
 	app.camera.position = {400, 400}
 
 	last := eng.now_seconds()
+	frame_i := 0
+	sum_ms: f64
+	peak_ms: f64
 
 	for eng.events() {
 		now := eng.now_seconds()
 		dt := f32(now - last)
 		last = now
+		frame_ms := f64(dt) * 1000.0
+		sum_ms += frame_ms
+		if frame_ms > peak_ms do peak_ms = frame_ms
+		frame_i += 1
+
+		if frame_i % FRAME_LOG_EVERY == 0 {
+			avg := sum_ms / f64(FRAME_LOG_EVERY)
+			fps := 1000.0 / avg if avg > 0 else 0
+			fmt.printfln(
+				"crowd frame: avg=%.2f ms (%.1f FPS) peak=%.2f ms over %d frames",
+				avg,
+				fps,
+				peak_ms,
+				FRAME_LOG_EVERY,
+			)
+			sum_ms = 0
+			peak_ms = 0
+		}
 
 		for &s in sprites {
 			eng.update_sprite(&s, dt)

flame/crowd-20260809-140133-report.txt

@@ -0,0 +1,783 @@
+# To display the perf.data header info, please use --header/--header-only options.
+#
+#
+# Total Lost Samples: 0
+#
+# Samples: 1K of event 'cpu/cycles/Pu'
+# Event count (approx.): 8251313686
+#
+# Overhead  Command          Shared Object                   Symbol                                                                                                                                                                
+# ........  ...............  ..............................  ......................................................................................................................................................................
+#
+    10.24%  crowd_perf       crowd_perf                      [.] engine::draw_sprite
+            |
+            ---engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     5.73%  crowd_perf       crowd_perf                      [.] engine::to_clip
+            |
+            ---engine::to_clip
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     2.74%  crowd_perf       crowd_perf                      [.] runtime::default_hasher
+            |
+            ---runtime::default_hasher
+               runtime::default_hasher_string
+               __$hasher$$string
+               |          
+               |--2.10%--engine::character_clip
+               |          engine::update_sprite
+               |          main::main
+               |          main
+               |          0x7fec32c27740
+               |          __libc_start_main
+               |          _start
+               |          
+                --0.64%--engine::character_frame
+                          engine::draw_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     2.48%  crowd_perf       crowd_perf                      [.] engine::sprite_feet_quad
+            |
+            ---engine::sprite_feet_quad
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     2.16%  crowd_perf       libc.so.6                       [.] pthread_mutex_lock
+            |
+            ---pthread_mutex_lock
+               |          
+                --0.60%--wl_proxy_marshal_array_flags
+                          wl_proxy_marshal_flags
+
+     2.09%  crowd_perf       crowd_perf                      [.] __$map_get$$map[string]engine::Clip_Def
+            |
+            ---__$map_get$$map[string]engine::Clip_Def
+               |          
+               |--1.49%--engine::character_clip
+               |          engine::update_sprite
+               |          main::main
+               |          main
+               |          0x7fec32c27740
+               |          __libc_start_main
+               |          _start
+               |          
+                --0.60%--engine::character_frame
+                          engine::draw_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     2.04%  crowd_perf       crowd_perf                      [.] engine::update_sprite
+            |
+            ---engine::update_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     1.91%  crowd_perf       crowd_perf                      [.] runtime::memory_equal
+            |
+            ---runtime::memory_equal
+               runtime::string_eq
+               __$map_get$$map[string]engine::Clip_Def
+               |          
+               |--1.32%--engine::character_frame
+               |          engine::draw_sprite
+               |          main::main
+               |          main
+               |          0x7fec32c27740
+               |          __libc_start_main
+               |          _start
+               |          
+                --0.58%--engine::character_clip
+                          engine::update_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     1.90%  crowd_perf       crowd_perf                      [.] engine::character_clip
+            |
+            ---engine::character_clip
+               engine::update_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     1.85%  crowd_perf       crowd_perf                      [.] engine::world_to_screen
+            |
+            ---engine::world_to_screen
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     1.41%  crowd_perf       crowd_perf                      [.] runtime::_append_elem
+            |
+            ---runtime::_append_elem
+               runtime::append_elem:proc(array:^[dynamic]engine::Queued_Sprite,arg:engine::Queued_Sprite,loc:runtime::Source_Code_Location)->(n:int,err:runtime::Allocator_Error)
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     1.37%  crowd_perf       crowd_perf                      [.] engine::end_frame
+            |
+            ---engine::end_frame
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     1.15%  crowd_perf       libc.so.6                       [.] clock_gettime
+            |
+            ---clock_gettime
+
+     1.05%  crowd_perf       libdbus-1.so.3.38.3             [.] _dbus_atomic_dec
+            |
+            ---_dbus_atomic_dec
+               |          
+                --0.95%--_dbus_connection_unref_unlocked
+                          0x7fec32e8fbae
+                          0x7fec32e8fdad
+                          0x7fec32e94b31
+                          0x7fec33054fca
+                          0x7fec33055bbd
+                          engine::events
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.95%  crowd_perf       crowd_perf                      [.] main::main
+            |
+            ---main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     0.91%  crowd_perf       crowd_perf                      [.] runtime::append_elem:proc(array:^[dynamic]engine::Queued_Sprite,arg:engine::Queued_Sprite,loc:runtime::Source_Code_Location)->(n:int,err:runtime::Allocator_Error)
+            |
+            ---runtime::append_elem:proc(array:^[dynamic]engine::Queued_Sprite,arg:engine::Queued_Sprite,loc:runtime::Source_Code_Location)->(n:int,err:runtime::Allocator_Error)
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     0.91%  crowd_perf       libc.so.6                       [.] 0x000000000018a4c4
+            |
+            ---0x7fec32d8a4c4
+               |          
+                --0.82%--engine::draw_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.86%  crowd_perf       crowd_perf                      [.] runtime::string_eq
+            |
+            ---runtime::string_eq
+               __$map_get$$map[string]engine::Clip_Def
+               |          
+                --0.60%--engine::character_clip
+                          engine::update_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.84%  crowd_perf       crowd_perf                      [.] engine::character_frame
+            |
+            ---engine::character_frame
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     0.81%  crowd_perf       libwayland-client.so.0.25.0     [.] wl_proxy_marshal_array_flags
+            |
+            ---wl_proxy_marshal_array_flags
+               wl_proxy_marshal_flags
+
+     0.77%  crowd_perf       libc.so.6                       [.] 0x00000000000a7159
+            |
+            ---0x7fec32ca7159
+               |          
+                --0.61%--0x7fec12d80142
+                          0x7fec12d82613
+                          0x7fec12d3cff4
+                          0x7fec12ddcaf6
+                          0x7fec12ddccd4
+                          0x7fec12de6f2c
+                          0x7fec3324fec1
+                          engine::end_frame
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.74%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000093fff
+     0.73%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000143ffe
+            |
+            ---0x7fec33143ffe
+               0x7fec3314a028
+               0x7fec33141b9a
+
+     0.73%  crowd_perf       crowd_perf                      [.] runtime::bounds_check_error
+            |
+            ---runtime::bounds_check_error
+               |          
+                --0.53%--engine::character_frame
+                          engine::draw_sprite
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.71%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f41b7
+            |
+            ---0x7fec12df41b7
+               0x7fec12df44e5
+               |          
+                --0.59%--0x7fec12c2baf6
+                          0x7fec12c2da03
+                          0x7fec12c2e4ca
+                          0x7fec12c2f277
+                          0x7fec12de052c
+                          0x7fec12de1521
+                          0x7fec33247581
+                          0x7fec33064bab
+                          engine::end_frame
+                          main::main
+
+     0.70%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023af6a
+            |
+            ---0x7fec3323af6a
+               |          
+                --0.58%--0x7fec33249f38
+                          engine::end_frame
+                          main::main
+                          main
+                          0x7fec32c27740
+                          __libc_start_main
+                          _start
+
+     0.69%  crowd_perf       crowd_perf                      [.] engine::frame_uvs
+            |
+            ---engine::frame_uvs
+               engine::draw_sprite
+               main::main
+               main
+               0x7fec32c27740
+               __libc_start_main
+               _start
+
+     0.68%  crowd_perf       libc.so.6                       [.] 0x000000000009ca5c
+            |
+            ---0x7fec32c9ca5c
+
+     0.67%  crowd_perf       [vdso]                          [.] __vdso_clock_gettime
+            |
+            ---__vdso_clock_gettime
+               clock_gettime
+
+     0.58%  crowd_perf       libdrm.so.2.134.0               [.] drmIoctl
+     0.58%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033b80b
+            |
+            ---0x7fec12f3b80b
+               0x7fec12df41ce
+               0x7fec12df44e5
+
+     0.53%  crowd_perf       libc.so.6                       [.] cfree
+            |
+            ---cfree
+
+     0.51%  crowd_perf       [unknown]                       [k] 0xffffffff84e00080
+            |
+            ---0xffffffff84e00080
+
+     0.45%  crowd_perf       libc.so.6                       [.] pthread_mutex_unlock
+     0.44%  crowd_perf       libc.so.6                       [.] pthread_rwlock_rdlock
+     0.43%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d2c23
+     0.40%  crowd_perf       libc.so.6                       [.] 0x0000000000180625
+     0.39%  crowd_perf       libc.so.6                       [.] 0x000000000018a547
+     0.37%  crowd_perf       crowd_perf                      [.] runtime::default_hasher_string
+     0.36%  crowd_perf       libc.so.6                       [.] 0x000000000018a4c0
+     0.35%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000247484
+     0.33%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003147
+     0.33%  crowd_perf       libc.so.6                       [.] 0x0000000000189cc4
+     0.33%  crowd_perf       [unknown]                       [k] 0xffffffff84e00084
+     0.31%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a44b7
+     0.31%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000110d98
+     0.31%  wl_cursor_surfa  libc.so.6                       [.] 0x000000000018a4f3
+     0.30%  crowd_perf       libc.so.6                       [.] 0x000000000018a4e2
+     0.30%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000e6624
+     0.28%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033b84d
+     0.28%  crowd_perf       libc.so.6                       [.] 0x00000000000a4524
+     0.28%  crowd_perf       libc.so.6                       [.] malloc
+     0.27%  crowd_perf       crowd_perf                      [.] runtime::map_seed_from_map_data
+     0.27%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001822f7
+     0.26%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033c9d7
+     0.26%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000be362
+     0.26%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024cff0
+     0.26%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cd8a8
+     0.26%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d44f
+     0.25%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001d131e
+     0.25%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000116255
+     0.25%  crowd_perf       libdbus-1.so.3.38.3             [.] _dbus_atomic_inc
+     0.25%  crowd_perf       crowd_perf                      [.] __$hasher$$string
+     0.25%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000062360
+     0.25%  crowd_perf       libdrm.so.2.134.0               [.] drmSyncobjTimelineWait
+     0.24%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022daa
+     0.24%  crowd_perf       libc.so.6                       [.] 0x000000000018a486
+     0.24%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b7b5f
+     0.24%  crowd_perf       libdbus-1.so.3.38.3             [.] _dbus_message_loader_queue_messages
+     0.24%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000168f4
+     0.24%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000144008
+     0.24%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024cd09
+     0.23%  crowd_perf       libc.so.6                       [.] 0x00000000000a45c9
+     0.23%  crowd_perf       crowd_perf                      [.] engine::texture_run_len
+     0.23%  crowd_perf       [unknown]                       [k] 0xffffffff86355a81
+     0.23%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023af07
+     0.23%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024d030
+     0.23%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003140
+     0.23%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000166c5
+     0.22%  crowd_perf       libc.so.6                       [.] pthread_rwlock_unlock
+     0.22%  crowd_perf       libc.so.6                       [.] 0x000000000018a4ea
+     0.22%  crowd_perf       libc.so.6                       [.] 0x000000000018a4ca
+     0.22%  crowd_perf       libc.so.6                       [.] 0x000000000009ca36
+     0.22%  crowd_perf       crowd_perf                      [.] engine::begin_frame
+     0.22%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000002501f2
+     0.22%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x00000000000032b2
+     0.22%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cf9cf
+     0.22%  crowd_perf       libc.so.6                       [.] 0x00000000000a58f9
+     0.22%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e47ac
+     0.21%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003263
+     0.21%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e61b8
+     0.21%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x00000000000049dc
+     0.21%  wl_cursor_surfa  libSDL3.so.0.4.12               [.] 0x00000000001cd7b4
+     0.21%  crowd_perf       [unknown]                       [k] 0xffffffff85a7a084
+     0.20%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d2761
+     0.19%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003203
+     0.19%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002295c
+     0.19%  crowd_perf       libc.so.6                       [.] 0x0000000000190598
+     0.18%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d33ea
+     0.17%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000541ae
+     0.17%  crowd_perf       [unknown]                       [k] 0xffffffff855d7847
+     0.17%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000037a095
+     0.17%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5b8f
+     0.17%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x0000000000016a5d
+     0.17%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002ca02
+     0.16%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000181459
+     0.16%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] wl_display_flush
+     0.16%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ebd77
+     0.16%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e35cb
+     0.16%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x0000000000031bdf
+     0.16%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bbf75
+     0.16%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4a6a
+     0.15%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4d24
+     0.15%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000016610
+     0.15%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ed46e
+     0.15%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d496
+     0.15%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b8dea
+     0.15%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024fd04
+     0.14%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000249f10
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ba831
+     0.14%  crowd_perf       libc.so.6                       [.] 0x000000000018a55c
+     0.14%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003165
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000035f660
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000115185
+     0.14%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000018584
+     0.14%  crowd_perf       libc.so.6                       [.] 0x000000000009ffc4
+     0.14%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000657d0
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000028528
+     0.14%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000004cb4
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000021b325
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000013c5ff
+     0.14%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a7586
+     0.14%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000016675
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000035f6d0
+     0.14%  crowd_perf       [unknown]                       [k] 0xffffffff855e8fd6
+     0.14%  crowd_perf       libc.so.6                       [.] 0x00000000000a44b7
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018aae8
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022b11
+     0.14%  crowd_perf       libdbus-1.so.3.38.3             [.] dbus_connection_ref
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001d9f6f
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001814d7
+     0.14%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000035f634
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000181ee4
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033cb4a
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cb17f
+     0.13%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] wl_display_read_events
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018c7aa
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033b7e1
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c9cb4
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5e16
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017dbbb
+     0.13%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000f7a33
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017ea01
+     0.13%  crowd_perf       libnvidia-glcore.so.610.43.03   [.] 0x0000000000fcd46c
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ccf75
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002c934
+     0.13%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000185a9
+     0.13%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003193
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000115378
+     0.13%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000062cee
+     0.13%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x00000000000039f1
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5525
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001dbca4
+     0.13%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000094084
+     0.13%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a66c4
+     0.13%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000001c8cfd
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5b0f
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000116284
+     0.13%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x000000000000320b
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017d7c4
+     0.13%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023af40
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002cd72
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cd651
+     0.13%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000217945
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024e846
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017ff51
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000186261
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000002440cf
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ebdf7
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f3ff0
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cb17b
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001deb23
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2e1b
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f44d1
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001161e8
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d88e7
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001168fc
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cea95
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4771
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000336cae
+     0.12%  crowd_perf       [unknown]                       [k] 0xffffffff84e00087
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cd7c4
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b8712
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000010da71
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001dca18
+     0.12%  crowd_perf       libc.so.6                       [.] 0x00000000000a6ed3
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bf533
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ceb86
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001166e5
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000068cca2
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000116312
+     0.12%  crowd_perf       libdbus-1.so.3.38.3             [.] _dbus_list_pop_first_link
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000180ab2
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002336f
+     0.12%  crowd_perf       crowd_perf                      [.] engine::now_seconds
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024fc98
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f3ff4
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000116118
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000181449
+     0.12%  crowd_perf       libdrm.so.2.134.0               [.] drmSyncobjWait
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b707d
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000011621a
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023c102
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000002469b4
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001d8d26
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bdcf2
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4c57
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c2897
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023be6f
+     0.12%  crowd_perf       [unknown]                       [k] 0xffffffff84e015f4
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000025442a
+     0.12%  crowd_perf       libc.so.6                       [.] 0x00000000000a6403
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f3010
+     0.12%  wl_cursor_surfa  libSDL3.so.0.4.12               [.] 0x00000000001e3f78
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e61f1
+     0.12%  crowd_perf       [unknown]                       [k] 0xffffffff85a7a016
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d4e4
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000f4af3
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001153f9
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cb4b9
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000283b6
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d2d0b
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e6d70
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000115a48
+     0.12%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024d110
+     0.12%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017ff7a
+     0.11%  crowd_perf       libc.so.6                       [.] 0x00000000000a5735
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000011416b
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023aefa
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cd413
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000068cc64
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022d88
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000025478f
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000545e3
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018c87b
+     0.11%  crowd_perf       libc.so.6                       [.] 0x000000000005bcfd
+     0.11%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x00000000000032a4
+     0.11%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x000000000001aa7b
+     0.11%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a674c
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d6749
+     0.11%  crowd_perf       libffi.so.8.4.1                 [.] 0x0000000000002bf4
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000054e93
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000018567
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000189a35
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000182313
+     0.11%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x000000000003219d
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] SDL_UnmapGPUTransferBuffer
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000176c2
+     0.11%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] 0x0000000000003689
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022a03
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002f38d
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d2686
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000244358
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ce843
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f41d6
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000217e57
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cca9b
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000022d261
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ebc8d
+     0.11%  crowd_perf       libc.so.6                       [.] pthread_getspecific
+     0.11%  crowd_perf       libc.so.6                       [.] 0x00000000000a4520
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c0133
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000176d1
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000002475f1
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000035f6c7
+     0.11%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a661d
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000246fbc
+     0.11%  wl_cursor_surfa  libc.so.6                       [.] pthread_mutex_lock
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c4a78
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d227c
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cf034
+     0.11%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000016e32
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b91fb
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e6228
+     0.11%  crowd_perf       libc.so.6                       [.] 0x0000000000189c5a
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000b7a68
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2b1b
+     0.11%  crowd_perf       libc.so.6                       [.] __libc_calloc
+     0.11%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5ba8
+     0.11%  crowd_perf       libc.so.6                       [.] 0x0000000000189c6e
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033c9cd
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bc661
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022a90
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d2ed4
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cfbdd
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001158db
+     0.10%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x000000000000315e
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c5b36
+     0.10%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x000000000000326e
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000013c87e
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000062c29
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024e2b6
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000023be24
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000197523
+     0.10%  crowd_perf       libwayland-client.so.0.25.0     [.] wl_display_prepare_read_queue
+     0.10%  crowd_perf       libc.so.6                       [.] 0x00000000000a57e4
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000002441e6
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cd71c
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018c8b9
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001cfb14
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000067a27
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000022ddf5
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000254752
+     0.10%  crowd_perf       libc.so.6                       [.] 0x000000000009ca4f
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000189e7f
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2d44
+     0.10%  crowd_perf       libc.so.6                       [.] 0x0000000000183444
+     0.10%  crowd_perf       libc.so.6                       [.] ioctl
+     0.10%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000001662f
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d3c1f
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ed479
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4e14
+     0.10%  wl_cursor_surfa  libSDL3.so.0.4.12               [.] 0x00000000001e3f76
+     0.10%  crowd_perf       libwayland-client.so.0.25.0     [.] wl_list_empty
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d6c8b
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000193681
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001dd4e5
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d452
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000028474
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bc657
+     0.10%  crowd_perf       libdbus-1.so.3.38.3             [.] dbus_connection_get_dispatch_status
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000068fe91
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000017e9d8
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000fa720
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000013d041
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000033b851
+     0.10%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e3616
+     0.09%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024f5a2
+     0.09%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000025445f
+     0.09%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000cb359
+     0.09%  crowd_perf       libc.so.6                       [.] strchrnul@plt
+     0.09%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000d3493
+     0.09%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022b67
+     0.09%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000116982
+     0.09%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000035f664
+     0.09%  crowd_perf       libc.so.6                       [.] 0x0000000000189c47
+     0.08%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x00000000000031c3
+     0.08%  crowd_perf       libc.so.6                       [.] 0x00000000000a66c4
+     0.08%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ebd95
+     0.08%  crowd_perf       libc.so.6                       [.] 0x00000000000a5750
+     0.08%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ce980
+     0.08%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000115f93
+     0.08%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d5e9
+     0.08%  wl_cursor_surfa  libc.so.6                       [.] 0x000000000009ca5c
+     0.07%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018aaf9
+     0.07%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000c4a6a
+     0.07%  wl_cursor_surfa  libSDL3.so.0.4.12               [.] 0x00000000001cd7b1
+     0.07%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e4e3e
+     0.06%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] wl_list_insert
+     0.06%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a6ed3
+     0.03%  crowd_perf       libxkbcommon.so.0.13.2          [.] 0x00000000000084b7
+     0.03%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a6f67
+     0.02%  crowd_perf       libc.so.6                       [.] 0x0000000000189d47
+     0.02%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e5074
+     0.02%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x000000000000ac3a
+     0.01%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000182d8f
+     0.00%  crowd_perf       libc.so.6                       [.] __cxa_finalize
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] pthread_cond_broadcast
+     0.00%  wl_cursor_surfa  [unknown]                       [k] 0xffffffff84e00080
+     0.00%  crowd_perf       libc.so.6                       [.] 0x00000000000a7681
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] 0x00000000000036ef
+     0.00%  crowd_p:disk$0   libc.so.6                       [.] pthread_cond_wait
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] 0x0000000000003621
+     0.00%  crowd_perf       libc.so.6                       [.] 0x00000000000534eb
+     0.00%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x0000000000037c44
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x000000000009ca21
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] ppoll
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000002d5ba
+     0.00%  crowd_perf       libSDL3.so.0.4.12               [.] 0x00000000000670f4
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000037a011
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000189cf7
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x0000000000015951
+     0.00%  crowd_perf       libSDL3.so.0.4.12               [.] 0x000000000024e620
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2f92
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x00000000000a4463
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000001e56c
+     0.00%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x000000000001004a
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] 0x00000000000031c3
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x0000000000014887
+     0.00%  crowd_perf       libc.so.6                       [.] 0x000000000005b734
+     0.00%  crowd_perf       libc.so.6                       [.] 0x000000000005bd50
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001e3e38
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000064b99
+     0.00%  crowd_perf       libc.so.6                       [.] 0x000000000005a244
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345b18
+     0.00%  crowd_perf       libc.so.6                       [.] __ctype_init
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff86355a14
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff86355a10
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345ce7
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345adb
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x0000000000654f48
+     0.00%  wl_cursor_surfa  libSDL3.so.0.4.12               [.] 0x00000000001e3f74
+     0.00%  crowd_perf       libc.so.6                       [.] __errno_location
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ca8f2
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x0000000001961f52
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345837
+     0.00%  crowd_perf       libc.so.6                       [.] pthread_self
+     0.00%  wl_cursor_surfa  [unknown]                       [k] 0xffffffff852a9115
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000103a63
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000018d575
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345cfe
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000097417
+     0.00%  crowd_perf       libc.so.6                       [.] 0x000000000009741b
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001166ae
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff84e015f0
+     0.00%  crowd_perf       libwayland-client.so.0.25.0     [.] wl_display_dispatch_queue_timeout
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000185400
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x0000000000008b5e
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022edc
+     0.00%  crowd_perf       libSDL3.so.0.4.12               [.] 0x0000000000018892
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000028ed39
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000094040
+     0.00%  crowd_perf       libc.so.6                       [.] sendmsg
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff84e01280
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000344ddb
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345bb3
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000344ddd
+     0.00%  crowd_perf       libc.so.6                       [.] 0x000000000011bed0
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000344cd4
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345ad6
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000094047
+     0.00%  crowd_perf       libc.so.6                       [.] 0x00000000000973a0
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000103a40
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000094047
+     0.00%  crowd_perf       libc.so.6                       [.] __poll
+     0.00%  crowd_perf       libc.so.6                       [.] 0x00000000000973a4
+     0.00%  crowd_perf       libdbus-1.so.3.38.3             [.] 0x0000000000032197
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff84e01630
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x000000000000932e
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x0000000000009339
+     0.00%  crowd_perf       ld-linux-x86-64.so.2            [.] 0x000000000001f103
+     0.00%  crowd_perf       libc.so.6                       [.] ppoll
+     0.00%  crowd_perf       libc.so.6                       [.] realloc
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000094040
+     0.00%  crowd_perf       libc.so.6                       [.] 0x0000000000094084
+     0.00%  crowd_perf       libc.so.6                       [.] 0x00000000000a78dc
+     0.00%  crowd_perf       libnvidia-glcore.so.610.43.03   [.] 0x00000000009e786b
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x0000000000455dd3
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x000000000067d1b0
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x000000000067d1c2
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x0000000001956940
+     0.00%  crowd_perf       libnvidia-gpucomp.so.610.43.03  [.] 0x000000000195a141
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022e9e
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022ea7
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000022ebd
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000bafc5
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ca918
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000000ca91f
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000011666f
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001166a8
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2dbf
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x00000000001f2dd0
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000028ece4
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000028ed0d
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x0000000000345bb0
+     0.00%  crowd_perf       libvulkan_radeon.so             [.] 0x000000000068d01a
+     0.00%  crowd_perf       libwayland-client.so.0.25.0     [.] 0x0000000000003aa8
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff84e01670
+     0.00%  crowd_perf       [unknown]                       [k] 0xffffffff84e01690
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000094050
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x0000000000094085
+     0.00%  wl_cursor_surfa  libc.so.6                       [.] 0x000000000009fff2
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0     [.] 0x0000000000004524
+     0.00%  wl_cursor_surfa  [unknown]                       [k] 0xffffffff84e01630
+
+
+#
+# (Tip: For tracepoint events, try: perf report -s trace_fields)
+#

flame/crowd-20260809-140317-report.txt

@@ -0,0 +1,730 @@
+# To display the perf.data header info, please use --header/--header-only options.
+#
+#
+# Total Lost Samples: 0
+#
+# Samples: 953  of event 'cpu/cycles/Pu'
+# Event count (approx.): 5763089468
+#
+# Overhead  Command          Shared Object                  Symbol                                                                                                                                                                                    
+# ........  ...............  .............................  ..........................................................................................................................................................................................
+#
+     4.03%  crowd_perf       libc.so.6                      [.] pthread_mutex_lock
+            |
+            ---pthread_mutex_lock
+               |          
+                --0.65%--0x7f80850501f1
+                          engine::end_frame (inlined)
+                          main::main
+                          main
+                          0x7f8084a27740
+                          __libc_start_main
+                          _start
+
+     3.19%  crowd_perf       crowd_perf                     [.] main::main
+            |          
+             --0.79%--runtime::default_hasher (inlined)
+                       runtime::default_hasher_string (inlined)
+                       |          
+                        --0.54%--engine::character_clip (inlined)
+                                  engine::update_sprite (inlined)
+                                  main::main
+                                  main
+                                  0x7f8084a27740
+                                  __libc_start_main
+                                  _start
+
+     2.85%  crowd_perf       libc.so.6                      [.] 0x00000000000a73e9
+            |
+            ---0x7f8084aa73e9
+               wl_proxy_marshal_array_flags
+               wl_proxy_marshal_flags
+               0x7f8082b97614
+               0x7f8082b8a4f8
+               0x7f808504ffc9
+               engine::end_frame (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     2.20%  crowd_perf       crowd_perf                     [.] __$map_get$$map[string]engine::Clip_Def
+            |
+            ---__$map_get$$map[string]engine::Clip_Def
+               |          
+                --1.91%--engine::character_clip (inlined)
+                          engine::update_sprite (inlined)
+                          main::main
+                          main
+                          0x7f8084a27740
+                          __libc_start_main
+                          _start
+
+     2.07%  crowd_perf       libc.so.6                      [.] 0x0000000000189c53
+            |
+            ---0x7f8084b89c53
+               runtime::_append_elem
+               runtime::append_elem:proc(array:^[dynamic]engine::Queued_Sprite,arg:engine::Queued_Sprite,loc:runtime::Source_Code_Location)->(n:int,err:runtime::Allocator_Error) (inlined)
+               engine::draw_sprite (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     1.83%  crowd_perf       libc.so.6                      [.] clock_gettime
+            |
+            ---clock_gettime
+               |          
+               |--0.53%--0x7f808502c819
+               |          
+                --0.52%--0x7f8082d7a09a
+                          0x7f8082d3de27
+                          |          
+                           --0.52%--0x7f8082b975b5
+                                     0x7f8082b8a4f8
+                                     0x7f808504ffc9
+                                     engine::end_frame (inlined)
+                                     main::main
+                                     main
+                                     0x7f8084a27740
+                                     __libc_start_main
+                                     _start
+
+     1.58%  crowd_perf       libwayland-client.so.0.25.0    [.] wl_proxy_marshal_array_flags
+            |
+            ---wl_proxy_marshal_array_flags
+               wl_proxy_marshal_flags
+
+     1.55%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000031fb52
+            |
+            ---0x7f8082d1fb52
+               0x7f8082a2cc72
+               0x7f8082a2cf4e
+               0x7f8082a2e299
+               0x7f8082a2f277
+               0x7f8082be052c
+               0x7f8082be1521
+               0x7f8085047581
+               0x7f8084e64bab
+               engine::end_frame (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     1.34%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] wl_list_insert
+     1.30%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a678f
+     1.18%  crowd_perf       [unknown]                      [k] 0xffffffff84e00080
+            |
+            ---0xffffffff84e00080
+               |          
+                --0.94%--ioctl
+                          |          
+                           --0.80%--drmIoctl
+
+     1.07%  crowd_perf       libc.so.6                      [.] ioctl
+            |
+            ---ioctl
+               |          
+                --1.07%--drmIoctl
+                          |          
+                           --0.61%--drmSyncobjTimelineWait
+                                     |          
+                                      --0.50%--0x7f8082b8d8ad
+                                                0x7f8082b93f45
+                                                0x7f8082b89296
+                                                0x7f8082b89241
+                                                0x7f80850544bd
+                                                0x7f8084e69860
+                                                engine::begin_frame (inlined)
+                                                main::main
+                                                main
+                                                0x7f8084a27740
+                                                __libc_start_main
+                                                _start
+
+     1.05%  crowd_perf       [vdso]                         [.] __vdso_clock_gettime
+            |
+            ---__vdso_clock_gettime
+               clock_gettime
+               |          
+                --0.50%--0x7f8082d7a09a
+
+     0.93%  crowd_perf       [unknown]                      [k] 0xffffffff86355a81
+            |
+            ---0xffffffff86355a81
+               0xffffffff84e0012f
+               |          
+                --0.81%--ioctl
+                          |          
+                           --0.69%--drmIoctl
+
+     0.92%  crowd_perf       libdrm.so.2.134.0              [.] drmIoctl
+            |
+            ---drmIoctl
+
+     0.85%  crowd_perf       libc.so.6                      [.] cfree
+            |
+            ---cfree
+
+     0.81%  crowd_perf       libc.so.6                      [.] 0x000000000009ca5c
+            |
+            ---0x7f8084a9ca5c
+
+     0.78%  crowd_perf       libc.so.6                      [.] 0x00000000000a6ed3
+            |
+            ---0x7f8084aa6ed3
+               |          
+                --0.55%--0x7f8084aa714d
+
+     0.70%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002501f2
+            |
+            ---0x7f80850501f2
+               engine::end_frame (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     0.65%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022d88
+            |
+            ---0x7f8082a22d88
+
+     0.62%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f41b7
+            |
+            ---0x7f8082bf41b7
+               0x7f8082bf44e5
+
+     0.61%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d2c23
+            |
+            ---0x7f8082ad2c23
+               0x7f8082be6325
+
+     0.60%  crowd_perf       libc.so.6                      [.] 0x000000000018a547
+            |
+            ---0x7f8084b8a547
+
+     0.56%  crowd_perf       libc.so.6                      [.] malloc
+            |
+            ---malloc
+
+     0.55%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000e6624
+            |
+            ---0x7f8082ae6624
+               0x7f8082be6325
+
+     0.53%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002475f1
+            |
+            ---0x7f80850475f1
+               0x7f8084e64bab
+               engine::end_frame (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     0.53%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e61b8
+            |
+            ---0x7f8082be61b8
+               0x7f808503b9d8
+               0x7f8085049f22
+               engine::end_frame (inlined)
+               main::main
+               main
+               0x7f8084a27740
+               __libc_start_main
+               _start
+
+     0.51%  crowd_perf       [unknown]                      [k] 0xffffffff855d7847
+            |
+            ---0xffffffff855d7847
+               0xffffffff86355aba
+               0xffffffff84e0012f
+               ioctl
+               drmIoctl
+
+     0.50%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033b80b
+            |
+            ---0x7f8082d3b80b
+               0x7f8082bf41ce
+
+     0.50%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023af6a
+     0.48%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001deb23
+     0.48%  crowd_perf       libc.so.6                      [.] pthread_rwlock_unlock
+     0.48%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033c9d7
+     0.47%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002ca18
+     0.46%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] wl_display_flush
+     0.46%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b92b8
+     0.45%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001822f7
+     0.44%  crowd_perf       libc.so.6                      [.] pthread_rwlock_wrlock
+     0.41%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003203
+     0.41%  crowd_perf       libc.so.6                      [.] __errno_location
+     0.40%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000180ab2
+     0.40%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024d183
+     0.40%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d2761
+     0.39%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000016900
+     0.39%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000243e0a
+     0.39%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a6747
+     0.36%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d492
+     0.35%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001814c2
+     0.35%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b8fdd
+     0.35%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000e5edc
+     0.33%  wl_cursor_surfa  libSDL3.so.0.4.12              [.] 0x00000000001e3f74
+     0.33%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000001493ed
+     0.32%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000005430
+     0.32%  crowd_perf       libc.so.6                      [.] 0x00000000000a7554
+     0.29%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e0534
+     0.29%  crowd_perf       libwayland-client.so.0.25.0    [.] wl_proxy_marshal_flags
+     0.29%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000110d3b
+     0.29%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001defd2
+     0.29%  wl_cursor_surfa  libc.so.6                      [.] 0x000000000018a507
+     0.29%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003147
+     0.29%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x00000000000032a4
+     0.28%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d44f
+     0.28%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d866
+     0.28%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000168f4
+     0.27%  wl_cursor_surfa  libc.so.6                      [.] ppoll
+     0.27%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d227c
+     0.27%  crowd_perf       crowd_perf                     [.] runtime::_append_elem
+     0.27%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003943
+     0.27%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b91fd
+     0.26%  crowd_perf       libc.so.6                      [.] pthread_mutex_unlock
+     0.26%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f41d6
+     0.26%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002441e6
+     0.26%  crowd_perf       libc.so.6                      [.] 0x00000000000a6ed7
+     0.26%  crowd_perf       libc.so.6                      [.] 0x00000000000a590c
+     0.26%  crowd_perf       [unknown]                      [k] 0xffffffff84e00084
+     0.26%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] wl_display_read_events
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033cb4a
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f2f9e
+     0.25%  crowd_perf       libc.so.6                      [.] 0x0000000000180604
+     0.25%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000016904
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000181449
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000fabbd
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022daa
+     0.25%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b69b6
+     0.24%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ba831
+     0.24%  wl_cursor_surfa  libc.so.6                      [.] pthread_mutex_lock
+     0.24%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000068ccac
+     0.24%  crowd_perf       libc.so.6                      [.] 0x00000000000a7101
+     0.24%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001152d6
+     0.24%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bdd3d
+     0.24%  crowd_perf       libc.so.6                      [.] 0x000000000018a54e
+     0.24%  crowd_perf       [unknown]                      [k] 0xffffffff85a7a016
+     0.24%  wl_cursor_surfa  libc.so.6                      [.] recvmsg
+     0.23%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000035f607
+     0.23%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f3ff4
+     0.23%  crowd_perf       libdrm.so.2.134.0              [.] drmSyncobjWait
+     0.23%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x000000000000320b
+     0.22%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023434e
+     0.22%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024ff8e
+     0.22%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002504d8
+     0.21%  wl_cursor_surfa  libc.so.6                      [.] 0x0000000000093fe4
+     0.21%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f4165
+     0.20%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000018896
+     0.20%  crowd_perf       libc.so.6                      [.] 0x0000000000183444
+     0.19%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd91c
+     0.19%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000e6243
+     0.19%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd030
+     0.19%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000001663d
+     0.18%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000115378
+     0.18%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001da01c
+     0.18%  crowd_perf       libc.so.6                      [.] 0x00000000000a579b
+     0.18%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x0000000000004cb4
+     0.17%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ebd58
+     0.17%  crowd_perf       libc.so.6                      [.] 0x0000000000180625
+     0.17%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001df838
+     0.17%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cfab0
+     0.17%  crowd_perf       libc.so.6                      [.] 0x00000000000a678f
+     0.17%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cf034
+     0.16%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024cec9
+     0.16%  crowd_perf       [unknown]                      [k] 0xffffffff86355a14
+     0.16%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023af5d
+     0.16%  wl_cursor_surfa  libc.so.6                      [.] 0x0000000000094085
+     0.16%  crowd_perf       libdbus-1.so.3.38.3            [.] _dbus_atomic_inc
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000037a25e
+     0.16%  crowd_perf       libdbus-1.so.3.38.3            [.] dbus_connection_unref
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000181484
+     0.16%  crowd_perf       libwayland-client.so.0.25.0    [.] wl_list_remove
+     0.16%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000025445f
+     0.16%  crowd_perf       libc.so.6                      [.] 0x000000000009ca14
+     0.16%  crowd_perf       libdbus-1.so.3.38.3            [.] _dbus_connection_lock
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000217ee9
+     0.16%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000254472
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001dd6f2
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000f4ad9
+     0.16%  crowd_perf       libnvidia-glcore.so.610.43.03  [.] 0x0000000000fcd461
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018aaf2
+     0.16%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002caab
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e6434
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002ca15
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c5ba8
+     0.15%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003263
+     0.15%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000015f1c3
+     0.15%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x00000000000032dc
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f3344
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d7063
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c4a41
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ec895
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000335bd4
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ebdc5
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f3ff6
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ebe76
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ed816
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e61f1
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002d5ef
+     0.15%  crowd_perf       libc.so.6                      [.] 0x000000000018062b
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d13c3
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d8386
+     0.15%  wl_cursor_surfa  libc.so.6                      [.] 0x000000000009ca5c
+     0.15%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000015f1a4
+     0.15%  crowd_perf       libc.so.6                      [.] 0x00000000000a5735
+     0.15%  crowd_perf       [unknown]                      [k] 0xffffffff84e00087
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022b88
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000217dba
+     0.15%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000001da04c
+     0.15%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000019371b
+     0.15%  crowd_perf       libc.so.6                      [.] 0x0000000000189c44
+     0.14%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x000000000001ab32
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000196829
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000017690
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d844
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bddf1
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000013ca2e
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000054e60
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000194631
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c9aeb
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000017dbc1
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000197523
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001cf344
+     0.14%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x000000000001aa6d
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024ce11
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000055379
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024bb5e
+     0.14%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x0000000000031883
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d6418
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000018a57d
+     0.14%  crowd_perf       libc.so.6                      [.] 0x0000000000189c93
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000009ca4f
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000168f0
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000028474
+     0.14%  crowd_perf       libc.so.6                      [.] 0x00000000000a7477
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022a86
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d4ac
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000035f6c7
+     0.14%  crowd_perf       libc.so.6                      [.] 0x00000000000a66c4
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000002310fb
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000176c6
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000009ca19
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023b2d1
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002d8b8
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d9f47
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bbf60
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cea95
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000115ac7
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000115b65
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002470cf
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024d18e
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000009ffc0
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cf4c5
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000244261
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002d886
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001896c4
+     0.14%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x00000000000049dc
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c0ac8
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002ca2a
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d3493
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000001e62d
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000116118
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000053d7e
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c877c
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000018a4f3
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000022d354
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022d55
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e5ebd
+     0.14%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000004c80
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f41a4
+     0.14%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003140
+     0.14%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e60b2
+     0.14%  crowd_perf       libc.so.6                      [.] 0x000000000009ca5a
+     0.14%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023c133
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024d1c6
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033ca1e
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000be09c
+     0.13%  crowd_perf       libc.so.6                      [.] 0x0000000000189cc4
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000185a0
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cc0cb
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b74ff
+     0.13%  crowd_perf       libdbus-1.so.3.38.3            [.] _dbus_rmutex_lock
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bc373
+     0.13%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003193
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d148b
+     0.13%  crowd_perf       libc.so.6                      [.] 0x0000000000189d47
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023c3e7
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024b818
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000217eac
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000027f8e
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022aa5
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c9d9f
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002f38d
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024cf70
+     0.13%  crowd_perf       [unknown]                      [k] 0xffffffff855e8f44
+     0.13%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x00000000000032b2
+     0.13%  crowd_perf       libc.so.6                      [.] 0x000000000009ca31
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000005536a
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000013c684
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024fc98
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ed0ff
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c6ce6
+     0.13%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x000000000003187f
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001cfb65
+     0.13%  crowd_perf       libc.so.6                      [.] 0x0000000000180614
+     0.13%  crowd_perf       libdbus-1.so.3.38.3            [.] _dbus_list_pop_first_link
+     0.13%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000005485
+     0.13%  crowd_perf       libc.so.6                      [.] __libc_calloc
+     0.13%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x000000000000320e
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001db541
+     0.13%  crowd_perf       libc.so.6                      [.] 0x000000000009408f
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f2f92
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c5bde
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d16a6
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001398b4
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024f60d
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d5e9
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d793a
+     0.13%  crowd_perf       libc.so.6                      [.] 0x000000000018a4c4
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001cf563
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ccf20
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000002310dc
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002d7a3
+     0.13%  crowd_perf       libc.so.6                      [.] __close
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000035f634
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ed45b
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d2d0b
+     0.13%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000f7a33
+     0.13%  crowd_perf       libc.so.6                      [.] 0x00000000000a7491
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000230ea5
+     0.13%  crowd_perf       libc.so.6                      [.] 0x00000000000a57a6
+     0.13%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000110d5e
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000068d087
+     0.12%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x0000000000031820
+     0.12%  crowd_perf       libc.so.6                      [.] 0x000000000009ca17
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024d030
+     0.12%  wl_cursor_surfa  libc.so.6                      [.] pthread_mutex_unlock
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024e291
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d2ac1
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018c879
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022b1c
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f2c85
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e34fc
+     0.12%  crowd_perf       libc.so.6                      [.] ppoll
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bcb9e
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002334f
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022950
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d649e
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cfa60
+     0.12%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003912
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d1145
+     0.12%  crowd_perf       libdbus-1.so.3.38.3            [.] 0x00000000000318bf
+     0.12%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x00000000000049dc
+     0.12%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x0000000000003689
+     0.12%  crowd_perf       libc.so.6                      [.] 0x00000000000a6621
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002d844
+     0.12%  crowd_perf       [unknown]                      [k] 0xffffffff86355a41
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002bc13
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033cb5b
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002ce05
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000014f29b
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000025478f
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d462
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e6d9f
+     0.12%  crowd_perf       libc.so.6                      [.] 0x00000000000a6610
+     0.12%  crowd_perf       [unknown]                      [k] 0xffffffff850a84c5
+     0.12%  crowd_perf       libc.so.6                      [.] 0x0000000000180653
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033ca37
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000249e81
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001dcabc
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000110ce8
+     0.12%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x000000000000328a
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024cef0
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd943
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c2584
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd7c1
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000022f3e
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d635
+     0.12%  crowd_perf       libc.so.6                      [.] 0x000000000009ca74
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cea42
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023b143
+     0.12%  wl_cursor_surfa  libc.so.6                      [.] 0x000000000018a4f3
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd71c
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d1865
+     0.12%  crowd_perf       libc.so.6                      [.] 0x000000000018a486
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e519a
+     0.12%  crowd_perf       libc.so.6                      [.] 0x00000000000a66e2
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000019678f
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e5134
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000002463df
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000054e93
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000068cf84
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000b6d7d
+     0.12%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000af32
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ed081
+     0.12%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000218046
+     0.12%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000541ae
+     0.12%  crowd_perf       libdbus-1.so.3.38.3            [.] _dbus_message_loader_queue_messages
+     0.12%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x000000000000546e
+     0.12%  crowd_perf       libwayland-client.so.0.25.0    [.] 0x0000000000003233
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000180ada
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000028174
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000657d0
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ce7ac
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000250239
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000068d014
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023ba94
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000013cae3
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000cd796
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024d1b9
+     0.11%  crowd_perf       libc.so.6                      [.] 0x000000000018a507
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f3465
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d452
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001e6363
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000021b281
+     0.11%  crowd_perf       libc.so.6                      [.] 0x00000000000a5904
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f401a
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000001c8c05
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d2d97
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000379fe4
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001529e1
+     0.11%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a6732
+     0.11%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] wl_display_prepare_read_queue
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024cddc
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000010da99
+     0.11%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x0000000000004961
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d62b5
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d874
+     0.11%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a66e2
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000182733
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000023598
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000054f23
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x00000000000176cf
+     0.11%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000024e2b6
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001f44c0
+     0.11%  crowd_perf       libc.so.6                      [.] 0x00000000000a6403
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d11b3
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d3c36
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033df64
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000d3a9c
+     0.11%  crowd_perf       libc.so.6                      [.] 0x00000000000a6603
+     0.11%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000283b6
+     0.11%  crowd_perf       libc.so.6                      [.] 0x00000000000a456a
+     0.11%  crowd_perf       libc.so.6                      [.] 0x0000000000189d0b
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000c5581
+     0.10%  crowd_perf       libc.so.6                      [.] 0x00000000000a5851
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000ce761
+     0.10%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023bdb8
+     0.10%  crowd_perf       [unknown]                      [k] 0xffffffff86355a45
+     0.10%  crowd_perf       libSDL3.so.0.4.12              [.] 0x000000000023b914
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000022d239
+     0.10%  crowd_perf       libc.so.6                      [.] 0x0000000000064888
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bdd81
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000231160
+     0.10%  crowd_perf       libc.so.6                      [.] 0x000000000018a4c0
+     0.10%  crowd_perf       libc.so.6                      [.] 0x000000000018a56f
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000022d386
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000280a5
+     0.10%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000002cd72
+     0.10%  crowd_perf       libSDL3.so.0.4.12              [.] 0x0000000000069865
+     0.09%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018a489
+     0.09%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000033b807
+     0.09%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000035f6d4
+     0.09%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000fa782
+     0.08%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000000bdfc3
+     0.03%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000fea2
+     0.01%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001d12c7
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a447d
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x0000000000004951
+     0.00%  crowd_perf       libc.so.6                      [.] 0x00000000000a5701
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] wl_display_dispatch_queue_pending
+     0.00%  wl_cursor_surfa  libwayland-client.so.0.25.0    [.] 0x0000000000003193
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001dd35f
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000040242
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a7491
+     0.00%  crowd_perf       libc.so.6                      [.] 0x00000000000a6ea4
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000027f18
+     0.00%  crowd_perf       [unknown]                      [k] 0xffffffff8632ecd9
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000aed9
+     0.00%  crowd_perf       libc.so.6                      [.] getenv
+     0.00%  crowd_perf       libGLX_nvidia.so.610.43.03     [.] 0x000000000009e60a
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000094006
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x00000000001895fc
+     0.00%  crowd_perf       libc.so.6                      [.] __libc_secure_getenv
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x00000000000a6ea4
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x00000000000147ed
+     0.00%  crowd_perf       [unknown]                      [k] 0xffffffff850a7e70
+     0.00%  crowd_perf       libc.so.6                      [.] __ctype_init
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000064845
+     0.00%  crowd_perf       libc.so.6                      [.] 0x000000000009741b
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000345adb
+     0.00%  wl_cursor_surfa  libSDL3.so.0.4.12              [.] 0x00000000001cd7b4
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000345cfe
+     0.00%  wl_cursor_surfa  libSDL3.so.0.4.12              [.] 0x00000000001e3f76
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000028ed0d
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000345b18
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000345ad6
+     0.00%  crowd_perf       libLLVM.so.22.1                [.] std::enable_if<llvm::hashing::detail::is_hashable_data<char const>::value, llvm::hash_code>::type llvm::hashing::detail::hash_combine_range_impl<char const>(char const*, char const*)
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000097417
+     0.00%  crowd_perf       libc.so.6                      [.] 0x00000000000a5770
+     0.00%  wl_cursor_surfa  libSDL3.so.0.4.12              [.] 0x00000000001cd7b9
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000103a63
+     0.00%  crowd_perf       libnvidia-glcore.so.610.43.03  [.] 0x0000000000fcd46c
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d572
+     0.00%  crowd_perf       libdrm.so.2.134.0              [.] drmSyncobjExportSyncFile
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000deb7
+     0.00%  crowd_perf       libnvidia-glsi.so.610.43.03    [.] 0x00000000000460e4
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000018d7de
+     0.00%  crowd_perf       libdrm.so.2.134.0              [.] drmSyncobjTransfer
+     0.00%  crowd_perf       libdrm_amdgpu.so.1.134.0       [.] amdgpu_query_info
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000001fce9
+     0.00%  wl_cursor_surfa  libSDL3.so.0.4.12              [.] 0x00000000001e3f78
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000344ddb
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000344cd4
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000344ccb
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000344ddd
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x0000000000345bb3
+     0.00%  crowd_perf       [unknown]                      [k] 0xffffffff84e01280
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x0000000000094040
+     0.00%  crowd_perf       libc.so.6                      [.] 0x000000000011bed0
+     0.00%  crowd_perf       libc.so.6                      [.] 0x00000000000973a0
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x0000000000094084
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000103a40
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000028ece4
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000028ed4d
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000dedf
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000f60f
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000000f611
+     0.00%  crowd_perf       ld-linux-x86-64.so.2           [.] 0x000000000001f103
+     0.00%  crowd_perf       libLLVM.so.22.1                [.] 0x000000000083a104
+     0.00%  crowd_perf       libLLVM.so.22.1                [.] 0x000000000083a146
+     0.00%  crowd_perf       libc.so.6                      [.] wait4
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000094040
+     0.00%  crowd_perf       libc.so.6                      [.] 0x0000000000094047
+     0.00%  crowd_perf       libc.so.6                      [.] 0x00000000000a58a9
+     0.00%  crowd_perf       libdrm.so.2.134.0              [.] drmCommandWrite
+     0.00%  crowd_perf       libdrm.so.2.134.0              [.] drmSyncobjTimelineWait
+     0.00%  crowd_perf       libnvidia-glcore.so.610.43.03  [.] 0x0000000000fcd46a
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000017fa4b
+     0.00%  crowd_perf       libvulkan_radeon.so            [.] 0x000000000017fae8
+     0.00%  crowd_perf       [unknown]                      [k] 0xffffffff84e01670
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x0000000000094050
+     0.00%  wl_cursor_surfa  libc.so.6                      [.] 0x000000000009408f
+     0.00%  wl_cursor_surfa  [unknown]                      [k] 0xffffffff84e01630
+
+
+#
+# (Tip: For hierarchical output, try: perf report --hierarchy)
+#