Files

T

marfrit a4e7d8ab90 initial seed: retrofit campaign lineage from local working trees

panvk-bifrost campaigns (r1..r4 Vulkan compositor + r5.video1 Vulkan
video decode) shipped before this repo existed; the deliverable
patches live in marfrit-packages, but the reasoning chain, phase docs,
and source-state evidence lived only in local working trees on the
development host.

This retrofit imports:
- mesa-panvk-bifrost/   — r1..r4 era phase docs (iter1..iter18)
                          (libmali stub blobs at iter18/blob/ excluded
                          — 109MB of RE artifacts replaced with a README
                          pointer)
- mesa-panvk-bifrost-video/ — sibling campaign phase docs + probe
- evidence/             — frozen .tgz source snapshots at each milestone
                          (basis for the 0005 patch diff generation)

Future iterations should branch off here from day one, so each iter is
a commit rather than a snapshot. See [[feedback-session-local-process-pins]]
for the process drift this retrofit closes.

Total: 1.9 MB across 124 files.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-23 05:25:37 +02:00

4.0 KiB

Raw Blame History

Phase 4 close — iter13 VK_EXT_transform_feedback implementation

Result: GREEN. PanVk-Bifrost now implements VK_EXT_transform_feedback end-to-end.

Probe outcome

[info] VK_EXT_transform_feedback present on device
[info] transformFeedback=1 geometryStreams=0
[info] vertex 0: (0.000000, 0.000000, 4660.000000, 51966.000000)
[info] vertex 1: (1.000000, 0.000000, 4660.000000, 51966.000000)
[info] vertex 2: (2.000000, 0.000000, 4660.000000, 51966.000000)
[PASS] PanVk-Bifrost transform feedback: 3 vertices captured correctly.

Byte-exact match against expected vec4(vertex_id, instance_id=0, 0x1234, 0xcafe) for each of 3 vertices. Output buffer was pre-filled with 0xDEADBEEF sentinel — verified GPU actually wrote real data, not a stale init pattern.

Source landings on ohm (mesa 26.0.6)

Files modified (1 NEW + 6 edited):

File	Change
`src/panfrost/vulkan/panvk_shader.h`	sysval struct: + `uint32_t num_vertices`, `uint64_t xfb_address[4]` (under `PAN_ARCH < 9`)
`src/panfrost/vulkan/panvk_vX_physical_device.c`	extension + feature + properties exposure (`PAN_ARCH < 9` gate)
`src/panfrost/vulkan/panvk_vX_shader.c`	(1) `#include "pan_nir.h"` (2) sysval lowering cases for `load_num_vertices` + `load_xfb_address[0..3]` (3) the 3-pass XFB lowering (`nir_opt_constant_folding` → `nir_io_add_intrinsic_xfb_info` → `pan_nir_lower_xfb`) inserted AFTER `nir_lower_io` in `panvk_lower_nir` (4) `inputs.no_idvs` true for XFB-bearing vertex shaders
`src/panfrost/vulkan/panvk_cmd_draw.h`	+ `xfb` substruct in `panvk_cmd_graphics_state` (active flag + buffer_count + 4× buffers)
`src/panfrost/vulkan/panvk_vX_cmd_draw.c`	per-draw `set_gfx_sysval` for `vs.num_vertices` + `vs.xfb_address[0..3]`
`src/panfrost/vulkan/jm/panvk_vX_cmd_xfb.c`	NEW — `CmdBind/Begin/EndTransformFeedbackEXT` entry points
`src/panfrost/vulkan/meson.build`	+ `'jm/panvk_vX_cmd_xfb.c'` in jm_files

Key learnings (vs Phase 1 source map)

Pass placement matters. Phase 1's plan put pan_nir_lower_xfb inside panvk_preprocess_nir. Wrong — at that point the shader still has store_deref (var-based) intrinsics. nir_lower_io (which converts var-stores → store_output intrinsics) runs later inside panvk_lower_nir. The pass must run right after nir_lower_io, mirroring Panfrost-Gallium's flow where nir_lower_io precedes the XFB block in pan_create_shader_state.
nir_io_add_intrinsic_xfb_info is mandatory. Phase 1 assumed nir->xfb_info was the gate. Wrong — Mesa's pass that converts SPV xfb decorations into intrinsic-attached io_xfb info needs to run first. Gating on nir->info.has_transform_feedback_varyings instead (set by SPV→NIR for XFB-decorated outputs) is the correct trigger.
no_idvs is non-negotiable. Phase 1 noted Panfrost-Gallium sets inputs.no_idvs = has_transform_feedback_varyings but framed it as optional. It isn't — IDVS splits vertex shading into position + varying paths, but the JM job model for the varying path doesn't run for raster-discarded draws. Single non-IDVS vertex job is required for XFB.
The sysval dirty mechanism does work for array fields. set_gfx_sysval(..., vs.xfb_address[0], _xa0) expands correctly via offsetof(struct, vs.xfb_address[0]) + sizeof(uint64_t) macros. Confirmed empirically — the FAU upload triggered as expected and the shader read the correct address.

What the working shader looks like

After all passes, the vertex shader does:

store_global(addr = xfb_address[0] + (instance_id * num_vertices + vertex_id) * stride,
             value = (vertex_id_as_float, instance_id_as_float, 4660.0, 51966.0))

Where xfb_address[0] is a 64-bit FAU sysval populated per-draw from cmdbuf->state.gfx.xfb.buffers[0].addr + offset.

Phase 4 artifact snapshot

Working state of all 7 source files captured in iter13/applied_state/ for replication.

Next: Phase 5

Per CLAUDE.md "Reviews are never skippable" — second-model review of the implementation.

4.0 KiB Raw Blame History Unescape Escape