Under Proton (RADV/ACO), three Model M kernels go over the 192-VGPR bound
Mantenedores costumam responder em até 1 dia
Ninguém assumiu esta issue ainda.
Avaliação
- Dificuldade
- 5/5
- Tempo estimado
- Mais de uma semana
- Facilidade para iniciantes
- 15/100
- Tipo de issue
- Bug
- Clareza
- Precisa de esclarecimento
- Status de atividade
- Ativa
- Stack de tecnologia
- cpp
- Domínio
- computer-graphics, performance
Direção de pesquisa
The issue asks for a maintainer decision, not a code change: restructure the kernels, report the SPIR-V to Mesa ACO, or leave it. Start with clean/dx12/vgpr_limits.json and clean/dx12/README.md, then the kernels under clean/dx12/kernels built by build_dx12.py. Reproducing the VGPR counts needs RADV_DEBUG=shaderstats under Wine with native_direct_test. Done means a chosen path, agreed with the maintainer, and no code change to the kernels has been made yet.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
What
Under Proton, Mesa's ACO compiler needs more VGPRs than clean/dx12/vgpr_limits.json allows for three of Model M's heaviest kernels. Per vgpr_limits.json's own note, they then fit one 256-lane workgroup per CU instead of two:
| Kernel | VGPRs under ACO | Bound | Waves/SIMD | GPU time per frame |
|---|---|---|---|---|
swin_block_c64_nc |
240 | 192 | 6 | 0.30 ms |
swin_block_c96_pm_rev_nc |
256 | 192 | 5 | 0.26 ms |
bneck/swin_bneck6_mbo_nc |
256 | 192 | 5 | 0.43 ms |
swin_block_c96_add_xe_xo_nc |
192 | 192 | 8 | 0.21 ms |
d1p12/swin_block_c64_add_dec0_nc |
192 | 192 | 8 | 0.43 ms |
That's about 1.0 ms of Model M's roughly 2.3 ms on the direct route, at 1706×960 → 2560×1440. The repository's notes put a lost workgroup per CU at +38 µs (swin_block_c96_add_xe_* at 215 VGPRs) to +103 µs (dec0 at 201/215 VGPRs) per frame at 1440p Quality. So this is probably a few tenths of a millisecond on Linux. I haven't measured that directly: I can't force ACO to 192 VGPRs to compare.
It isn't loop unrolling. That was my first guess, because of the "unroll loops despite [loop]" note in clean/dx12/README.md, so I checked:
swin_block_c64_nc's DXIL has no loops at all: DXC already unrolled it, so AMD's Windows compiler gets the same straight-line code and fits it in ≤192 VGPRs (the build's RGA check).swin_block_c96_pm_rev_ncand the bottleneck keep their loops under ACO (2 and 8 back-edges).
So it's ACO's register allocation on these large kernels. Before scheduling it's already about 198 VGPRs for c64, and 194 and 230 for the other two.
How it was measured (synthetic data only)
- RX 9070 XT, Mesa RADV 27.0.0-devel, GE-Proton 11-11's Wine, vkd3d-proton
5b1089c8with dxil-spirv #362 (dxil-spirv114e664eplus the PR). - Kernels built from main's
clean/dx12/kernels(unchanged since a8500cb) withbuild_dx12.py. native_direct_test(direct route, check mode, 3 frames) run under Wine withRADV_DEBUG=shaderstats(VGPRs, waves, LDS) andRADV_DEBUG=shaders(ACO's ISA).- Kernels matched by their WMMA count: each SPIR-V cooperative-matrix multiply-add becomes two
v_wmmain ACO's ISA (736, 560 and 1312 for the three), and by LDS size where that could be read. - GPU times are from
WG_D3D12_PROFILEin the same harness. Profiling adds overhead, so treat them as rough.
What could be done (your call):
- Restructure these kernels so they need fewer registers on any compiler. That would change the Windows DXIL too.
- Report it to Mesa (ACO) with these kernels' SPIR-V as a reproducer. They're WrongGPU's own MIT-licensed code, so the SPIR-V can be shared. I can put that together if you'd rather it went that way.
- Leave it. On Linux this is a few tenths of a millisecond, not a correctness problem.
Related: #29, #10.
- Linguagem predominante
- C++
- Estrelas
- 12
- Forks
- 2
- Merge médio
- 3h 10min
- PRs com merge (30d)
- 171
Preparar o ambiente
- Sem Dockerfile nem arquivo Docker Compose
- Tem um modelo de pull request
- Ler o guia de contribuição
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de phantoslayer21/wronggpu
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 88/100
phantoslayer21/wronggpu#275 ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 82/100
phantoslayer21/wronggpu#274 ·
Mantenedores costumam responder em até 1 dia
-
bug
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 88/100
phantoslayer21/wronggpu#241 ·
Mantenedores costumam responder em até 1 dia
-
bug build
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 74/100
phantoslayer21/wronggpu#234 ·
Mantenedores costumam responder em até 1 dia
-
Launcher tests: "an older record: update available" fakes a version newer than the test buildAbertabug build
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 80/100
phantoslayer21/wronggpu#233 ·
Mantenedores costumam responder em até 1 dia
Todas as issues de phantoslayer21/wronggpu
Issues semelhantes
-
Dificuldade 1/5 1-3 horas Facilidade para iniciantes 77/100
Mantenedores costumam responder em até 1 dia
-
bug good first issue
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 75/100
ReyeMe/SaturnRingLib#155 ·
-
bug
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 62/100
Nheko-Reborn/nheko#2092 ·
-
Dificuldade 1/5 1-3 horas Facilidade para iniciantes 78/100
isocpp/CppCoreGuidelines#2345 ·
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 71/100
ROCm/rocm-libraries#16108 ·
Mantenedores costumam responder em até 2 dias