wyj
11e703e33d
Archive fixed catalog subsets and captured events, manifests, reproducible commands, raw timing and regression logs, and device resource evidence. Document distribution-dependent tile reduction gains and independent indexed producer throughput. Update the GPU plan and renderer design while retaining the production atomic path. Preserve historical measurement metadata and exclude generated Python bytecode.
11 lines
962 B
Plaintext
11 lines
962 B
Plaintext
# Repository root; all builds complete before final_cases.py is started.
|
|
make psf-capture
|
|
make PSF_BACKEND=hip HIP_CXXFLAGS='--offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic' hip-psf-replay
|
|
make build/Release/make_psf_fixture
|
|
make -j4 SPACETIME=minkowski PSF_BACKEND=cpu ENABLE_HDR=1 backend
|
|
make -j4 SPACETIME=minkowski PSF_BACKEND=hip ENABLE_HDR=1 HIP_CXXFLAGS='--offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic' backend hip-psf-test
|
|
make -j4 SPACETIME=schwarzschild PSF_BACKEND=cpu ENABLE_HDR=1 backend
|
|
make -j4 SPACETIME=schwarzschild PSF_BACKEND=hip ENABLE_HDR=1 HIP_CXXFLAGS='--offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic' backend
|
|
hipcc --offload-arch=gfx1201 --cuda-device-only -std=c++17 -O2 -Isrc -S tests/replay_psf.hip -o /tmp/gr-psf-replay-device.s
|
|
rg -n '\.name:|\.vgpr_count:|\.sgpr_count:|\.private_segment_fixed_size:|\.group_segment_fixed_size:|\.max_flat_workgroup_size:' /tmp/gr-psf-replay-device.s
|