HIP: accelerate PSF accumulation and restore parallel producers
Cooperate across 32 lanes per PSF and use two completion-protected staging slots with complete batch timing. Restore coarse OpenMP event production while serializing shared GPU submissions and direct fallback boundaries. Add bounded benchmarks, streaming and renderer regressions, and preserve validation evidence and ownership documentation.
This commit is contained in:
1 parent
265d7b95d5
commit
e1ec480669
45 files changed
+10251
-95
No files matched your search
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"base_commit": "265d7b95d5b916ec4768d174d73ad963a43f0088",
|
||||
"optimized_source": "uncommitted worktree changes",
|
||||
"compiler": "HIP version: 7.2.53210-9999\nclang version 22.1.8\nTarget: x86_64-pc-linux-gnu\nThread model: posix\nInstalledDir: /usr/lib/llvm/22/bin\nConfiguration file: /etc/clang/22/x86_64-pc-linux-gnu-clang++.cfg",
|
||||
"hip_config_version": "7.2.53210-9999",
|
||||
"kernel": "Linux 6.18.41-gentoo",
|
||||
"cpu": [
|
||||
"CPU(s): 16",
|
||||
"Model name: 12th Gen Intel(R) Core(TM) i7-12700K",
|
||||
"Thread(s) per core: 2",
|
||||
"Core(s) per socket: 8",
|
||||
"NUMA node0 CPU(s): 0-15"
|
||||
],
|
||||
"OMP_NUM_THREADS": 16,
|
||||
"catalog_workers": 4,
|
||||
"hip_flags": "--offload-arch=gfx1201 -std=c++17 -O2 -Wall -Wextra -Wpedantic",
|
||||
"cpu_flags": "-std=c11 -march=native -pipe -Wall -Wextra -Wpedantic -O2 -DNDEBUG -fopenmp",
|
||||
"event_bytes": 56,
|
||||
"event_capacity": 16384,
|
||||
"device_staging_slots": 2,
|
||||
"sha256": {
|
||||
"src/frame.c": "338d24eaa89d2d4c1e5a7f34d08ca827db13bb79ac3a6caeb155a731390ab023",
|
||||
"src/hip_psf.hip": "b93fed04034a97e1eb25f3fc234da995287bf0c3fcde50609f95b0b3f4052a75",
|
||||
"src/hip_psf.h": "00502f3d95c30d4c3d346e49dcf0e3cb846b5d461c2bfd5b3f24c7257791fad0",
|
||||
"tests/benchmark_hip_psf.hip": "56cccf515b66762acb824556681c9f6986c0ffe3e3346eeadac23bc6d5926aa4",
|
||||
"build/Release/schwarzschild_sky_hip": "1c340e1d8ab008e892101b46132069255ab92eb0d200bd91b2b300a4f4dacf6e",
|
||||
"/tmp/gr-schwarzschild-hip-baseline": "de945e3dc826d559e1f8218a56d24f524c06e5382c8aa43667f9ac1fe5d2d719",
|
||||
"/tmp/gr-hip-baseline-src/build/Release/schwarzschild_sky_hip": "de945e3dc826d559e1f8218a56d24f524c06e5382c8aa43667f9ac1fe5d2d719",
|
||||
"output/lens/schwarzschild_galactic_center_R100_45deg_16_4_4k_.grlens": "905f960aea2d276f9586c79fba545a72cf742311e9e7e18faea293835c68bf28"
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user