commaai
/
tinygrad
mirror of https://github.com/commaai/tinygrad.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

correct kernargs alignment (#6984)

This commit is contained in:
nimlgen 2024-10-11 00:06:28 +03:00 committed by GitHub
parent 2b17279d4e
commit f9d454aed5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/benchmark.yml vendored
View File

@ -500,6 +500,8 @@ jobs:
run: PYTHONPATH="." QCOM=1 python3 examples/openpilot/compile3.py https://github.com/commaai/openpilot/raw/v0.9.7/selfdrive/modeld/models/supercombo.onnx
- name: openpilot compile3 0.9.7+ tomb raider
run: PYTHONPATH="." QCOM=1 python3 examples/openpilot/compile3.py https://github.com/commaai/openpilot/raw/e8bea2c78ffa92685ece511e9b554122aaf1a79d/selfdrive/modeld/models/supercombo.onnx
- name: openpilot dmonitoring compile3 0.9.7
run: PYTHONPATH="." QCOM=1 python3 examples/openpilot/compile3.py https://github.com/commaai/openpilot/raw/v0.9.7/selfdrive/modeld/models/dmonitoring_model.onnx
- name: Run process replay tests
run: cp test/external/process_replay/process_replay.py ./process_replay.py && git fetch origin master && git -c advice.detachedHead=false checkout origin/master && PYTHONPATH=. python3 process_replay.py
- uses: actions/upload-artifact@v4

3
tinygrad/runtime/ops_qcom.py
View File

@ -219,7 +219,8 @@ class QCOMProgram(HCQProgram):
self.max_threads = min(1024, ((384 * 32) // (max(1, (self.fregs + round_up(self.hregs, 2) // 2)) * 128)) * 128)
device._ensure_stack_size(self.hw_stack_offset * 4)
super().__init__(QCOMArgsState, self.device, self.name, kernargs_alloc_size=2048 + (self.tex_cnt + self.ibo_cnt) * 0x40 + self.samp_cnt * 0x10)
kernargs_alloc_size = round_up(2048 + (self.tex_cnt + self.ibo_cnt) * 0x40 + self.samp_cnt * 0x10, 0x100)
super().__init__(QCOMArgsState, self.device, self.name, kernargs_alloc_size=kernargs_alloc_size)
def __call__(self, *bufs, global_size:Tuple[int,int,int]=(1,1,1), local_size:Tuple[int,int,int]=(1,1,1), vals:Tuple[int, ...]=(), wait=False):
if self.max_threads < prod(local_size): raise RuntimeError("Too many resources requested for launch")