CUDA Turing TC (#8597)

* init turing tc

* reorder tc

* hotfix: remove some spaces

* revert var name to x

* consistent order of factors

* revert order of terms to match old stuff

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
This commit is contained in:
ignaciosica
2025-01-14 15:35:14 -03:00
committed by GitHub
parent cbfd51f5a5
commit d5a646d492
4 changed files with 31 additions and 15 deletions

View File

@@ -166,6 +166,7 @@ jobs:
- name: Test emulated CUDA tensor cores
run: |
DEBUG=2 EMULATE_CUDA=1 FORWARD_ONLY=1 PYTHON=1 python3 test/test_ops.py TestOps.test_gemm_fp16
DEBUG=2 EMULATE_CUDA_SM75=1 FORWARD_ONLY=1 PYTHON=1 python3 test/test_ops.py TestOps.test_gemm_fp16
PYTHONPATH="." DEBUG=2 EMULATE_CUDA=1 FORWARD_ONLY=1 PYTHON=1 python3 test/test_linearizer.py TestLinearizer.test_tensor_cores TestLinearizer.test_tensor_cores_padded
- name: Test emulated INTEL OpenCL tensor cores
run: DEBUG=2 EMULATE_INTEL=1 FORWARD_ONLY=1 PYTHON=1 HALF=1 N=64 python3 ./extra/gemm/simple_matmul.py