github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-29 03:00:14 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix __launch_bounds__ and benchmark TC MATMUL (#1575)

Browse Source 
* fix

* benchmark matmul
This commit is contained in:
George Hotz
2023-08-19 10:54:39 -07:00
committed by GitHub
parent 92754e177c
commit ad7d26c393
3 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/benchmark.yml vendored
View File

@@ -20,6 +20,8 @@ jobs:
run: python3 test/external/external_model_benchmark.py
- name: Test speed vs torch
run: BIG=2 MPS=1 python3 test/test_speed_v_torch.py | tee torch_speed.txt
- name: Run Tensor Core GEMM
run: DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt
- name: Run Stable Diffusion
run: |
ln -s ~/tinygrad/weights/sd-v1-4.ckpt weights/sd-v1-4.ckpt
@@ -49,6 +51,7 @@ jobs:
llama_jitted.txt
gpt2_unjitted.txt
gpt2_jitted.txt
matmul.txt
testamdbenchmark:
name: AMD Benchmark
@@ -63,6 +66,8 @@ jobs:
run: python3 test/external/external_model_benchmark.py
- name: Test speed vs torch
run: BIG=2 TORCHCUDA=1 python3 test/test_speed_v_torch.py | tee torch_speed.txt
- name: Run Tensor Core GEMM
run: HIP=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt
- name: Run Stable Diffusion
run: |
ln -s ~/tinygrad/weights/sd-v1-4.ckpt weights/sd-v1-4.ckpt
@@ -92,3 +97,4 @@ jobs:
llama_jitted.txt
gpt2_unjitted.txt
gpt2_jitted.txt
matmul.txt