Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CUDA]batch_matmul tensorcore schedule #7146

Merged
merged 12 commits into from
Jan 11, 2021
+422 −2
Merged

[CUDA]batch_matmul tensorcore schedule #7146

Changes from 1 commit
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
9844939
add batch_matmul_tensorcore
Meteorix Oct 29, 2020
1ea5ea8
add bmm cublas autotune
Meteorix Oct 29, 2020
debec15
add bmm tests
Meteorix Nov 9, 2020
a1808b4
out_shape for bmm_tensorcore
Meteorix Nov 9, 2020
a2eee2a
fix comments
Meteorix Dec 22, 2020
bf8936a
code format
Meteorix Dec 30, 2020
8ce932c
add todos for tensorcore datatype checking
Meteorix Dec 30, 2020
595b9f1
fix lint
Meteorix Dec 31, 2020
3da8299
fix lint
Meteorix Dec 31, 2020
cdca880
fix have_tensorcore
Meteorix Dec 31, 2020
72a5885
add dtype check for batch_matmul_tensorcore
Meteorix Jan 8, 2021
618b4bf
fix
Meteorix Jan 8, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix lint
  • Loading branch information
@Meteorix
Meteorix committed Dec 31, 2020
commit 3da829919fc073cf9077ecf7d8e1ab8cb7c3eead
2 changes: 1 addition & 1 deletion python/tvm/topi/cuda/batch_matmul_tensorcore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,7 +300,7 @@ def batch_matmul_tensorcore_cuda(x, y):
(M % 8 == 0 and K % 16 == 0 and N % 32 == 0)
or (M % 16 == 0 and K % 16 == 0 and N % 16 == 0)
or (M % 32 == 0 and K % 16 == 0 and N % 8 == 0)
), "The shape of (M, K, N) must be multiple of (16, 16, 16) or (32, 16, 8) or (8, 16, 32) for now"
), "The shape of (M, K, N) must be multiple of (16, 16, 16) or (32, 16, 8) or (8, 16, 32)"

x_16 = te.compute((batch, M, K), lambda b, i, k: x[b, i, k].astype("float16"))
y_16 = te.compute((batch, N, K), lambda b, j, k: y[b, j, k].astype("float16"))
Expand Down