-
Notifications
You must be signed in to change notification settings - Fork 215
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.
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
Bugfix for batched gemv #2481
base: master
Are you sure you want to change the base?
Bugfix for batched gemv #2481
Conversation
Fix incorrect definition of m and n in gemv_strided_batched!
Shouldn't CUDA.jl/lib/cublas/wrappers.jl Lines 426 to 438 in 8b54f85
Can you add a test that covers the case that doesn't work right now, and works after the change? |
No, according to the official cuBLAS documentation, definitions of For
For
For |
I will try to add some tests this week. |
See also the CUDA.jl/lib/cublas/wrappers.jl Lines 378 to 384 in bbe625b
|
all the input dimensions should be identical for gemv_batched!
@maleadt A similar bug was found on |
LGTM, let's just ping the original author of these functions: @lpawela |
@maleadt What is the status of this PR? |
It hangs on me, sorry. I'll have a look within a couple of days. |
I have problems launching tests on this patch.
when launching julia> CUDA.versioninfo()
CUDA runtime 12.6, artifact installation
CUDA driver 12.4
NVIDIA driver 550.90.7
CUDA libraries:
- CUBLAS: 12.6.0
- CURAND: 10.3.7
- CUFFT: 11.2.6
- CUSOLVER: 11.6.4
- CUSPARSE: 12.5.2
- CUPTI: 2024.3.0 (API 24.0.0)
- NVML: 12.0.0+550.90.7
Julia packages:
- CUDA: 5.5.0
- CUDA_Driver_jll: 0.10.0+0
- CUDA_Runtime_jll: 0.15.1+0
Toolchain:
- Julia: 1.10.2
- LLVM: 15.0.7
1 device:
0: NVIDIA GeForce RTX 3080 (sm_86, 7.857 GiB / 10.000 GiB available) |
The changes in this PR seem to triggering some illegal memory access. |
I'm seeing similar issues locally, but I'm having a hard time isolating the problem. Many times, the |
Fix incorrect definition of m and n in gemv_strided_batched!