mirror of
https://github.com/marian-nmt/marian.git
synced 2024-09-17 09:47:34 +03:00
Avoid Ampere misaligment issue
This commit is contained in:
parent
49e379bba5
commit
8b818b7c07
@ -41,6 +41,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
|
||||
- Broken links to MNIST data sets
|
||||
|
||||
### Changed
|
||||
- Set REQUIRED_BIAS_ALIGNMENT = 16 in tensors/gpu/prod.cpp to avoid memory-misalignment on certain Ampere GPUs.
|
||||
- For BUILD_ARCH != native enable all intrinsics types by default, can be disabled like this: -DCOMPILE_AVX512=off
|
||||
- Moved FBGEMM pointer to commit c258054 for gcc 9.3+ fix
|
||||
- Change compile options a la -DCOMPILE_CUDA_SM35 to -DCOMPILE_KEPLER, -DCOMPILE_MAXWELL,
|
||||
|
@ -1 +1 @@
|
||||
Subproject commit 1afd4eb1014ac451c6a3d6f9b5d34c322902e624
|
||||
Subproject commit 7d612ca5e4b27a76f92584dad76d240e34f216d0
|
@ -22,7 +22,7 @@ namespace gpu {
|
||||
// It seems that the bias must be 8 byte aligned for the cublasLt epilogue to work. Therefore,
|
||||
// if the bias pointer is not 8 byte aligned, we do a normal matmul in cublasLt and invoke a
|
||||
// custom epilogue kernel.
|
||||
static constexpr int REQUIRED_BIAS_ALIGNMENT = 8;
|
||||
static constexpr int REQUIRED_BIAS_ALIGNMENT = 16; // @TODO: MJD: changed this to 16 to avoid alignment error on A100. Seems to work fine.
|
||||
|
||||
// Used to set preferences for cublasLt to filter out algos if matrices to not meet default 256 byte alignment
|
||||
int getAlignmentUpTo256(const void *ptr) {
|
||||
|
Loading…
Reference in New Issue
Block a user