mirror of
https://github.com/ROCm/jax.git
synced 2025-04-16 03:46:06 +00:00
b6306e3953
In the batched LU decomposition in cuBLAS, the output buffer is required to be a pointer of pointers to the appropriate batch matrices. Previously this reshaping was done on the host and then copied to the device, requiring a synchronization, but it seems straightforward to instead implement a tiny CUDA kernel to do this work. This definitely isn't a bottleneck or a high priority change, but this seemed like a reasonable time to fix a longstanding TODO. PiperOrigin-RevId: 663686539
31 lines
1.0 KiB
C++
31 lines
1.0 KiB
C++
/* Copyright 2024 The JAX Authors.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
==============================================================================*/
|
|
|
|
#ifndef JAXLIB_GPU_MAKE_BATCH_POINTERS_H_
|
|
#define JAXLIB_GPU_MAKE_BATCH_POINTERS_H_
|
|
|
|
#include "jaxlib/gpu/vendor.h"
|
|
|
|
namespace jax {
|
|
namespace JAX_GPU_NAMESPACE {
|
|
|
|
void MakeBatchPointersAsync(gpuStream_t stream, void* buffer_in,
|
|
void* buffer_out, int batch, int batch_elem_size);
|
|
|
|
} // namespace JAX_GPU_NAMESPACE
|
|
} // namespace jax
|
|
|
|
#endif // JAXLIB_GPU_MAKE_BATCH_POINTERS_H_
|