Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/39277
This PR contains initial changes that makes PyTorch build with Ampere GPU, CUDA 11, and cuDNN 8.
TF32 related features will not be included in this PR.
Test Plan: Imported from OSS
Differential Revision: D21832814
Pulled By: malfet
fbshipit-source-id: 37f9c6827e0c26ae3e303580f666584230832d06
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/33554
NVCC/GCC accepts the existing syntax, but not Clang which requires a proper escape. Here `%laneid` is one of the many registers that CUDA's pseudo-asm provides [1]. And using the extra `%` doesn't change the semantics, as PTX expects `%laneid` value after it's processed by the asm tool.
1. https://docs.nvidia.com/cuda/parallel-thread-execution/index.html
Test Plan:
```lang=bash
buck build mode/opt -c fbcode.cuda_use_clang=true //fblearner/flow/projects/dper:workflow
buck build mode/opt //fblearner/flow/projects/dper:workflow
Reviewed By: bddppq
Differential Revision: D20003621
fbshipit-source-id: 8e550e55a3455925e7bd92c6df3e504b5d38c2dc
Summary:
This PR contains changes for:
1. Adding HIP top_k operator in Caffe2
2. Added HIP equivalent definitions of GPUDefs and GPUScanUtils
3. Removing the top_k operator test from ROCm test ignore list
4. Bug fixes in related code in THC/THCAsmUtils.cuh
Differential Revision: D12986451
Pulled By: bddppq
fbshipit-source-id: 6d5241fb674eaeb7cde42166426ac88043b83504
Summary:
Adds support for the CUDA 9 toolkit.
Includes new fp16 data type fixes, and changes to warp-synchronous programming. Also updates CUB third-party repo for CUDA 9 support.
Closes https://github.com/caffe2/caffe2/pull/853
Differential Revision: D5548507
Pulled By: Yangqing
fbshipit-source-id: c7fd2edb623f2aa8c67b9a1000efc8f71e6832ab
Summary:
This is a real implementation (not GPUFallbackOp) of the TopKOp for GPU.
There are two algorithm implementations:
-for k <= 512, it maps to a warp-wide min-heap implementation, which requires only a single scan of the input data.
-for k > 512, it maps to a multi-pass radix selection algorithm that I originally wrote in cutorch. I took the recent cutorch code and removed some cutorch-specific things as it made sense.
Also added several utility files that one or the other implementations use, some from the Faiss library and some from the cutorch library.
Reviewed By: jamesr66a
Differential Revision: D5248206
fbshipit-source-id: ae5fa3451473264293516c2838f1f40688781cf3
