Popular repositories
-
-
Forked from microsoft/DirectXShaderCompiler
This repo hosts the source for the DirectX Shader Compiler which is based on LLVM/Clang.
C++
-
Forked from llvm/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at…
C++
-
Forked from google/uVkCompute
A micro Vulkan compute pipeline and a collection of benchmarking compute shaders
C++
-
514 contributions in the last year
Activity overview
Contribution activity
May 2021
Created 23 commits in 2 repositories
Created a pull request in google/iree that received 5 comments
Disable folding unit dimension reshapes during fusion
This fixes regression in MobileBert GPU.
Opened 8 other pull requests in 1 repository
google/iree
1
open
7
merged
- Extend vector transfer scalarization fallback
- Revert "Fix how to get the orignal shape in generic op launch config" (#5603)
- [CUDA codegen] Add basic support for convolution
- Remove patterns from VectorToGPU
- Add simple heuristic to decide if TensorReshape should be folded during fusion
- Improve the vector flow for SPIR-V codegen
- Revert workaround in LinalgVectorizePass now that vector unroll is fixed
- Re-enable mobilenet-V2 benchmark

