Converting CUDA program to mlir (gpu, linalg etc.)
|
|
9
|
156
|
May 21, 2025
|
Help with MLIR CUDA Stream Management for Multiple CUDNN Convolutions
|
|
2
|
72
|
May 13, 2025
|
In clang cuda compiling, Can I call gcc with host code build, and use clang+llvm with device code build?
|
|
3
|
53
|
March 14, 2025
|
[RFC] Use the 'new' offloding driver for CUDA and HIP compilation by default
|
|
27
|
814
|
January 10, 2025
|
Std::invoke_result_t of functor's __device__ operator()
|
|
5
|
60
|
December 20, 2024
|
CMake CUDA opinions
|
|
2
|
83
|
December 9, 2024
|
Copy capture rules for [=, *this]
|
|
5
|
153
|
March 12, 2024
|
Showcasing LLVM/Offload
|
|
0
|
882
|
December 15, 2023
|
How to implement vectorloadStore pass for a new GPU backend?
|
|
1
|
326
|
June 28, 2023
|
About the plan for CUDA Fortran support in Flang
|
|
0
|
367
|
July 3, 2023
|
LLVM reordering blocks breaks ptxas divergence analysis
|
|
31
|
748
|
June 13, 2023
|
Compiling CUDA code fails
|
|
16
|
3045
|
May 25, 2023
|
Does MLIR supports CUDA source code generation?
|
|
3
|
1105
|
May 17, 2023
|
CUCLANG struggle with cooperative groups headers
|
|
4
|
486
|
February 28, 2023
|
[RFC] Floating-point accuracy control
|
|
32
|
2826
|
February 11, 2023
|
NVPTX: SyncScope/AtomicOrdering of atomicrmw support?
|
|
1
|
222
|
February 7, 2023
|
CUDA Support for clang-tidy
|
|
6
|
732
|
July 25, 2022
|
Cannot pass __device__ function as template parameter in CUDA?
|
|
3
|
999
|
June 28, 2022
|
Clang++ 15.0.0 with OpenMP offloading to nVidia GPU on Windows with VS2022CE - too many errors
|
|
4
|
1555
|
June 5, 2022
|
LLVM@14.0.0 doesn't support well on CUDA@11.5.0 about variadic function and other definitions
|
|
8
|
1044
|
May 13, 2022
|
[CUDA] CUDA device code does not support variadic functions in clang
|
|
1
|
1087
|
February 24, 2022
|
NVPTX: Calling convention for aggregate arguments passed by value
|
|
13
|
678
|
January 24, 2022
|