Ye Luo ffd159d8e9 [OpenMP] cmake option LIBOMPTARGET_NVPTX_MAX_SM for nvptx device RTL ...

It allows customizing MAX_SM for non-flagship GPU and reduces graphic memory usage.

In addition, so far the size is hard-coded up to __CUDA_ARCH__ 700 and is already a hassle for 800.
Introduce MAX_SM for 800 and protect future arch

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D88185

2020-09-24 12:39:59 -04:00

..

amdgcn

[OpenMP][NFC] Remove unused and untested code from the device runtime

2020-07-10 19:09:41 -05:00

common

[OpenMP][AMDGPU] Use DS_Max_Warp_Number instead of WARPSIZE

2020-09-07 05:15:21 -04:00

nvptx

[OpenMP] cmake option LIBOMPTARGET_NVPTX_MAX_SM for nvptx device RTL

2020-09-24 12:39:59 -04:00

CMakeLists.txt

[libomptarget][nfc] Disable amdgcn rtl build. The cmake logic for finding llvm is misbehaving.

2020-03-21 00:01:03 +00:00

interface.h

[OpenMP][NFC] Remove unused (always fixed) arguments

2020-07-11 00:51:51 -05:00