vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add __shfl_sync to HIP

Browse source
This commit is contained in:
Johannes Gäßler 2025-02-02 13:32:28 +01:00
parent e3b7c574b1
commit 817f87b2bb
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/src/ggml-cuda/vendors/hip.h vendored
View file

@ -25,6 +25,7 @@
#define CU_MEM_LOCATION_TYPE_DEVICE hipMemLocationTypeDevice
#define CU_MEM_ACCESS_FLAGS_PROT_READWRITE hipMemAccessFlagsProtReadWrite
#define CU_CHECK(fn) {hipError_t err = fn; if(err != hipSuccess) { GGML_ABORT("HipVMM Failure: %s\n", hipGetErrorString(err)); }}
#define __shfl_sync(mask, var, laneMask, width) __shfl(var, laneMask, width)
#define __shfl_xor_sync(mask, var, laneMask, width) __shfl_xor(var, laneMask, width)
#define cublasComputeType_t hipblasDatatype_t //deprecated, new hipblasComputeType_t not in 5.6
#define cublasCreate hipblasCreate