Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

musa: remove Clang builtins mapping (#9421)

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2024-09-11 09:46:55 +08:00 committed by GitHub
parent 51b6038636
commit b34e023480
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
ggml/src/ggml-cuda/vendors/musa.h vendored
View File

@ -130,42 +130,3 @@
#define cudaKernelNodeParams musaKernelNodeParams #define cudaKernelNodeParams musaKernelNodeParams
#define cudaStreamCaptureModeRelaxed musaStreamCaptureModeRelaxed #define cudaStreamCaptureModeRelaxed musaStreamCaptureModeRelaxed
#define cudaStreamEndCapture musaStreamEndCapture #define cudaStreamEndCapture musaStreamEndCapture
// XXX: Clang builtins mapping
#define __vsub4 __vsub4_musa
#define __vcmpeq4 __vcmpeq4_musa
#define __vcmpne4 __vcmpne4_musa
#ifndef __has_builtin
#define __has_builtin(x) 0
#endif
typedef uint8_t uint8x4_t __attribute__((ext_vector_type(4)));
static __device__ __forceinline__ int __vsub4_musa(const int a, const int b) {
return __vsubss4(a, b);
}
static __device__ __forceinline__ unsigned int __vcmpeq4_musa(unsigned int a, unsigned int b) {
const uint8x4_t& va = reinterpret_cast<const uint8x4_t&>(a);
const uint8x4_t& vb = reinterpret_cast<const uint8x4_t&>(b);
unsigned int c;
uint8x4_t& vc = reinterpret_cast<uint8x4_t&>(c);
#pragma unroll
for (int i = 0; i < 4; ++i) {
vc[i] = va[i] == vb[i] ? 0xff : 0x00;
}
return c;
}
static __device__ __forceinline__ unsigned int __vcmpne4_musa(unsigned int a, unsigned int b) {
const uint8x4_t& va = reinterpret_cast<const uint8x4_t&>(a);
const uint8x4_t& vb = reinterpret_cast<const uint8x4_t&>(b);
unsigned int c;
uint8x4_t& vc = reinterpret_cast<uint8x4_t&>(c);
#pragma unroll
for (int i = 0; i < 4; ++i) {
vc[i] = va[i] == vb[i] ? 0x00 : 0xff;
}
return c;
}