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

CUDA: rename macros to avoid conflicts with WinAPI (#10736)

Browse source 
* Renames NVIDIA GPU-architecture flags to avoid name clashes with WinAPI. (e.g. CC_PASCAL, GPU architecture or WinAPI pascal compiler flag?)

* Reverts erroneous rename in SYCL-code.

* Renames GGML_CUDA_MIN_CC_DP4A to GGML_CUDA_CC_DP4A.

* Renames the rest of the compute capability macros for consistency.
This commit is contained in:
Andreas Kieslinger 2024-12-10 18:23:24 +01:00 • committed by GitHub
parent a86ad841f1
commit 750cb3e246
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 69 additions and 71 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-cuda/mma.cuh
View file

@ -171,7 +171,7 @@ struct mma_int_C_I16J8 {
__device__ __forceinline__ void mma_K4(const mma_int_A_I16K4 & mma_A, const mma_int_B_J8K4 & mma_B) {
#ifdef INT8_MMA_AVAILABLE
#if __CUDA_ARCH__ >= CC_AMPERE
#if __CUDA_ARCH__ >= GGML_CUDA_CC_AMPERE
asm("mma.sync.aligned.m16n8k16.row.col.s32.s8.s8.s32 {%0, %1, %2, %3}, {%4, %5}, {%6}, {%0, %1, %2, %3};"
: "+r"(x[0]), "+r"(x[1]), "+r"(x[2]), "+r"(x[3])
: "r"(mma_A.x[0]), "r"(mma_A.x[1]), "r"(mma_B.x[0]));
@ -183,7 +183,7 @@ struct mma_int_C_I16J8 {
asm("mma.sync.aligned.m8n8k16.row.col.s32.s8.s8.s32 {%0, %1}, {%2}, {%3}, {%0, %1};"
: "+r"(x[2]), "+r"(x[3])
: "r"(mma_A.x[1]), "r"(mma_B.x[0]));
#endif // __CUDA_ARCH__ >= CC_AMPERE
#endif // __CUDA_ARCH__ >= GGML_CUDA_CC_AMPERE
#else
GGML_UNUSED(mma_A);
GGML_UNUSED(mma_B);
@ -193,7 +193,7 @@ struct mma_int_C_I16J8 {
__device__ __forceinline__ void mma_K8(const mma_int_A_I16K8 & mma_A, const mma_int_B_J8K8 & mma_B) {
#ifdef INT8_MMA_AVAILABLE
#if __CUDA_ARCH__ >= CC_AMPERE
#if __CUDA_ARCH__ >= GGML_CUDA_CC_AMPERE
asm("mma.sync.aligned.m16n8k32.row.col.s32.s8.s8.s32 {%0, %1, %2, %3}, {%4, %5, %6, %7}, {%8, %9}, {%0, %1, %2, %3};"
: "+r"(x[0]), "+r"(x[1]), "+r"(x[2]), "+r"(x[3])
: "r"(mma_A.x[0]), "r"(mma_A.x[1]), "r"(mma_A.x[2]), "r"(mma_A.x[3]), "r"(mma_B.x[0]), "r"(mma_B.x[1]));
@ -211,7 +211,7 @@ struct mma_int_C_I16J8 {
asm("mma.sync.aligned.m8n8k16.row.col.s32.s8.s8.s32 {%0, %1}, {%2}, {%3}, {%0, %1};"
: "+r"(x[2]), "+r"(x[3])
: "r"(mma_A.x[3]), "r"(mma_B.x[1]));
#endif // __CUDA_ARCH__ >= CC_AMPERE
#endif // __CUDA_ARCH__ >= GGML_CUDA_CC_AMPERE
#else
GGML_UNUSED(mma_A);
GGML_UNUSED(mma_B);