Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Avoid PDL race conditions by disabling __restrict__ when PDL is used (#24030)

Browse Source 
* Removes __restrict__ from PDL kernel headers due to incompatibility with
PDL. Adds preprocessor directives based on arch in kernel body to add
__restrict__ to retain performance on older architectures.

* Simplifies new __restrict__ usage via macro

* Add hopper to PDL __restrict__ fix.

Co-authored-by: Oliver Simons <osimons@nvidia.com>

---------

Co-authored-by: Oliver Simons <osimons@nvidia.com>
This commit is contained in:
Andreas Kieslinger
2026-06-03 13:56:42 +02:00
committed by GitHub
co-authored by Oliver Simons
parent 3571fa5435
commit 9e58d4d692
14 changed files with 145 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/getrows.cu
+4 -1
View File
@@ -42,7 +42,7 @@ static __global__ void k_get_rows(
template<typename src0_t, typename dst_t>
static __global__ void k_get_rows_float(
const src0_t * __restrict__ src0, const int32_t * __restrict__ src1, dst_t * __restrict__ dst,
const src0_t * src0_ptr, const int32_t * src1_ptr, dst_t * dst_ptr,
const int64_t ne00, /*const int64_t ne01, const int64_t ne02, const int64_t ne03,*/
/*const int64_t ne10,*/ const int64_t ne11, const uint3 ne12_fdv, /*const int64_t ne13,*/
/*const size_t s0,*/ const size_t s1, const size_t s2, const size_t s3,
@@ -50,6 +50,9 @@ static __global__ void k_get_rows_float(
const size_t s10, const size_t s11, const size_t s12/*, const size_t s13*/) {
ggml_cuda_pdl_lc();
const src0_t * GGML_CUDA_RESTRICT src0 = src0_ptr;
const int32_t * GGML_CUDA_RESTRICT src1 = src1_ptr;
dst_t * GGML_CUDA_RESTRICT dst = dst_ptr;
ggml_cuda_pdl_sync();
for (int64_t z = blockIdx.z; z < ne11*(int64_t)ne12_fdv.z; z += gridDim.z) {
for (int64_t i00 = blockIdx.y*blockDim.x + threadIdx.x; i00 < ne00; i00 += gridDim.y*blockDim.x) {