diff options
Diffstat (limited to 'src/kernels/level3/xgemm_part1.opencl')
-rw-r--r-- | src/kernels/level3/xgemm_part1.opencl | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/src/kernels/level3/xgemm_part1.opencl b/src/kernels/level3/xgemm_part1.opencl index cc03696e..306280bc 100644 --- a/src/kernels/level3/xgemm_part1.opencl +++ b/src/kernels/level3/xgemm_part1.opencl @@ -125,8 +125,9 @@ R"( #define USE_SUBGROUP_SHUFFLING 0 // Optionally enables subgroup shuffling for Intel GPUs #endif -// Intel subgroups (https://www.khronos.org/registry/OpenCL/extensions/intel/cl_intel_subgroups.txt) +// Intel subgroups (https://www.khronos.org/registry/OpenCL/extensions/intel/cl_intel_subgroups.html) #if USE_SUBGROUP_SHUFFLING == 1 && SUBGROUP_SHUFFLING_INTEL == 1 + #pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation: enable #define SUBGROUP_SIZE 8 // Assumes subgroup size is always 8 on Intel GPUs #endif |