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

vulkan : added the PAD_REFLECT_1D operation (#26586)

Browse Source 
* vulkan : added PAD_REFLECT_1D operation

Implemented the GGML_OP_PAD_REFLECT_1D operation for the Vulkan backend

Changes:
- pad_reflect_1d.comp: implemented the GLSL compute shader with reflection logic
- vulkan-shaders-gen.cpp: register the shader for SPIR-V compilation
- ggml-vulkan.cpp: pushed constants struct, pipeline creation,
  supports_op, dispatch function, compute switch and debug validation

Tested the PAD_REFLECT_1D on Intel Iris Xe (Vulkan 1.4, Mesa 25.2.8):

Correctness:
  PAD_REFLECT_1D(type=f32,ne_a=[512,34,2,1],pad_0=10,pad_1=9) = Pass
  PAD_REFLECT_1D(type=f32,ne_a=[3000,384,4,1],pad_0=10,pad_1=9) = Pass
  2/2 tests passed
 - All test are passed

Performance:
  ne_a=[512,34,2,1] -> 5.38 us/run, 24.55 GB/s
  ne_a=[3000,80,1,1] -> 30.09 us/run, 59.62 GB/s
  ne_a=[3000,384,4,1] -> 158.31 us/run, 54.39 GB/s

* Update ggml/src/ggml-vulkan/vulkan-shaders/pad_reflect_1d.comp

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
This commit is contained in:
Safi Ullah
2026-08-22 14:42:20 -05:00
committed by GitHub
co-authored by Jeff Bolz
parent b21e4de745
commit 3f545becce
3 changed files with 70 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+1
View File
@@ -896,6 +896,7 @@ void process_shaders() {
string_to_spv("scale_f32", "scale.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});
string_to_spv("pad_f32", "pad.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("pad_reflect_1d_f32", "pad_reflect_1d.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("concat_i8", "concat.comp", {{"A_TYPE", "uint8_t"}, {"B_TYPE", "uint8_t"}, {"D_TYPE", "uint8_t"}});
string_to_spv("concat_i16", "concat.comp", {{"A_TYPE", "uint16_t"}, {"B_TYPE", "uint16_t"}, {"D_TYPE", "uint16_t"}});