ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-19 15:23:45 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

vulkan: Use push constant offset to handle misaligned descriptors (llama/10987)

Browse Source
This commit is contained in:
Jeff Bolz
2024-12-29 02:35:11 -06:00
committed by Georgi Gerganov
parent 8de1e99907
commit fc84ecd445
19 changed files with 103 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.comp
View File

@ -7,7 +7,7 @@ layout (push_constant) uniform parameter
uint ne00; uint ne01; uint ne02; uint ne03; uint nb00; uint nb01; uint nb02; uint nb03;
uint ne10; uint ne11; uint ne12; uint ne13; uint nb10; uint nb11; uint nb12; uint nb13;
uint ne20; uint ne21; uint ne22; uint ne23; uint nb20; uint nb21; uint nb22; uint nb23;
uint d_offset;
uint misalign_offsets;
float param1; float param2; int param3;
} p;
@ -22,6 +22,10 @@ uint get_idx() {
return gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
}
uint get_aoffset() { return p.misalign_offsets >> 16; }
uint get_boffset() { return (p.misalign_offsets >> 8) & 0xFF; }
uint get_doffset() { return p.misalign_offsets & 0xFF; }
// mod and div are expensive and coordinates/dimensions are often power of 2 or equal to 1
uint fastmod(uint a, uint b) {
if ((b & (b-1)) == 0) {