llama.cpp/ggml/src/vulkan-shaders/repeat.comp
0cc4m 5fd89a70ea
Vulkan Optimizations and Fixes (#8959)
* Optimize Vulkan REPEAT performance

* Use Vulkan GLSL fused multiply-add instruction where possible

* Add GGML_VULKAN_PERF option to output performance data per operator

* Rework and fix Vulkan descriptor set and descriptor pool handling

* Fix float32 concat f16 shader validation error

* Add Vulkan GROUP_NORM eps parameter

* Fix validation error with transfer queue memory barrier flags

* Remove trailing whitespaces
2024-08-14 18:32:53 +02:00

25 lines
722 B
Plaintext

#version 450
#include "types.comp"
#include "generic_unary_head.comp"
uint src0_idx_mod(uint idx) {
const uint i13 = idx / (p.ne12*p.ne11*p.ne10);
const uint i13_offset = i13 * p.ne12*p.ne11*p.ne10;
const uint i12 = (idx - i13_offset) / (p.ne11*p.ne10);
const uint i12_offset = i12*p.ne11*p.ne10;
const uint i11 = (idx - i13_offset - i12_offset) / p.ne10;
const uint i10 = idx - i13_offset - i12_offset - i11*p.ne10;
return (i13 % p.ne03)*p.nb03 + (i12 % p.ne02)*p.nb02 + (i11 % p.ne01)*p.nb01 + (i10 % p.ne00)*p.nb00;
}
void main() {
const uint idx = get_idx();
if (idx >= p.ne) {
return;
}
data_d[p.d_offset + dst_idx(idx)] = D_TYPE(data_a[src0_idx_mod(idx)]);
}