ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-05-09 20:13:14 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

vulkan: improve im2col (llama/11826)

Browse Source 
* vulkan: improve im2col performance
This commit is contained in:
Daniele 2025-02-28 06:52:51 +00:00 committed by Georgi Gerganov
parent 8255a830a8
commit 40dea850fd
1 changed files with 33 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
ggml/src/ggml-vulkan/vulkan-shaders/im2col.comp
View File

@ -40,6 +40,20 @@ void main() {
const uint batch = gl_GlobalInvocationID.z / p.IC;
const uint ic = gl_GlobalInvocationID.z % p.IC;
const uint src_base = ic * p.offset_delta + batch * p.batch_offset;
const uint dst_base = ((batch * p.OH + oh) * p.OW) * p.CHW + ic * (p.KW * p.KH);
const int oh_s1 = int(oh) * p.s1;
const uint ksize = p.OW * (p.KH > 1 ? p.KW : 1);
const uint base_linear_idx = gidx * NUM_ITER;
const uint max_ky = ksize / p.OW;
uint current_kx = base_linear_idx / ksize;
const uint rem = base_linear_idx - (current_kx * ksize);
uint current_ky = rem / p.OW;
uint current_ix = rem % p.OW;
A_TYPE values[NUM_ITER];
uint offset_dst[NUM_ITER];
[[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {
@ -48,36 +62,35 @@ void main() {
[[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {
const uint i = gidx * NUM_ITER + idx;
const uint linear_idx = base_linear_idx + idx;
const uint ksize = p.OW * (p.KH > 1 ? p.KW : 1);
const uint kx = i / ksize;
const uint kd = kx * ksize;
const uint ky = (i - kd) / p.OW;
const uint ix = i % p.OW;
const uint iiw = ix * p.s0 + kx * p.d0 - p.p0;
const uint iih = oh * p.s1 + ky * p.d1 - p.p1;
offset_dst[idx] =
((batch * p.OH + oh) * p.OW + ix) * p.CHW +
(ic * (p.KW * p.KH) + ky * p.KW + kx);
if (i >= p.pelements) {
if (linear_idx >= p.pelements) {
continue;
}
if (iih < p.IH && iiw < p.IW) {
const uint offset_src = ic * p.offset_delta + batch * p.batch_offset;
values[idx] = data_a[offset_src + iih * p.IW + iiw];
const uint iiw = current_ix * p.s0 + current_kx * p.d0 - p.p0;
const uint iih = oh_s1 + current_ky * p.d1 - p.p1;
offset_dst[idx] = dst_base + current_ix * p.CHW + current_ky * p.KW + current_kx;
if ((iih < p.IH) && (iiw < p.IW)) {
values[idx] = data_a[src_base + iih * p.IW + iiw];
}
if (++current_ix == p.OW) {
current_ix = 0;
if (++current_ky == max_ky) {
current_ky = 0;
current_kx++;
}
}
}
[[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {
const uint i = gidx * NUM_ITER + idx;
const uint linear_idx = base_linear_idx + idx;
if (i >= p.pelements) {
if (linear_idx >= p.pelements) {
continue;
}