Skip to content

[ET-VK][ez] Fix 8 bit linear compute shader dispatch #9531

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Mar 26, 2025
Merged

[ET-VK][ez] Fix 8 bit linear compute shader dispatch #9531

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
44aace8
[ET-VK][ez] Fix 8 bit linear compute shader dispatch
SS-JIA Mar 23, 2025
a6fc34a
Update on "[ET-VK][ez] Fix 8 bit linear compute shader dispatch"
SS-JIA Mar 26, 2025
a3a3d85
Update on "[ET-VK][ez] Fix 8 bit linear compute shader dispatch"
SS-JIA Mar 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions backends/vulkan/runtime/graph/ops/glsl/q_8w_linear.glsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,9 +90,10 @@ void main() {

void main() {
const u16vec2 out_pos = u16vec2(
gl_GlobalInvocationID.x / out_limits.y,
gl_GlobalInvocationID.x % out_limits.y);
if (out_pos.x >= out_limits.x) {
gl_GlobalInvocationID.x,
gl_GlobalInvocationID.y);

if (out_pos.x >= out_limits.x || out_pos.y >= out_limits.y) {
return;
}

Expand Down
32 changes: 27 additions & 5 deletions backends/vulkan/runtime/graph/ops/impl/QuantizedLinear.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,15 +114,37 @@ void add_q_8w_linear_node(
graph.sizes_ubo(mat1_W_packed)});
}

// set global work group size to be 1 dimensional
const utils::uvec3 wg_size = {
static_cast<uint32_t>(graph.numel_of(out_W_packed)), 1, 1};
utils::uvec3 global_wg;
if (graph.is_buffer_storage(out)) {
global_wg = {static_cast<uint32_t>(graph.numel_of(out_W_packed)), 1, 1};
} else {
global_wg = graph.logical_limits_of(out_W_packed);
}

utils::uvec3 local_wg{8, 8, 1};
int32_t out_W = graph.size_at<int32_t>(-1, out_W_packed);

if (graph.is_buffer_storage(out_W_packed)) {
local_wg[0] = 64;
local_wg[1] = 1;
local_wg[2] = 1;
} else {
if (out_W % 8 != 0) {
if (out_W % 4 == 0) {
local_wg[0] = 4;
local_wg[1] = 16;
} else {
local_wg[0] = 2;
local_wg[1] = 32;
}
}
}

graph.execute_nodes().emplace_back(new DispatchNode(
graph,
VK_KERNEL_FROM_STR(kernel_name),
wg_size,
graph.create_local_wg_size(wg_size),
global_wg,
local_wg,
// Inputs and Outputs
{{out_W_packed, vkapi::MemoryAccessType::WRITE},
{{mat1_W_packed, q_mat2, scales}, vkapi::MemoryAccessType::READ}},
Expand Down
Loading