Skip to content

vulkan: Increase workgroup size for GLU, for performance #14345

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 2 commits into from
Jun 28, 2025
Merged

vulkan: Increase workgroup size for GLU, for performance #14345

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2d67196
vulkan: Increase workgroup size for GLU, for performance
jeffbolznv Jun 23, 2025
398bcba
vulkan: change GLU shaders to do one element per invocation rather th…
jeffbolznv Jun 23, 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
4 changes: 2 additions & 2 deletions ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2761,8 +2761,8 @@ static void ggml_vk_load_shaders(vk_device& device) {
#undef CREATE_UNARY

#define CREATE_GLU(name) \
ggml_vk_create_pipeline(device, device->pipeline_ ## name [0], #name "_f32", name ## _f32_len, name ## _f32_data, "main", 3, sizeof(vk_op_glu_push_constants), {1, 1, 1}, { device->subgroup_size }, 1); \
ggml_vk_create_pipeline(device, device->pipeline_ ## name [1], #name "_f16", name ## _f16_len, name ## _f16_data, "main", 3, sizeof(vk_op_glu_push_constants), {1, 1, 1}, { device->subgroup_size }, 1);
ggml_vk_create_pipeline(device, device->pipeline_ ## name [0], #name "_f32", name ## _f32_len, name ## _f32_data, "main", 3, sizeof(vk_op_glu_push_constants), {1, 1, 1}, {}, 1); \
ggml_vk_create_pipeline(device, device->pipeline_ ## name [1], #name "_f16", name ## _f16_len, name ## _f16_data, "main", 3, sizeof(vk_op_glu_push_constants), {1, 1, 1}, {}, 1);

CREATE_GLU(geglu)
CREATE_GLU(reglu)
Expand Down
4 changes: 2 additions & 2 deletions ggml/src/ggml-vulkan/vulkan-shaders/glu_head.comp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
#extension GL_EXT_shader_16bit_storage : require

layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;

layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
layout (binding = 1) readonly buffer B {A_TYPE data_b[];};
layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};

layout (constant_id = 0) const uint BLOCK_SIZE = 32;
const uint BLOCK_SIZE = 512;

layout (push_constant) uniform parameter
{
Expand Down
Loading