Skip to content

[ET-VK][qconv] Read weight buffer as int in pack_q8_conv2d_weights shader #17690

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

Closed
SS-JIA wants to merge 1 commit into from
Closed

[ET-VK][qconv] Read weight buffer as int in pack_q8_conv2d_weights shader #17690

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions backends/vulkan/runtime/graph/ops/glsl/pack_q8_conv2d_weights.glsl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,6 @@

#version 450 core

${define_required_extensions("buffer", "int8")}

#define PRECISION ${PRECISION}

${define_active_storage_type(STORAGE)}
Expand All @@ -19,7 +17,7 @@ ${define_active_storage_type(STORAGE)}
layout(std430) buffer;

${layout_declare_tensor(B, "w", "t_packed_int8_weight", "int", STORAGE, is_scalar_array=False)}
${layout_declare_tensor(B, "r", "t_int8_weight", "int8", "buffer")}
${layout_declare_tensor(B, "r", "t_int8_weight", "int", "buffer")}

layout(push_constant) uniform restrict Block {
ivec4 qmat2_sizes;
Expand Down Expand Up @@ -65,7 +63,9 @@ void main() {
ivec4 weight_vals = ivec4(0);
for (int col = 0; col < 4; col++) {
if (ic + col < orig_sizes.w) {
weight_vals[col] = int(t_int8_weight[buf_idx + col]);
const int byte_idx = buf_idx + col;
const int byte_pos = byte_idx & 3;
weight_vals[col] = (t_int8_weight[byte_idx >> 2] >> (byte_pos * 8)) & 0xFF;
}
}
packed_block[row] = pack_into_int32(weight_vals);
Expand Down
Loading