llama.cpp/ggml/src/vulkan-shaders/sum_rows.comp
0cc4m a3738b2fa7 vulkan : implement Stable Diffusion operators (ggml/904)
* Fix Vulkan repeat op

* Implement Vulkan concat op

* Delete old Vulkan shader generator

* Implement Vulkan im2col op

* Implement Vulkan unary gelu_quick op

* Implement Vulkan group_norm op

* Implement Vulkan timestep_embedding op

* Implement Vulkan upscale op

* Fix Vulkan vk_context tensor extra index issue

* Fix Vulkan matmul shader parameter bug

* Properly fix Vulkan matmul shader parameter bug

* Add Vulkan ADD f16 + f32 -> f16 operator support

* Implement Vulkan tanh op

* Fix Vulkan group count too large Validation error on non-Nvidia GPUs

* Throw error when too much memory is requested

* Fix another Vulkan group count too large Validation error on non-Nvidia GPUs

* Fix matmul MMQ condition

* Implement Vulkan pad op

* Fix Vulkan crash when tensor is used multiple times in a compute graph

* Add Vulkan CONCAT f16 + f16 -> f16 op

* Add Vulkan LEAKY_RELU op
2024-08-05 08:50:57 +03:00

38 lines
940 B
Plaintext

#version 450
#include "generic_head.comp"
#include "types.comp"
#extension GL_EXT_control_flow_attributes : enable
layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
layout (constant_id = 0) const uint BLOCK_SIZE = 32;
shared FLOAT_TYPE tmp[BLOCK_SIZE];
void main() {
const uint row = gl_WorkGroupID.z * 262144 + gl_WorkGroupID.y * 512 + gl_WorkGroupID.x;
const uint col = gl_LocalInvocationID.x;
tmp[col] = FLOAT_TYPE(0.0f);
for (uint i = col; i < p.KX; i += BLOCK_SIZE) {
tmp[col] += FLOAT_TYPE(data_a[row*p.KX + i]);
}
barrier();
[[unroll]] for (int s = int(BLOCK_SIZE) / 2; s > 0; s >>= 1) {
if (col < s) {
tmp[col] += tmp[col + s];
}
barrier();
}
if (col == 0) {
data_d[row] = D_TYPE(tmp[0]);
}
}