llama.cpp/ggml/src/vulkan-shaders/timestep_embedding.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

42 lines
1.0 KiB
Plaintext

#version 450
#extension GL_EXT_shader_16bit_storage : require
layout (push_constant) uniform parameter
{
uint nb1;
uint dim;
uint max_period;
} p;
#include "types.comp"
#extension GL_EXT_control_flow_attributes : enable
#define BLOCK_SIZE 256
layout(local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in;
layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
void main() {
const uint i = gl_WorkGroupID.y;
const uint j = gl_GlobalInvocationID.x;
const uint d_offset = i * p.nb1;
if (p.dim % 2 != 0 && j == ((p.dim + 1) / 2)) {
data_d[d_offset + p.dim] = 0.f;
}
const uint half_dim = p.dim / 2;
if (j >= half_dim) {
return;
}
const float timestep = float(data_a[i]);
const float freq = float(exp(-log(p.max_period) * j / half_dim));
const float arg = timestep * freq;
data_d[d_offset + j] = D_TYPE(cos(arg));
data_d[d_offset + j + half_dim] = D_TYPE(sin(arg));
}