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

24 lines
631 B
Plaintext

#version 450
#include "generic_head.comp"
#include "types.comp"
#extension GL_EXT_control_flow_attributes : enable
layout(local_size_x = 512, 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 float GELU_QUICK_COEF = -1.702f;
const uint i = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
if (i >= p.KX) {
return;
}
const float x = float(data_a[i]);
data_d[i] = D_TYPE(x * (1.0f / (1.0f + exp(GELU_QUICK_COEF * x))));
}