Acly
e29acf74fe
* vulkan (DRAFT): split shader generation by GLSL source file, to improve incremental build times * support dep-files so shaders are recompiled if their included files change * rename shader files which are used as "headers" to use .glsl extension * move glslc extension detection shaders to separate folders * the above is to prevent them from getting glob'd with the actual compute shaders that need to be compiled * vulkan : only write embedded shader .hpp/.cpp when they change * avoid recompiling ggml-vulkan.cpp when editing shaders * pass single --source argument instead of --input-dir & --filter to shader gen * check for source file match earlier * fix hang in vulkan-shaders-gen when there are compilation errors * early out did not decrement compile_count * clean up * fix glslc integer dot product test * unconditionally write the embedded shader cpp output * replace output filepath in generated dep-files to match output in CMakeLists --------- Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
28 lines
882 B
Plaintext
28 lines
882 B
Plaintext
#version 450
|
|
|
|
#include "glu_head.glsl"
|
|
|
|
// based on Abramowitz and Stegun formula 7.1.26 or similar Hastings' approximation
|
|
// ref: https://www.johndcook.com/blog/python_erf/
|
|
const float p_erf = 0.3275911f;
|
|
const float a1_erf = 0.254829592f;
|
|
const float a2_erf = -0.284496736f;
|
|
const float a3_erf = 1.421413741f;
|
|
const float a4_erf = -1.453152027f;
|
|
const float a5_erf = 1.061405429f;
|
|
|
|
const float SQRT_2_INV = 0.70710678118654752440084436210484f;
|
|
|
|
float op(float a, float b) {
|
|
const float a_div_sqr2 = a * SQRT_2_INV;
|
|
const float sign_x = sign(a_div_sqr2);
|
|
const float x = abs(a_div_sqr2);
|
|
const float t = 1.0f / (1.0f + p_erf * x);
|
|
const float y = 1.0f - (((((a5_erf * t + a4_erf) * t) + a3_erf) * t + a2_erf) * t + a1_erf) * t * exp(-x * x);
|
|
const float erf_approx = sign_x * y;
|
|
|
|
return 0.5f * a * (1.0f + erf_approx) * b;
|
|
}
|
|
|
|
#include "glu_main.glsl"
|