EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

ggml : fix interpolate with align-corners and ne=1 (#16700)

Browse Source 
* ggml : fix interpolate with align-corners and ne=1

* avoid division by zero if one of the spatial dimensions is 1
* cpu, cuda, opencl returned correct result anyway due to clamp
* vulkan didn't clamp for align-corners so results were broken

* fix clang warning
This commit is contained in:
Acly
2025-10-27 21:50:22 +01:00
committed by GitHub
parent 80d28f104c
commit 10640e31aa
6 changed files with 29 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
ggml/src/ggml-vulkan/vulkan-shaders/upscale.comp
View File

@@ -7,6 +7,7 @@ layout (push_constant) uniform parameter
uint nb00; uint nb01; uint nb02; uint nb03;
uint ne10; uint ne11; uint ne12; uint ne13;
float sf0; float sf1; float sf2; float sf3;
float pixel_offset;
} p;
#include "types.glsl"
@@ -19,7 +20,6 @@ layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
// from ggml.h: enum ggml_scale_mode, enum ggml_scale_flag
#define NEAREST 0
#define BILINEAR 1
#define ALIGN_CORNERS (1 << 8)
layout (constant_id = 0) const uint scale_mode = 0;
@@ -52,7 +52,7 @@ float fetch_bilinear(ivec2 c0, ivec2 c1, vec2 d, uint i12, uint i13) {
float interpolate_bilinear(uint i10, uint i11, uint i12, uint i13) {
const ivec2 ne0 = ivec2(p.ne00, p.ne01);
const vec2 c = (vec2(i10, i11) + 0.5) / vec2(p.sf0, p.sf1) - 0.5;
const vec2 c = (vec2(i10, i11) + p.pixel_offset) / vec2(p.sf0, p.sf1) - p.pixel_offset;
const vec2 c0f = floor(c);
const vec2 d = c - c0f;
const ivec2 c0 = max(ivec2(c0f), 0);
@@ -61,16 +61,6 @@ float interpolate_bilinear(uint i10, uint i11, uint i12, uint i13) {
return fetch_bilinear(c0, c1, d, i12, i13);
}
float interpolate_bilinear_align_corners(uint i10, uint i11, uint i12, uint i13) {
const vec2 c = vec2(i10, i11) / vec2(p.sf0, p.sf1);
const vec2 c0f = floor(c);
const vec2 d = c - c0f;
const ivec2 c0 = ivec2(c0f);
const ivec2 c1 = c0 + 1;
return fetch_bilinear(c0, c1, d, i12, i13);
}
void main() {
const uint idx = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
@@ -91,9 +81,6 @@ void main() {
case BILINEAR:
result = interpolate_bilinear(i10, i11, i12, i13);
break;
case BILINEAR | ALIGN_CORNERS:
result = interpolate_bilinear_align_corners(i10, i11, i12, i13);
break;
}
data_d[p.d_offset + idx] = D_TYPE(result);