summaryrefslogtreecommitdiff
path: root/vulkan-shaders/get_rows.comp
diff options
context:
space:
mode:
author0cc4m <picard12@live.de>2024-06-16 07:17:31 +0200
committerGitHub <noreply@github.com>2024-06-16 07:17:31 +0200
commit7c7836d9d4062d6858e3fb337b135c417ccee6ce (patch)
treec896967a106e2985763bf1c7bfd7bfb8cbe4f0fd /vulkan-shaders/get_rows.comp
parent0c7b3595b9e5ad2355818e259f06b0dc3f0065b3 (diff)
Vulkan Shader Refactor, Memory Debugging Option (#7947)
* Refactor shaders, extract GLSL code from ggml_vk_generate_shaders.py into vulkan-shaders directory * Improve debug log code * Add memory debug output option * Fix flake8 * Fix unnecessary high llama-3 VRAM use
Diffstat (limited to 'vulkan-shaders/get_rows.comp')
-rw-r--r--vulkan-shaders/get_rows.comp26
1 files changed, 26 insertions, 0 deletions
diff --git a/vulkan-shaders/get_rows.comp b/vulkan-shaders/get_rows.comp
new file mode 100644
index 00000000..e9ff22ef
--- /dev/null
+++ b/vulkan-shaders/get_rows.comp
@@ -0,0 +1,26 @@
+#version 450
+
+#include "types.comp"
+#include "generic_binary_head.comp"
+
+void main() {
+ const uint i00 = gl_GlobalInvocationID.x;
+ const uint i10 = gl_GlobalInvocationID.y;
+ const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
+ const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
+
+ if (i00 >= p.ne00) {
+ return;
+ }
+
+ const uint i01 = data_b[i10*p.nb10 + i11*p.nb11 + i12*p.nb12];
+
+ const uint a_offset = i01*p.nb01 + i11*p.nb02 + i12*p.nb03;
+ const uint d_offset = i10*p.nb21 + i11*p.nb22 + i12*p.nb23;
+
+#ifndef OPTIMIZATION_ERROR_WORKAROUND
+ data_d[d_offset + i00] = D_TYPE(data_a[a_offset + i00]);
+#else
+ data_d[d_offset + i00] = data_a[a_offset + i00];
+#endif
+}