vulkan : incremental shader builds (#16341)

* 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>

ggml/src/ggml-vulkan/CMakeLists.txt

@@ -1,5 +1,6 @@
 cmake_minimum_required(VERSION 3.19)
 cmake_policy(SET CMP0114 NEW)
+cmake_policy(SET CMP0116 NEW)
 
 find_package(Vulkan COMPONENTS glslc REQUIRED)
 
@@ -54,25 +55,25 @@ if (Vulkan_FOUND)
     # Test all shader extensions
     test_shader_extension_support(
         "GL_KHR_cooperative_matrix"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_coopmat_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/coopmat.comp"
         "GGML_VULKAN_COOPMAT_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_NV_cooperative_matrix2"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_coopmat2_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/coopmat2.comp"
         "GGML_VULKAN_COOPMAT2_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_EXT_integer_dot_product"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_integer_dot_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/integer_dot.comp"
         "GGML_VULKAN_INTEGER_DOT_GLSLC_SUPPORT"
     )
 
     test_shader_extension_support(
         "GL_EXT_bfloat16"
-        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/test_bfloat16_support.comp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders/feature-tests/bfloat16.comp"
         "GGML_VULKAN_BFLOAT16_GLSLC_SUPPORT"
     )
 
@@ -160,7 +161,6 @@ if (Vulkan_FOUND)
     set (_ggml_vk_genshaders_dir "${CMAKE_BINARY_DIR}/$<CONFIG>")
     set (_ggml_vk_genshaders_cmd "${_ggml_vk_genshaders_dir}/vulkan-shaders-gen${_ggml_vk_host_suffix}")
     set (_ggml_vk_header     "${CMAKE_CURRENT_BINARY_DIR}/ggml-vulkan-shaders.hpp")
-    set (_ggml_vk_source     "${CMAKE_CURRENT_BINARY_DIR}/ggml-vulkan-shaders.cpp")
     set (_ggml_vk_input_dir  "${CMAKE_CURRENT_SOURCE_DIR}/vulkan-shaders")
     set (_ggml_vk_output_dir "${CMAKE_CURRENT_BINARY_DIR}/vulkan-shaders.spv")
 
@@ -176,24 +176,35 @@ if (Vulkan_FOUND)
 
     add_custom_command(
         OUTPUT ${_ggml_vk_header}
-               ${_ggml_vk_source}
-
         COMMAND ${_ggml_vk_genshaders_cmd}
-            --glslc      ${Vulkan_GLSLC_EXECUTABLE}
-            --input-dir  ${_ggml_vk_input_dir}
             --output-dir ${_ggml_vk_output_dir}
             --target-hpp ${_ggml_vk_header}
-            --target-cpp ${_ggml_vk_source}
-            --no-clean
-
-        DEPENDS ${_ggml_vk_shader_files}
-                ${_ggml_vk_shaders_gen_sources}
+        DEPENDS ${_ggml_vk_shaders_gen_sources}
                 vulkan-shaders-gen
-
-        COMMENT "Generate vulkan shaders"
+        COMMENT "Generate vulkan shaders header"
     )
+    target_sources(ggml-vulkan PRIVATE ${_ggml_vk_header})
 
-    target_sources(ggml-vulkan PRIVATE ${_ggml_vk_source} ${_ggml_vk_header})
+    foreach (file_full ${_ggml_vk_shader_files})
+        get_filename_component(file ${file_full} NAME)
+        set (_ggml_vk_target_cpp "${CMAKE_CURRENT_BINARY_DIR}/${file}.cpp")
+
+        add_custom_command(
+            OUTPUT  ${_ggml_vk_target_cpp}
+            DEPFILE ${_ggml_vk_target_cpp}.d
+            COMMAND ${_ggml_vk_genshaders_cmd}
+                --glslc      ${Vulkan_GLSLC_EXECUTABLE}
+                --source     ${file_full}
+                --output-dir ${_ggml_vk_output_dir}
+                --target-hpp ${_ggml_vk_header}
+                --target-cpp ${_ggml_vk_target_cpp}
+            DEPENDS ${file_full}
+                    ${_ggml_vk_shaders_gen_sources}
+                    vulkan-shaders-gen
+            COMMENT "Generate vulkan shaders for ${file}"
+        )
+        target_sources(ggml-vulkan PRIVATE ${_ggml_vk_target_cpp})
+    endforeach()
 
 else()
     message(WARNING "Vulkan not found")

ggml/src/ggml-vulkan/vulkan-shaders/acc.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/add.comp

@@ -6,8 +6,8 @@
 #extension GL_KHR_shader_subgroup_basic : enable
 #endif
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

ggml/src/ggml-vulkan/vulkan-shaders/add_id.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_control_flow_attributes : require
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/argmax.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/argsort.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(constant_id = 0) const int BLOCK_SIZE = 1024;
 layout(constant_id = 1) const int BLOCK_SIZE_LOG2 = 10;

ggml/src/ggml-vulkan/vulkan-shaders/clamp.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/concat.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/contig_copy.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 #extension GL_EXT_control_flow_attributes : require
 

ggml/src/ggml-vulkan/vulkan-shaders/conv2d_dw.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/conv2d_mm.comp

@@ -11,7 +11,7 @@
 #    extension GL_KHR_shader_subgroup_shuffle : enable
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 // shape notation: [dim(N), ..., dim(0)] -- stride(dim(j)) >= stride(dim(i)) if i > j
 layout(binding = 0) readonly buffer A {

ggml/src/ggml-vulkan/vulkan-shaders/conv_transpose_1d.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (binding = 0) readonly buffer A {A_TYPE data_a[];};   // src0 - kernel:    [K, Cout, Cin]
 layout (binding = 1) readonly buffer B {B_TYPE data_b[];};   // src1 - input:     [L, Cin]

ggml/src/ggml-vulkan/vulkan-shaders/copy.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/copy_from_quant.comp

@@ -1,8 +1,8 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
-#include "dequant_funcs.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
+#include "dequant_funcs.glsl"
 
 #if defined(DATA_A_IQ4_NL) || defined(DATA_A_MXFP4)
 // 16 invocations needed for init_iq_shmem

ggml/src/ggml-vulkan/vulkan-shaders/copy_to_quant.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "rte.comp"
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 #if defined(SET_ROWS) && QUANT_K == 1
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
@@ -14,7 +14,7 @@ const uint BLOCK_SIZE = 32;
 layout (binding = 0) readonly buffer S {float data_s[];};
 
 #if defined(SET_ROWS)
-#include "generic_binary_head.comp"
+#include "generic_binary_head.glsl"
 layout (binding = 1) readonly buffer C {B_TYPE data_i[];};
 layout (binding = 2) writeonly buffer Q {A_TYPE data_q[];};
 
@@ -25,7 +25,7 @@ layout (binding = 2) writeonly buffer Q {A_TYPE data_q[];};
 #endif
 
 #else
-#include "generic_unary_head.comp"
+#include "generic_unary_head.glsl"
 layout (binding = 1) writeonly buffer Q {A_TYPE data_q[];};
 #endif
 

ggml/src/ggml-vulkan/vulkan-shaders/cos.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_unary_head.comp"
+#include "types.glsl"
+#include "generic_unary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/count_equal.comp

@@ -2,8 +2,8 @@
 
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
-#include "generic_head.comp"
+#include "types.glsl"
+#include "generic_head.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_f32.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs.glsl

@@ -2,7 +2,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int8 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #if defined(A_TYPE_PACKED16)
 layout (binding = 0) readonly buffer A_PACKED16 {A_TYPE_PACKED16 data_a_packed16[];};

ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.glsl

@@ -1,5 +1,5 @@
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(buffer_reference, std430, buffer_reference_align = 2) buffer decodeBufQ4_0 {
    block_q4_0_packed16 block;

ggml/src/ggml-vulkan/vulkan-shaders/dequant_head.glsl

@@ -10,4 +10,4 @@ layout (push_constant) uniform parameter
     uint nel;
 } p;
 
-#include "types.comp"
+#include "types.glsl"

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq1_m.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq1_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_xs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq2_xxs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_s.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq3_xxs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq4_nl.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_iq4_xs.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_mxfp4.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q2_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q3_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_1.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q4_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_1.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q5_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q6_k.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/dequant_q8_0.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "dequant_head.comp"
+#include "dequant_head.glsl"
 
 layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/diag_mask_inf.comp

@@ -10,7 +10,7 @@ layout (push_constant) uniform parameter
     uint n_past;
 } p;
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(local_size_x = 1, local_size_y = 512, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/div.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

ggml/src/ggml-vulkan/vulkan-shaders/exp.comp

@@ -1,8 +1,8 @@
 #version 450
 
-#include "rte.comp"
-#include "generic_head.comp"
-#include "types.comp"
+#include "rte.glsl"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp

@@ -8,8 +8,8 @@
 
 #extension GL_KHR_shader_subgroup_shuffle : enable
 
-#include "types.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "flash_attn_base.glsl"
 
 const uint32_t HSK_per_thread = HSK / D_split;
 const uint32_t HSV_per_thread = HSV / D_split;

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp

@@ -10,8 +10,8 @@
 #extension GL_KHR_memory_scope_semantics : enable
 #extension GL_KHR_cooperative_matrix : enable
 
-#include "types.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "flash_attn_base.glsl"
 
 const uint32_t HSK_per_thread = HSK / D_split;
 const uint32_t HSV_per_thread = HSV / D_split;

ggml/src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp

@@ -16,9 +16,9 @@
 #extension GL_KHR_shader_subgroup_vote : enable
 #extension GL_EXT_null_initializer : enable
 
-#include "types.comp"
-#include "dequant_funcs_cm2.comp"
-#include "flash_attn_base.comp"
+#include "types.glsl"
+#include "dequant_funcs_cm2.glsl"
+#include "flash_attn_base.glsl"
 
 layout (binding = 0) readonly buffer Q {uint8_t data_q[];};
 layout (binding = 1) readonly buffer K {uint8_t data_k[];};

ggml/src/ggml-vulkan/vulkan-shaders/geglu.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#include "glu_head.glsl"
 
 const float GELU_COEF_A    = 0.044715f;
 const float SQRT_2_OVER_PI = 0.79788456080286535587989211986876f;
@@ -10,4 +10,4 @@ float op(float a, float b) {
     return 0.5f*a*(2.0f - 2.0f / (exp(2 * val) + 1)) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

ggml/src/ggml-vulkan/vulkan-shaders/geglu_erf.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#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/
@@ -24,4 +24,4 @@ float op(float a, float b) {
     return 0.5f * a * (1.0f + erf_approx) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

ggml/src/ggml-vulkan/vulkan-shaders/geglu_quick.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "glu_head.comp"
+#include "glu_head.glsl"
 
 const float GELU_QUICK_COEF = -1.702f;
 
@@ -8,4 +8,4 @@ float op(float a, float b) {
     return a * (1.0f / (1.0f + exp(GELU_QUICK_COEF * a))) * b;
 }
 
-#include "glu_main.comp"
+#include "glu_main.glsl"

ggml/src/ggml-vulkan/vulkan-shaders/gelu.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/gelu_erf.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/gelu_quick.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.glsl

@@ -1,8 +1,8 @@
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_control_flow_attributes : require
 
-#include "rte.comp"
-#include "utils.comp"
+#include "rte.glsl"
+#include "utils.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/get_rows.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/get_rows_quant.comp

@@ -2,9 +2,9 @@
 
 #extension GL_EXT_control_flow_attributes : enable
 
-#include "types.comp"
-#include "generic_binary_head.comp"
-#include "dequant_funcs.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
+#include "dequant_funcs.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/glu_head.glsl

@@ -1,6 +1,6 @@
 #extension GL_EXT_shader_16bit_storage : require
 
-#include "rte.comp"
+#include "rte.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/group_norm.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 #define BLOCK_SIZE 512

ggml/src/ggml-vulkan/vulkan-shaders/hardsigmoid.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/hardswish.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/im2col.comp

@@ -3,9 +3,8 @@
 #extension GL_EXT_shader_16bit_storage : require
 #extension GL_EXT_control_flow_attributes : require
 
-#include "rte.comp"
-
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/im2col_3d.comp

@@ -4,9 +4,8 @@
 #extension GL_EXT_control_flow_attributes : require
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "rte.comp"
-
-#include "types.comp"
+#include "rte.glsl"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/l2_norm.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 #define BLOCK_SIZE 512

ggml/src/ggml-vulkan/vulkan-shaders/leaky_relu.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/mul.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "types.comp"
-#include "generic_binary_head.comp"
+#include "types.glsl"
+#include "generic_binary_head.glsl"
 
 const uint num_threads = 256;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.glsl

@@ -11,7 +11,7 @@
 #define EXPERT_COUNT 8
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #ifndef MMQ
 layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
@@ -32,7 +32,7 @@ layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
 layout (binding = 3) readonly buffer IDS {int data_ids[];};
 #endif
 
-#include "dequant_funcs.comp"
+#include "dequant_funcs.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq1_m.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq1_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_xs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq2_xxs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq3_s.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_iq3_xxs.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q2_k.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q3_k.comp

@@ -1,7 +1,7 @@
 #version 450
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q4_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q5_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q6_k.comp

@@ -2,7 +2,7 @@
 
 #extension GL_EXT_shader_explicit_arithmetic_types_int32 : require
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vecq.comp

@@ -6,13 +6,13 @@
 #define MMQ
 #define B_TYPE block_q8_1_x4
 
-#include "mul_mat_vec_base.comp"
+#include "mul_mat_vec_base.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
 #define K_PER_ITER 8
 
-#include "mul_mmq_funcs.comp"
+#include "mul_mmq_funcs.glsl"
 
 uint a_offset, b_offset, d_offset;
 

ggml/src/ggml-vulkan/vulkan-shaders/mul_mm.comp

@@ -28,7 +28,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 #ifndef LOAD_VEC_A
 #define LOAD_VEC_A 1
@@ -195,7 +195,7 @@ void load_row_ids(uint expert_idx, bool nei0_is_pow2, uint ic) {
 shared ACC_TYPE coopmat_stage[TM * TN * NUM_WARPS];
 #endif
 
-#include "mul_mm_funcs.comp"
+#include "mul_mm_funcs.glsl"
 
 void main() {
 #ifdef NEEDS_INIT_IQ_SHMEM

ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_cm2.comp

@@ -18,8 +18,8 @@
 #extension GL_EXT_bfloat16 : enable
 #endif
 
-#include "types.comp"
-#include "utils.comp"
+#include "types.glsl"
+#include "utils.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
@@ -71,7 +71,7 @@ layout (binding = 2) writeonly buffer D {D_TYPE data_d[];};
 #if QUANT_K > 1
 #define DECODEFUNCA , dequantFuncA
 
-#include "dequant_funcs_cm2.comp"
+#include "dequant_funcs_cm2.glsl"
 
 #else
 #define DECODEFUNCA

ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq.comp

@@ -20,7 +20,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 #endif
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
 
@@ -110,7 +110,7 @@ shared u16vec2 row_ids[4096];
 shared ACC_TYPE coopmat_stage[TM * TN * NUM_WARPS];
 #endif
 
-#include "mul_mmq_funcs.comp"
+#include "mul_mmq_funcs.glsl"
 
 void main() {
 #ifdef NEEDS_INIT_IQ_SHMEM

ggml/src/ggml-vulkan/vulkan-shaders/mul_mmq_funcs.glsl

@@ -2,7 +2,7 @@
 #extension GL_EXT_shader_explicit_arithmetic_types_int16 : require
 #extension GL_EXT_shader_explicit_arithmetic_types_int8 : require
 
-#include "types.comp"
+#include "types.glsl"
 
 // Each iqs value maps to a 32-bit integer
 

ggml/src/ggml-vulkan/vulkan-shaders/multi_add.comp

@@ -8,9 +8,9 @@
 #extension GL_KHR_shader_subgroup_basic : enable
 #endif
 
-#include "rte.comp"
-#include "types.comp"
-#include "utils.comp"
+#include "rte.glsl"
+#include "types.glsl"
+#include "utils.glsl"
 
 layout (push_constant) uniform parameter2
 {

ggml/src/ggml-vulkan/vulkan-shaders/norm.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 #define BLOCK_SIZE 512

ggml/src/ggml-vulkan/vulkan-shaders/opt_step_adamw.comp

@@ -1,7 +1,7 @@
 #version 450
 
-#include "generic_head.comp"
-#include "types.comp"
+#include "generic_head.glsl"
+#include "types.glsl"
 
 #extension GL_EXT_control_flow_attributes : enable
 

ggml/src/ggml-vulkan/vulkan-shaders/opt_step_sgd.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "generic_head.comp"
+#include "generic_head.glsl"
 
 layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
 

ggml/src/ggml-vulkan/vulkan-shaders/pad.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 layout (push_constant) uniform parameter
 {

ggml/src/ggml-vulkan/vulkan-shaders/pool2d.comp

@@ -1,6 +1,6 @@
 #version 450
 
-#include "types.comp"
+#include "types.glsl"
 
 #extension GL_EXT_shader_16bit_storage : require
 

ggml/src/ggml-vulkan/vulkan-shaders/quantize_q8_1.comp

@@ -17,7 +17,7 @@ layout (push_constant) uniform parameter
     uint ne;
 } p;
 
-#include "types.comp"
+#include "types.glsl"
 
 layout(constant_id = 0) const uint GROUP_SIZE = 32;
 layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;