vec2 unpack for q8

Author: netrunnereve

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

@@ -82,9 +82,9 @@ vec2 dequantize(uint ib, uint iqs, uint a_offset) {
     return vec2(int(data_a[a_offset + ib].qs[iqs]), int(data_a[a_offset + ib].qs[iqs + 1]));
 }
 vec4 dequantize4(uint ib, uint iqs, uint a_offset) {
-    uint32_t v0 = data_a_packed16[a_offset + ib].qs[iqs/2];
-    uint32_t v1 = data_a_packed16[a_offset + ib].qs[iqs/2 + 1];
-    return vec4(int8_t(v0 & 0xFF), int8_t(v0 >> 8), int8_t(v1 & 0xFF), int8_t(v1 >> 8));
+    const i8vec2 v0 = unpack8(data_a_packed16[a_offset + ib].qs[iqs/2]);
+    const i8vec2 v1 = unpack8(data_a_packed16[a_offset + ib].qs[iqs/2 + 1]);
+    return vec4(v0.x, v0.y, v1.x, v1.y);
 }
 #endif
 

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

@@ -92,7 +92,7 @@ float16_t dequantFuncQ8_0(const in decodeBufQ8_0 bl, const in uint blockCoords[2
     const uint iqs = idx;
 
     // Load 16b and select the byte for this element
-    int32_t qs = unpack8(int32_t(bl.block.qs[(iqs & 0x1E) >> 1]))[iqs & 1];
+    int32_t qs = unpack8(bl.block.qs[(iqs & 0x1E) >> 1])[iqs & 1];
     float16_t ret = float16_t(qs) * d;
     return ret;
 }

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

@@ -336,9 +336,9 @@ void main() {
             const uint iqs = idx & 0x07;
 
             const float d = float(data_a_packed16[ib].d);
-            const uint v0 = uint(data_a_packed16[ib].qs[2*iqs]);
-            const uint v1 = uint(data_a_packed16[ib].qs[2*iqs + 1]);
-            const vec4 v = vec4(int8_t(v0 & 0xFF), int8_t(v0 >> 8), int8_t(v1 & 0xFF), int8_t(v1 >> 8)) * d;
+            const i8vec2 v0 = unpack8(data_a_packed16[ib].qs[2*iqs]);
+            const i8vec2 v1 = unpack8(data_a_packed16[ib].qs[2*iqs + 1]);
+            const vec4 v = vec4(v0.x, v0.y, v1.x, v1.y) * d;
 
             buf_a[buf_idx    ] = FLOAT_TYPE(v.x);
             buf_a[buf_idx + 1] = FLOAT_TYPE(v.y);

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

@@ -139,7 +139,7 @@ struct block_q8_0
 struct block_q8_0_packed16
 {
     float16_t d;
-    uint16_t qs[32/2];
+    int16_t qs[32/2];
 };
 
 #if defined(DATA_A_Q8_0)