metal : refactor pad parameters into a struct

Author: alexju

ggml/src/ggml-metal/ggml-metal-impl.h

@@ -445,4 +445,23 @@ typedef struct {
     float    sf3;
 } ggml_metal_kargs_upscale;
 
+typedef struct {
+    int64_t  ne00;
+    int64_t  ne01;
+    int64_t  ne02;
+    int64_t  ne03;
+    uint64_t nb00;
+    uint64_t nb01;
+    uint64_t nb02;
+    uint64_t nb03;
+    int64_t  ne0;
+    int64_t  ne1;
+    int64_t  ne2;
+    int64_t  ne3;
+    uint64_t nb0;
+    uint64_t nb1;
+    uint64_t nb2;
+    uint64_t nb3;
+} ggml_metal_kargs_pad;
+
 #endif // GGML_METAL_IMPL

ggml/src/ggml-metal/ggml-metal.m

@@ -3449,26 +3449,29 @@ static void ggml_metal_encode_node(
 
                 id<MTLComputePipelineState> pipeline = ctx->kernels[GGML_METAL_KERNEL_TYPE_PAD_F32].pipeline;
 
-                // TODO: add ggml_metal_kargs struct
+                ggml_metal_kargs_pad args = {
+                    /*.ne00 =*/ ne00,
+                    /*.ne01 =*/ ne01,
+                    /*.ne02 =*/ ne02,
+                    /*.ne03 =*/ ne03,
+                    /*.nb00 =*/ nb00,
+                    /*.nb01 =*/ nb01,
+                    /*.nb02 =*/ nb02,
+                    /*.nb03 =*/ nb03,
+                    /*.ne0 =*/ ne0,
+                    /*.ne1 =*/ ne1,
+                    /*.ne2 =*/ ne2,
+                    /*.ne3 =*/ ne3,
+                    /*.nb0 =*/ nb0,
+                    /*.nb1 =*/ nb1,
+                    /*.nb2 =*/ nb2,
+                    /*.nb3 =*/ nb3
+                };
+                
                 [encoder setComputePipelineState:pipeline];
                 [encoder setBuffer:id_src0 offset:offs_src0 atIndex:0];
                 [encoder setBuffer:id_dst  offset:offs_dst  atIndex:1];
-                [encoder setBytes:&ne00 length:sizeof(ne00) atIndex:2];
-                [encoder setBytes:&ne01 length:sizeof(ne01) atIndex:3];
-                [encoder setBytes:&ne02 length:sizeof(ne02) atIndex:4];
-                [encoder setBytes:&ne03 length:sizeof(ne03) atIndex:5];
-                [encoder setBytes:&nb00 length:sizeof(nb00) atIndex:6];
-                [encoder setBytes:&nb01 length:sizeof(nb01) atIndex:7];
-                [encoder setBytes:&nb02 length:sizeof(nb02) atIndex:8];
-                [encoder setBytes:&nb03 length:sizeof(nb03) atIndex:9];
-                [encoder setBytes:&ne0  length:sizeof(ne0)  atIndex:10];
-                [encoder setBytes:&ne1  length:sizeof(ne1)  atIndex:11];
-                [encoder setBytes:&ne2  length:sizeof(ne2)  atIndex:12];
-                [encoder setBytes:&ne3  length:sizeof(ne3)  atIndex:13];
-                [encoder setBytes:&nb0  length:sizeof(nb0)  atIndex:14];
-                [encoder setBytes:&nb1  length:sizeof(nb1)  atIndex:15];
-                [encoder setBytes:&nb2  length:sizeof(nb2)  atIndex:16];
-                [encoder setBytes:&nb3  length:sizeof(nb3)  atIndex:17];
+                [encoder setBytes:&args length:sizeof(args) atIndex:2];
 
                 const int nth = MIN(1024, ne0);
 

ggml/src/ggml-metal/ggml-metal.metal

@@ -2687,22 +2687,7 @@ kernel void kernel_upscale_f32(
 kernel void kernel_pad_f32(
     device  const char * src0,
     device        char * dst,
-    constant   int64_t & ne00,
-    constant   int64_t & ne01,
-    constant   int64_t & ne02,
-    constant   int64_t & ne03,
-    constant  uint64_t & nb00,
-    constant  uint64_t & nb01,
-    constant  uint64_t & nb02,
-    constant  uint64_t & nb03,
-    constant   int64_t & ne0,
-    constant   int64_t & ne1,
-    constant   int64_t & ne2,
-    constant   int64_t & ne3,
-    constant  uint64_t & nb0,
-    constant  uint64_t & nb1,
-    constant  uint64_t & nb2,
-    constant  uint64_t & nb3,
+    constant ggml_metal_kargs_pad & args,
     uint3 tgpig[[threadgroup_position_in_grid]],
     uint3 tpitg[[thread_position_in_threadgroup]],
     uint3   ntg[[threads_per_threadgroup]]) {
@@ -2715,12 +2700,12 @@ kernel void kernel_pad_f32(
     const int64_t i02 = i2;
     const int64_t i01 = i1;
 
-    device const float * src0_ptr = (device const float *) (src0 + i03*nb03 + i02*nb02 + i01*nb01);
-    device       float * dst_ptr  = (device       float *) (dst  +  i3*nb3  +  i2*nb2  +  i1*nb1);
+    device const float * src0_ptr = (device const float *) (src0 + i03*args.nb03 + i02*args.nb02 + i01*args.nb01);
+    device       float * dst_ptr  = (device       float *) (dst  +  i3*args.nb3  +  i2*args.nb2  +  i1*args.nb1);
 
-    if (i1 < ne01 && i2 < ne02 && i3 < ne03) {
-        for (int i0 = tpitg.x; i0 < ne0; i0 += ntg.x) {
-            if (i0 < ne00) {
+    if (i1 < args.ne01 && i2 < args.ne02 && i3 < args.ne03) {
+        for (int i0 = tpitg.x; i0 < args.ne0; i0 += ntg.x) {
+            if (i0 < args.ne00) {
                 dst_ptr[i0] = src0_ptr[i0];
             } else {
                 dst_ptr[i0] = 0.0f;
@@ -2730,7 +2715,7 @@ kernel void kernel_pad_f32(
         return;
     }
 
-    for (int i0 = tpitg.x; i0 < ne0; i0 += ntg.x) {
+    for (int i0 = tpitg.x; i0 < args.ne0; i0 += ntg.x) {
         dst_ptr[i0] = 0.0f;
     }
 }