ggml : generalize GGML_OP_CONCAT (#7563)

* ggml : generalize GGML_OP_CONCAT (WIP)

ggml-ci

* tests : add dim != 2 tests

* metal : generalize concat kernel

* tests : naming

* cuda : generalize concat kernel

ggml-ci

* sycl : add warning and assert

* ggml : fix op params handling

* metal : bugfix kernel

ggml-ci

* ggml : reimplement CPU and Metal

* cuda : add asserts

ggml-ci

* ggml : fix ptrs

ggml-ci

1 files changed, 14 insertions, 15 deletions

diff --git a/ggml-metal.metal b/ggml-metal.metal
index 174086b5..b16f2b7e 100644
--- a/ggml-metal.metal
+++ b/ggml-metal.metal
@@ -3366,31 +3366,30 @@ kernel void kernel_concat(
     constant  uint64_t & nb1,
     constant  uint64_t & nb2,
     constant  uint64_t & nb3,
+    constant   int32_t & dim,
     uint3 tgpig[[threadgroup_position_in_grid]],
     uint3 tpitg[[thread_position_in_threadgroup]],
     uint3   ntg[[threads_per_threadgroup]]) {
 
-    const int64_t i03 = tgpig.z;
-    const int64_t i02 = tgpig.y;
-    const int64_t i01 = tgpig.x;
+    const int64_t i3 = tgpig.z;
+    const int64_t i2 = tgpig.y;
+    const int64_t i1 = tgpig.x;
 
-    const int64_t i13 = i03 % ne13;
-    const int64_t i12 = i02 % ne12;
-    const int64_t i11 = i01 % ne11;
+    int64_t o[4] = {0, 0, 0, 0};
+    o[dim] = dim == 0 ? ne00 : (dim == 1 ? ne01 : (dim == 2 ? ne02 : ne03));
 
-    device const char * src0_ptr = src0 + i03*nb03 + i02*nb02 + i01*nb01 + tpitg.x*nb00;
-    device const char * src1_ptr = src1 + i13*nb13 + i12*nb12 + i11*nb11 + tpitg.x*nb10;
-    device       char * dst_ptr  = dst  + i03*nb3  + i02*nb2  + i01*nb1  + tpitg.x*nb0;
+    device const float * x;
 
     for (int i0 = tpitg.x; i0 < ne0; i0 += ntg.x) {
-        if (i02 < ne02) {
-            ((device float *)dst_ptr)[0] = ((device float *)src0_ptr)[0];
-            src0_ptr += ntg.x*nb00;
+        if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
+            x = (device const float *)(src0 + (i3       )*nb03 + (i2       )*nb02 + (i1       )*nb01 + (i0       )*nb00);
         } else {
-            ((device float *)dst_ptr)[0] = ((device float *)src1_ptr)[0];
-            src1_ptr += ntg.x*nb10;
+            x = (device const float *)(src1 + (i3 - o[3])*nb13 + (i2 - o[2])*nb12 + (i1 - o[1])*nb11 + (i0 - o[0])*nb10);
         }
-        dst_ptr += ntg.x*nb0;
+
+        device float * y = (device float *)(dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
+
+        *y = *x;
     }
 }