Change placement in ops.cpp

Author: tdakhran

ggml/src/ggml-cpu/ops.cpp

@@ -7402,9 +7402,27 @@ static void ggml_compute_forward_upscale_f32(
         sf1 = ne1 > 1 && ne01 > 1 ? (float)(ne1 - 1) / (ne01 - 1) : sf1;
     }
 
-    // Similar to F.interpolate(..., mode="bilinear", align_corners=False, antialias=True)
-    // https://github.com/pytorch/pytorch/blob/8871ff29b743948d1225389d5b7068f37b22750b/aten/src/ATen/native/cpu/UpSampleKernel.cpp
-    if (mode == GGML_SCALE_MODE_BILINEAR && (mode_flags & GGML_SCALE_FLAG_ANTIALIAS)) {
+    if (mode == GGML_SCALE_MODE_NEAREST) {
+        for (int64_t i3 = 0; i3 < ne3; i3++) {
+            const int64_t i03 = i3 / sf3;
+            for (int64_t i2 = ith; i2 < ne2; i2 += nth) {
+                const int64_t i02 = i2 / sf2;
+                for (int64_t i1 = 0; i1 < ne1; i1++) {
+                    const int64_t i01 = i1 / sf1;
+                    for (int64_t i0 = 0; i0 < ne0; i0++) {
+                        const int64_t i00 = i0 / sf0;
+
+                        const float * x = (float *)((char *) src0->data + i00*nb00 + i01*nb01 + i02*nb02 + i03*nb03);
+                              float * y = (float *)((char *)  dst->data +  i0*nb0  +  i1*nb1  +  i2*nb2  +  i3*nb3);
+
+                        *y = *x;
+                    }
+                }
+            }
+        }
+    } else if (mode == GGML_SCALE_MODE_BILINEAR && (mode_flags & GGML_SCALE_FLAG_ANTIALIAS)) {
+        // Similar to F.interpolate(..., mode="bilinear", align_corners=False, antialias=True)
+        // https://github.com/pytorch/pytorch/blob/8871ff29b743948d1225389d5b7068f37b22750b/aten/src/ATen/native/cpu/UpSampleKernel.cpp
         auto triangle_filter = [](float x) -> float {
             return std::max(1.0f - fabsf(x), 0.f);
         };
@@ -7461,24 +7479,6 @@ static void ggml_compute_forward_upscale_f32(
                 }
             }
         }
-    } else if (mode == GGML_SCALE_MODE_NEAREST) {
-        for (int64_t i3 = 0; i3 < ne3; i3++) {
-            const int64_t i03 = i3 / sf3;
-            for (int64_t i2 = ith; i2 < ne2; i2 += nth) {
-                const int64_t i02 = i2 / sf2;
-                for (int64_t i1 = 0; i1 < ne1; i1++) {
-                    const int64_t i01 = i1 / sf1;
-                    for (int64_t i0 = 0; i0 < ne0; i0++) {
-                        const int64_t i00 = i0 / sf0;
-
-                        const float * x = (float *)((char *) src0->data + i00*nb00 + i01*nb01 + i02*nb02 + i03*nb03);
-                              float * y = (float *)((char *)  dst->data +  i0*nb0  +  i1*nb1  +  i2*nb2  +  i3*nb3);
-
-                        *y = *x;
-                    }
-                }
-            }
-        }
     } else if (mode == GGML_SCALE_MODE_BILINEAR) {
         for (int64_t i3 = 0; i3 < ne3; i3++) {
             const int64_t i03 = i3 / sf3;