[CPU] Fixed Reduce kernel with bf16 destination precision

openvinotoolkit · Jan 29, 2025 · 895ec90 · 895ec90
1 parent ad44deb
commit 895ec90
Showing 1 changed file with 18 additions and 6 deletions.
diff --git a/src/plugins/intel_cpu/src/nodes/reduce.cpp b/src/plugins/intel_cpu/src/nodes/reduce.cpp
@@ -1006,9 +1006,15 @@ struct jit_uni_reduce_kernel_f32 : public jit_uni_reduce_kernel, public jit_gene
             uni_vmovups(op, vmm_dst);
             break;
         case memory::data_type::bf16:
-            uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
-                                         {static_cast<size_t>(ymm_dst.getIdx())});
-            vmovdqu16(op, ymm_dst);
+            if (isa == x64::avx512_core) {
+                uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
+                                             {static_cast<size_t>(ymm_dst.getIdx())});
+                vmovdqu16(op, ymm_dst);
+            } else {
+                uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
+                                             {static_cast<size_t>(xmm_dst.getIdx())});
+                uni_vmovdqu(op, xmm_dst);
+            }
             break;
         case memory::data_type::f16:
             vcvtps2ph(op, vmm_dst, 0x4);
@@ -1723,9 +1729,15 @@ struct jit_uni_reduce_post_kernel_f32 : public jit_uni_reduce_post_kernel, publi
             uni_vmovups(op, vmm_dst);
             break;
         case memory::data_type::bf16:
-            uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
-                                         {static_cast<size_t>(ymm_dst.getIdx())});
-            vmovdqu16(op, ymm_dst);
+            if (isa == x64::avx512_core) {
+                uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
+                                             {static_cast<size_t>(ymm_dst.getIdx())});
+                vmovdqu16(op, ymm_dst);
+            } else {
+                uni_vcvtneps2bf16->emit_code({static_cast<size_t>(vmm_dst.getIdx())},
+                                             {static_cast<size_t>(xmm_dst.getIdx())});
+                uni_vmovdqu(op, xmm_dst);
+            }
             break;
         case memory::data_type::f16:
             vcvtps2ph(op, vmm_dst, 0x4);