cpu: x64: pooling: use fp32 accumulator for bf16 max-pooling backprop

oneapi-src · Jan 13, 2025 · 2820609 · 2820609
1 parent d96d26d
commit 2820609
Show file tree

Hide file tree

Showing 5 changed files with 389 additions and 92 deletions.
diff --git a/src/common/memory_tracking.hpp b/src/common/memory_tracking.hpp
@@ -1,5 +1,5 @@
 /*******************************************************************************
-* Copyright 2018-2024 Intel Corporation
+* Copyright 2018-2025 Intel Corporation
 * Copyright 2024-2025 Arm Ltd. and affiliates
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
@@ -271,6 +271,7 @@ enum {
     key_pool_dst_plain2blocked_cvt,
     key_pool_ind_plain2blocked_cvt,
     key_pool_src_bf16cvt,
+    key_pool_src_f32_accum,
     key_pool_src_plain2blocked_cvt,
     key_pool_reduction,
     key_precomputed_scales,

diff --git a/src/cpu/x64/jit_primitive_conf.hpp b/src/cpu/x64/jit_primitive_conf.hpp
@@ -526,6 +526,8 @@ struct jit_pool_conf_t {
     bool with_binary;
     int nthr;
     memory_desc_t tmp_md;
+    bool needs_f32_accum_for_bf16;
+    dim_t f32_accum_block_size;
 };
 
 struct jit_pool_call_s {