Divide elementwise case from BroadcastKernel and refine transpose aut…

…otune (PaddlePaddle#33051) * First Commit. * add some codes * add elementwise loader * fix code styles * merge with develop * add some changes both in elementwise and transpose * add init operation in broadcast kernel. * change codes according to pr suggestions about transpose file * fix error for op-benchmark ci * fix according to ci
lxsbupt · Dec 14, 2022 · 82e890b · 82e890b
1 parent 3cbbd40
commit 82e890b
Show file tree

Hide file tree

Showing 9 changed files with 447 additions and 437 deletions.
diff --git a/paddle/fluid/operators/mkldnn/transpose_mkldnn_op.cc b/paddle/fluid/operators/mkldnn/transpose_mkldnn_op.cc
@@ -16,7 +16,6 @@
 #include "paddle/fluid/framework/op_registry.h"
 #include "paddle/fluid/memory/malloc.h"
 #include "paddle/fluid/platform/mkldnn_reuse.h"
-#include "paddle/phi/kernels/funcs/transpose_functor.h"
 
 namespace paddle {
 namespace operators {

diff --git a/paddle/fluid/operators/transpose_op.cc b/paddle/fluid/operators/transpose_op.cc
@@ -20,7 +20,6 @@ limitations under the License. */
 #include "paddle/fluid/platform/mkldnn_helper.h"
 #endif
 #include "paddle/fluid/framework/op_registry.h"
-#include "paddle/phi/kernels/funcs/transpose_functor.h"
 
 namespace paddle {
 namespace operators {

diff --git a/paddle/fluid/operators/transpose_op_mlu.cc b/paddle/fluid/operators/transpose_op_mlu.cc
@@ -13,7 +13,6 @@ See the License for the specific language governing permissions and
 limitations under the License. */
 
 #include "paddle/fluid/operators/mlu/mlu_baseop.h"
-#include "paddle/phi/kernels/funcs/transpose_functor.h"
 
 namespace paddle {
 namespace operators {

diff --git a/paddle/fluid/operators/unique_op.h b/paddle/fluid/operators/unique_op.h
@@ -24,7 +24,6 @@ limitations under the License. */
 #include "paddle/fluid/framework/op_registry.h"
 #include "paddle/fluid/operators/math/concat_and_split.h"
 #include "paddle/phi/kernels/funcs/math_function.h"
-#include "paddle/phi/kernels/funcs/transpose_functor.h"
 
 namespace paddle {
 namespace operators {

diff --git a/paddle/phi/kernels/autotune/auto_tune_base.h b/paddle/phi/kernels/autotune/auto_tune_base.h
@@ -123,7 +123,7 @@ class AutoTuneBase {
   float RunAndMeasureKernel(const Context& ctx, const int idx, Args&&... args) {
     // Regard 1st run as warmup, judge the compare result by the time cost
     // of rest cycles.
-    constexpr int repeats = 4;
+    constexpr int repeats = 6;
     phi::GpuTimer timer;
     float time_cost = 0;
     const auto& stream = ctx.stream();