Merge remote-tracking branch 'origin/develop' into stream-k-initial-impl

784ef1d3 · carlushuang · 556d2495 · d1838d32 · 784ef1d3 · 784ef1d3
Commit 784ef1d3 authored Jun 15, 2023 by carlushuang
20 changed files
--- a/example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp
+++ b/example/19_binary_elementwise/broadcast_add_2d_amn_bn.cpp
--- a/example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp
+++ b/example/19_binary_elementwise/broadcast_add_3d_am_bmnk.cpp
--- a/example/19_binary_elementwise/elementwise_add_1d.cpp
+++ b/example/19_binary_elementwise/elementwise_add_1d.cpp
--- a/example/19_binary_elementwise/elementwise_add_4d.cpp
+++ b/example/19_binary_elementwise/elementwise_add_4d.cpp
--- a/example/20_grouped_conv_bwd_weight/common.hpp
+++ b/example/20_grouped_conv_bwd_weight/common.hpp
--- a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp
+++ b/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_bf16.cpp
--- a/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp
+++ b/example/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_xdl_fp16.cpp
--- a/example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc
+++ b/example/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc
--- a/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp
+++ b/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp
--- a/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp
+++ b/example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp
--- a/example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp
+++ b/example/21_gemm_layernorm/gemm_layernorm_xdl_naive_fp16.cpp
--- a/example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp
+++ b/example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_fp16.cpp
--- a/example/22_cgemm/cgemm_xdl_bf16.cpp
+++ b/example/22_cgemm/cgemm_xdl_bf16.cpp
--- a/example/22_cgemm/cgemm_xdl_common.hpp
+++ b/example/22_cgemm/cgemm_xdl_common.hpp
--- a/example/22_cgemm/cgemm_xdl_fp16.cpp
+++ b/example/22_cgemm/cgemm_xdl_fp16.cpp
--- a/example/22_cgemm/cgemm_xdl_fp32.cpp
+++ b/example/22_cgemm/cgemm_xdl_fp32.cpp
--- a/example/22_cgemm/cgemm_xdl_int4.cpp
+++ b/example/22_cgemm/cgemm_xdl_int4.cpp
--- a/example/22_cgemm/cgemm_xdl_int8.cpp
+++ b/example/22_cgemm/cgemm_xdl_int8.cpp
--- a/example/23_softmax/softmax_blockwise.cpp
+++ b/example/23_softmax/softmax_blockwise.cpp
--- a/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
+++ b/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp