Rebased the hipTENSOR development branch with the contraction branch

example/20_convnd_bwd_weight_xdl/CMakeLists.txt

 add_example_executable(example_convnd_bwd_weight_xdl convnd_bwd_weight_xdl.cpp)
+add_example_executable(example_convnd_bwd_weight_xdl_bf16_splitk convnd_bwd_weight_xdl_bf16_splitk.cpp)
 target_link_libraries(example_convnd_bwd_weight_xdl PRIVATE conv_util)
+target_link_libraries(example_convnd_bwd_weight_xdl_bf16_splitk PRIVATE conv_util)
\ No newline at end of file

example/21_gemm_layernorm/CMakeLists.txt

+add_example_executable(example_gemm_bias_relu_add_layernorm_xdl_fp16 gemm_bias_relu_add_layernorm_xdl_fp16.cpp)
 add_example_executable(example_gemm_layernorm_xdl_fp16 gemm_layernorm_xdl_fp16.cpp)
+add_example_executable(example_gemm_xdl_layernorm_single_kernel_fp16 gemm_xdl_layernorm_single_kernel_fp16.cpp)

example/23_contraction/CMakeLists.txt

-add_example_executable(example_contraction_xdl_fp32 contraction_xdl_fp32.cpp)

example/23_softmax/CMakeLists.txt

+add_example_executable(example_softmax_blockwise softmax_blockwise.cpp)
\ No newline at end of file

example/23_softmax/README.md

+# Instructions for ```example_softmax_blockwise```
+
+## Run ```example_softmax_blockwise```
+```bash
+# -D <xxx> : input 3-d tensor lengths
+# -v <x> :   verification (0=no, 1=yes)
+#arg1: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
+#arg2: time kernel (0=no, 1=yes)
+example_softmax_blockwise -D 4,128,2048 -v 1 1 1
+```
+
+Result
+```
+launch_and_time_kernel: grid_dim {64, 1, 1}, block_dim {256, 1, 1}
+Warm up 1 time
+Start running 10 times...
+Perf: 0.0242877 ms, 259.039 GB/s, DeviceReduceSoftmax<256,M_C8_S1,K_C32_S8,InSrcVectorDim_1_InSrcVectorSize_8_OutDstVectorSize_8>
+```

example/24_batched_gemm_c_permute/CMakeLists.txt

+add_example_executable(example_batched_gemm_c_permute_xdl_fp16 batched_gemm_c_permute_xdl_fp16.cpp)
+

example/25_gemm_bias_c_permute/CMakeLists.txt

+add_example_executable(example_gemm_bias_c_permute_xdl_fp16 gemm_bias_c_permute_xdl_fp16.cpp)

example/26_contraction/CMakeLists.txt

+add_example_executable(example_contraction_bilinear_xdl_fp32 contraction_bilinear_xdl_fp32.cpp)
+add_example_executable(example_contraction_scale_xdl_fp32 contraction_scale_xdl_fp32.cpp)

example/23_contraction/README.md → example/26_contraction/README.md

-# Instructions for ```example_contraction_xdl_fp32```
+# Instructions for ```example_contraction_bilinear_xdl_fp32```
 
 ## Run
 ```bash
 #arg1: verification (0=no, 1=yes)
 #arg2: initialization (0=no init, 1=integer value, 2=decimal value)
 #arg3: time kernel (0=no, 1=yes)
-./bin/example_contraction_xdl_fp32 1 1 1
+./bin/example_contraction_bilinear_xdl_fp32 1 1 1
 ```
 
 Result (MI100 @ dynammic freq, 46TFlops peak FP32)
@@ -16,5 +16,5 @@ c_ms_ns: dim 4, lengths {30, 128, 32, 64}, strides {524288, 4096, 128, 1}
 launch_and_time_kernel: grid_dim {240, 1, 1}, block_dim {256, 1, 1}
 Warm up 1 time
 Start running 10 times...
-Perf: 0.843286 ms, 38.1985 TFlops, 94.5014 GB/s, DeviceContraction_Xdl_CShuffle<256, 256, 128, 16, 4, 4>
+Perf: 0.843286 ms, 38.1985 TFlops, 94.5014 GB/s, DeviceContractionMultipleD_Xdl_CShuffle<256, 256, 128, 16, 4, 4>
 ```