[OpOptimization] Sync with buddy-compiler/buddy-mlir#201

Author: EllisLambda

README.md

@@ -235,7 +235,34 @@ $ ninja <your target operation benchmark>
 //   - conv2d-nchw-fchw-benchmark
 //   - matmul-benchmark
 ```
-OpenMP is required in matmul-benchmark, make sure `libomp` and `libomp-dev` (on Ubuntu and Debian) / `libomp-devel` (on Redhat and SUSE) have been installed.
+### matmul-benchmark
+`OpenMP` and `lld` LTO is required in matmul-benchmark. To ensure version compatibility with the project, it's recommended to use the LLVM toolchains built within the `buddy-benchmark`. Follow the steps below:
+- build llvm toolchains with `lld` and `OpenMP`.
+```
+$ cd buddy-mlir/llvm/build
+$ cmake -G Ninja ../llvm \
+    -DLLVM_ENABLE_PROJECTS="mlir;clang;lld;openmp" \
+    -DLLVM_TARGETS_TO_BUILD="host;RISCV" \
+    -DLLVM_ENABLE_ASSERTIONS=ON \
+    -DLLVM_ENABLE_RUNTIMES=all \
+    -DOPENMP_ENABLE_LIBOMPTARGET=OFF \
+    -DCMAKE_BUILD_TYPE=RELEASE
+```
+- use the `clang++` in `buddy-mlir/llvm/build/bin`.
+```
+$ mkdir build && cd build
+$ cmake -G Ninja .. \
+    -DCMAKE_BUILD_TYPE=RELEASE \
+    -DOP_OPTIMIZATION_BENCHMARKS=ON \
+    -DCMAKE_CXX_COMPILER=/PATH/TO/BUDDY-MLIR/BUILD/bin/clang++ \
+    -DBUDDY_MLIR_BUILD_DIR=/PATH/TO/BUDDY-MLIR/BUILD/
+$ ninja matmul-benchmark
+```
+- `matmul-benchmark` need to load the `libomp.so` in `buddy-mlir/llvm/build/lib` to execute, here's a temporary way without root. 
+
+```
+$ export LD_LIBRARY_PATH=/PATH/TO/BUDDY-MLIR/BUILD/lib/:$LD_LIBRARY_PATH
+```
 
 Run TVM operation optimization benchmark cases.
 - Install TVM ([steps](./thirdparty/README.md#tvm)).

benchmarks/OpOptimization/MatMul/CMakeLists.txt

@@ -123,7 +123,7 @@ function(build_batch_matmul_broadcast step)
     COMMAND cat ${BUDDY_SOURCE_DIR}/benchmarks/OpOptimization/MatMul/BatchMatMul.mlir |
           sed 's/bm_batch_matmul/batch_matmul_broadcast_${step}/g' |
           ${BUDDY_MLIR_BUILD_DIR}/bin/buddy-opt
-            -batchmatmul-optimize="step-placeholder=${step}"
+            -batchmatmul-optimize="vector-size=${step}"
             -expand-strided-metadata
             -affine-super-vectorize
             -lower-affine
@@ -178,7 +178,7 @@ add_executable(matmul-benchmark
   MatMulBenchmark.cpp
   )
 
-set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native -fopenmp -flto")
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native -fopenmp -flto -fuse-ld=lld")
 
 target_link_libraries(matmul-benchmark
   GoogleBenchmark

benchmarks/OpOptimization/MatMul/MatMulBenchmark.cpp

@@ -131,7 +131,6 @@ BENCHMARK(BM_MATMUL_BROADCAST_32)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_MATMUL_BROADCAST_64)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_MATMUL_BROADCAST_128)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_MATMUL_BROADCAST_256)->Unit(benchmark::kMillisecond);
-BENCHMARK(BM_MATMUL_BROADCAST_256)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_BATCH_MATMUL_SCALAR)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_BATCH_MATMUL_BROADCAST_64)->Unit(benchmark::kMillisecond);
 BENCHMARK(BM_BATCH_MATMUL_BROADCAST_64_OMP)->Unit(benchmark::kMillisecond);