【Metax】Optimize code structure (PaddlePaddle#2119)

* [Metax] register fused_fc_elementwise_layernorm kernel (PaddlePaddle#143)

* [Metax] register fused_fc_elementwise_layernorm kernel

---------

Co-authored-by: chezhang <1376507468@qq.com>
Co-authored-by: duqimeng <77875733+duqimeng@users.noreply.github.com>
Co-authored-by: Mingkun.Zhang <2496808993@qq.com>
Co-authored-by: jiaxinWang-metax <189149612@qq.com>
Co-authored-by: MingkunZhang <39252862+StareAtYou@users.noreply.github.com>
Co-authored-by: zhang-chenyi <74278535+zhang-chenyi@users.noreply.github.com>
Co-authored-by: ZhouDuan <1184319564@qq.com>
Co-authored-by: Theendlessofhell <148317258+Theendlessofhell@users.noreply.github.com>
Co-authored-by: root <root@lt-wks-10-0-180-15.pub.metax-tech.com>
Co-authored-by: ZhouDuan <136539532+1184319564@users.noreply.github.com>
Co-authored-by: sw <1640472053@qq.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: tianshuo78520a <tianshuo78520a@users.noreply.github.com>

Author: 10 people

backends/metax_gpu/CMakeLists.txt

@@ -109,6 +109,10 @@ file(
   CUDA_SRCS
   # backends
   ${PADDLE_SOURCE_DIR}/paddle/phi/backends/gpu/cuda/cuda_info.cc
+  ${PADDLE_SOURCE_DIR}/paddle/phi/backends/dynload/dynamic_loader.cc
+  ${PADDLE_SOURCE_DIR}/paddle/phi/backends/dynload/cublas.cc
+  ${PADDLE_SOURCE_DIR}/paddle/phi/backends/dynload/cublasLt.cc
+  ${PADDLE_SOURCE_DIR}/paddle/phi/backends/dynload/cudnn.cc
   ${PADDLE_SOURCE_DIR}/paddle/phi/backends/dynload/cuda_driver.cc
   ${PADDLE_SOURCE_DIR}/paddle/phi/backends/gpu/cuda/cuda_graph.cc
   # Core
@@ -704,7 +708,6 @@ file(
   kernels/gpudnn/*.cu
   kernels/cuda_kernels/*.cc
   kernels/cuda_kernels/*.cu
-  kernels/funcs/blas/*.cc
   kernels/ernie_core/*.cu)
 
 set(CUSTOM_DEVICE_SRCS ${CUDA_SRCS} ${CC_SRCS} ${ERNIE_CORE_SRCS})
@@ -752,11 +755,28 @@ target_compile_definitions(
   PUBLIC PADDLE_WITH_CUDA=1
          PADDLE_WITH_CUSTOM_DEVICE=1
          mcblasContext=cublasContext
+         cublasLtContext=mcblasLtContext
          GPUContext=CustomContext
          KPSContext=CustomContext
          STREAM_TYPE=cudaStream_t
          EVENT_TYPE=cudaEvent_t
-         EIGEN_USE_GPU=1)
+         EIGEN_USE_GPU=1
+         CUDA_LIB_NAME="libmcruntime.so"
+         BLAS_LIB_NAME="libmcblas.so"
+         BLASLT_LIB_NAME="libmcblasLt.so"
+         DNN_LIB_NAME="libmcdnn.so"
+         PTI_LIB_NAME="libmcpti.so"
+         RAND_LIB_NAME="libcurand.so"
+         JPEG_LIB_NAME="libnvjpeg.so"
+         SOLVER_LIB_NAME="libmcsolver.so"
+         SPARSE_LIB_NAME="libmcsparse.so"
+         RTC_LIB_NAME="libmcruntime.so"
+         FLASHATTN_LIB_NAME="libmcFlashAttn.so"
+         FLASHATTNV3_LIB_NAME="libflashattnv3.so"
+         CCL_LIB_NAME="libmccl.so"
+         FFT_LIB_NAME="libcufft.so"
+         SPARSELT_LIB_NAME="libcusparseLt.so"
+         CUPTI_LIB_PATH="/root/cu-bridge/CUDA_DIR/extras/CUPTI/lib64")
 
 # packing wheel package
 configure_file(${CMAKE_CURRENT_SOURCE_DIR}/setup.py.in

backends/metax_gpu/common/flags_declare.cc

@@ -37,6 +37,27 @@
  */
 
 static constexpr int kDefaultConvWorkspaceSizeLimitMB = 512;
+/**
+ * CUDA related FLAG
+ * Name: FLAGS_cublaslt_exhaustive_search_times
+ * Since Version: 2.3.0
+ * Value Range: int64_t, default=0
+ * Example:
+ * Note: Represents times of exhaustive search to evaluate performance of
+ *       cuBlasLt matmul algorithm (with/without epilogue). Set this flag
+ *       with value > 0 to enable exhaustive search. Default is 0, means
+ *       getting algorithms via heuristic search. There are two search methods
+ *       in cuBlasLt, heuristic search and exhaustive search. Exhaustive search
+ *       attempts all cuBlasLt algorithms to select the fastest, which is very
+ *       time-consuming, and the selected algorithm will be cached for a given
+ *       layer specification Once you change the layer specifications
+ *       (such as M, N and K), it will re-search again.
+ */
+PHI_DEFINE_EXPORTED_int64(
+    cublaslt_exhaustive_search_times,
+    0,
+    "The times of exhaustive search for cuBlasLt matmul with/without "
+    " epilogue algorithms, default is 0, means disabling exhaustive search.");
 
 PHI_DEFINE_EXPORTED_bool(
     cudnn_exhaustive_search,