Better Arm64 input register loading and incrementation.

Believe it or not, these small changes make kernels about 3% faster.

PiperOrigin-RevId: 707440293

CMakeLists.txt

@@ -44,7 +44,12 @@ SET(CMAKE_CXX_EXTENSIONS NO)
 # ---[ Options.
 SET(XNNPACK_LIBRARY_TYPE "default" CACHE STRING "Type of library (shared, static, or default) to build")
 SET_PROPERTY(CACHE XNNPACK_LIBRARY_TYPE PROPERTY STRINGS default static shared)
-OPTION(XNNPACK_ENABLE_ASSEMBLY "Build XNNPACK with assembly micro-kernels" ON)
+IF(CMAKE_C_COMPILER_ID STREQUAL "MSVC")
+  # Disable assembly when using MSVC until support is added.
+  OPTION(XNNPACK_ENABLE_ASSEMBLY "Build XNNPACK with assembly micro-kernels" OFF)
+ELSE()
+  OPTION(XNNPACK_ENABLE_ASSEMBLY "Build XNNPACK with assembly micro-kernels" ON)
+ENDIF()
 OPTION(XNNPACK_ENABLE_MEMOPT "Build XNNPACK with optimized memory allocation scheme" ON)
 OPTION(XNNPACK_ENABLE_SPARSE "Build XNNPACK with graph rewriting for sparse inference" ON)
 OPTION(XNNPACK_ENABLE_GEMM_M_SPECIALIZATION "Build XNNPACK with support for selecting microkernel with different MR" ON)
@@ -658,6 +663,9 @@ IF(XNNPACK_TARGET_PROCESSOR MATCHES "^x86(_64)?$")
   LIST(APPEND PROD_MICROKERNEL_SRCS ${PROD_F16C_MICROKERNEL_SRCS})
   LIST(APPEND PROD_MICROKERNEL_SRCS ${PROD_FMA3_MICROKERNEL_SRCS})
   LIST(APPEND PROD_MICROKERNEL_SRCS ${PROD_AVX2_MICROKERNEL_SRCS})
+  IF(XNNPACK_ENABLE_ASSEMBLY AND XNNPACK_TARGET_PROCESSOR MATCHES "x86_64")
+    LIST(APPEND PROD_MICROKERNEL_SRCS ${PROD_AMD64_ASM_MICROKERNEL_SRCS})
+  ENDIF()
   IF(XNNPACK_ENABLE_AVX512AMX)
     LIST(APPEND PROD_MICROKERNEL_SRCS ${PROD_AVX512AMX_MICROKERNEL_SRCS})
   ENDIF()
@@ -705,6 +713,9 @@ IF(XNNPACK_TARGET_PROCESSOR MATCHES "^x86(_64)?$")
   LIST(APPEND NON_PROD_MICROKERNEL_SRCS ${NON_PROD_F16C_MICROKERNEL_SRCS})
   LIST(APPEND NON_PROD_MICROKERNEL_SRCS ${NON_PROD_FMA3_MICROKERNEL_SRCS})
   LIST(APPEND NON_PROD_MICROKERNEL_SRCS ${NON_PROD_AVX2_MICROKERNEL_SRCS})
+  IF(XNNPACK_ENABLE_ASSEMBLY AND XNNPACK_TARGET_PROCESSOR MATCHES "x86_64")
+    LIST(APPEND NON_PROD_MICROKERNEL_SRCS ${NON_PROD_AMD64_ASM_MICROKERNEL_SRCS})
+  ENDIF()
   IF(XNNPACK_ENABLE_AVX512AMX)
     LIST(APPEND NON_PROD_MICROKERNEL_SRCS ${NON_PROD_AVX512AMX_MICROKERNEL_SRCS})
   ENDIF()