AARCH32 4x8 NEON GEMM
Assembly version of 4x8 for 32 bit ARM.  Based on LD64.

PiperOrigin-RevId: 282889207
diff --git a/CMakeLists.txt b/CMakeLists.txt
index b3a81a8..77cd8c9 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -802,7 +802,8 @@
   src/math/extexp-avx512f-p5.c)
 
 SET(XNNPACK_AARCH32_ASM_MICROKERNEL_SRCS
-  src/q8-dwconv/up8x9-aarch32-neon.S)
+  src/q8-dwconv/up8x9-aarch32-neon.S
+  src/f32-gemm/4x8-aarch32-neon-ld64.S)
 
 SET(XNNPACK_AARCH64_ASM_MICROKERNEL_SRCS
   src/f32-dwconv/up4x9-aarch64-neonfma-cortex-a55.S