NEON-MLAL implementations of QU8 GEMM/IGEMM microkernels

PiperOrigin-RevId: 384836330
diff --git a/CMakeLists.txt b/CMakeLists.txt
index bd797a0..6b611a8 100755
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1267,8 +1267,12 @@
   src/qu8-gavgpool/7x-minmax-neon-c8.c
   src/qu8-gemm/4x8-minmax-gemmlowp-neon.c
   src/qu8-gemm/8x8-minmax-gemmlowp-neon.c
+  src/qu8-gemm/gen/1x16-minmax-fp32-neon-mlal-lane.c
+  src/qu8-gemm/gen/4x16-minmax-fp32-neon-mlal-lane.c
   src/qu8-igemm/4x8-minmax-gemmlowp-neon.c
   src/qu8-igemm/8x8-minmax-gemmlowp-neon.c
+  src/qu8-igemm/gen/1x16-minmax-fp32-neon-mlal-lane.c
+  src/qu8-igemm/gen/4x16-minmax-fp32-neon-mlal-lane.c
   src/qu8-requantization/fp32-neon.c
   src/qu8-requantization/gemmlowp-neon.c
   src/qu8-requantization/rndna-neon.c
@@ -1543,7 +1547,11 @@
   src/qs8-igemm/gen/1x16-minmax-fp32-neonv8-mlal-lane.c
   src/qs8-igemm/gen/2x8c2-minmax-fp32-neonv8-mlal-padal-dup.c
   src/qs8-igemm/gen/2x8c8-minmax-fp32-neonv8-mlal-padal.c
-  src/qs8-igemm/gen/4x16-minmax-fp32-neonv8-mlal-lane.c)
+  src/qs8-igemm/gen/4x16-minmax-fp32-neonv8-mlal-lane.c
+  src/qu8-gemm/gen/1x16-minmax-fp32-neon-mlal-lane.c
+  src/qu8-gemm/gen/4x16-minmax-fp32-neon-mlal-lane.c
+  src/qu8-igemm/gen/1x16-minmax-fp32-neon-mlal-lane.c
+  src/qu8-igemm/gen/4x16-minmax-fp32-neon-mlal-lane.c)
 
 SET(XNNPACK_AARCH64_NEONFMA_MICROKERNEL_SRCS
   src/f32-conv-hwc/gen/3x3s2p0p1c3x4-neonfma-2x1.c