Add QU8 NR=32 microkernels

- 1x32, 2x32, and 3x32 GEMM and IGEMM neon dot microkernels

PiperOrigin-RevId: 395551920
diff --git a/CMakeLists.txt b/CMakeLists.txt
index a389395..a2146dc 100755
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -2375,10 +2375,13 @@
   src/qs8-igemm/gen/8x16c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/1x8c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/1x16c4-minmax-rndnu-neondot.c
+  src/qu8-gemm/gen/1x32c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/2x8c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/2x16c4-minmax-rndnu-neondot.c
+  src/qu8-gemm/gen/2x32c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/3x8c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/3x16c4-minmax-rndnu-neondot.c
+  src/qu8-gemm/gen/3x32c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/4x8c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/4x16c4-minmax-rndnu-neondot.c
   src/qu8-gemm/gen/5x8c4-minmax-rndnu-neondot.c
@@ -2389,10 +2392,13 @@
   src/qu8-gemm/gen/8x16c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/1x8c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/1x16c4-minmax-rndnu-neondot.c
+  src/qu8-igemm/gen/1x32c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/2x8c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/2x16c4-minmax-rndnu-neondot.c
+  src/qu8-igemm/gen/2x32c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/3x8c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/3x16c4-minmax-rndnu-neondot.c
+  src/qu8-igemm/gen/3x32c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/4x8c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/4x16c4-minmax-rndnu-neondot.c
   src/qu8-igemm/gen/5x8c4-minmax-rndnu-neondot.c