SSE4.1 and XOP versions of MUL32 VADD[C] microkernels

PiperOrigin-RevId: 330328493
diff --git a/CMakeLists.txt b/CMakeLists.txt
index f122371..ba6e355 100755
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1567,10 +1567,18 @@
   src/qs8-vadd/gen/minmax-sse41-mul16-ld64-x16.c
   src/qs8-vadd/gen/minmax-sse41-mul16-ld64-x24.c
   src/qs8-vadd/gen/minmax-sse41-mul16-ld64-x32.c
+  src/qs8-vadd/gen/minmax-sse41-mul32-ld32-x8.c
+  src/qs8-vadd/gen/minmax-sse41-mul32-ld32-x16.c
+  src/qs8-vadd/gen/minmax-sse41-mul32-ld32-x24.c
+  src/qs8-vadd/gen/minmax-sse41-mul32-ld32-x32.c
   src/qs8-vaddc/gen/minmax-sse41-mul16-ld64-x8.c
   src/qs8-vaddc/gen/minmax-sse41-mul16-ld64-x16.c
   src/qs8-vaddc/gen/minmax-sse41-mul16-ld64-x24.c
   src/qs8-vaddc/gen/minmax-sse41-mul16-ld64-x32.c
+  src/qs8-vaddc/gen/minmax-sse41-mul32-ld32-x8.c
+  src/qs8-vaddc/gen/minmax-sse41-mul32-ld32-x16.c
+  src/qs8-vaddc/gen/minmax-sse41-mul32-ld32-x24.c
+  src/qs8-vaddc/gen/minmax-sse41-mul32-ld32-x32.c
   src/qu8-requantization/precise-sse4.c
   src/qu8-requantization/q31-sse4.c
   src/math/roundne-sse41.c
@@ -1702,7 +1710,15 @@
   src/qs8-igemm/gen/3x4c8-minmax-xop-ld64.c
   src/qs8-igemm/gen/1x4c8-minmax-xop-ld128.c
   src/qs8-igemm/gen/2x4c8-minmax-xop-ld128.c
-  src/qs8-igemm/gen/3x4c8-minmax-xop-ld128.c)
+  src/qs8-igemm/gen/3x4c8-minmax-xop-ld128.c
+  src/qs8-vadd/gen/minmax-xop-mul32-ld32-x8.c
+  src/qs8-vadd/gen/minmax-xop-mul32-ld32-x16.c
+  src/qs8-vadd/gen/minmax-xop-mul32-ld32-x24.c
+  src/qs8-vadd/gen/minmax-xop-mul32-ld32-x32.c
+  src/qs8-vaddc/gen/minmax-xop-mul32-ld32-x8.c
+  src/qs8-vaddc/gen/minmax-xop-mul32-ld32-x16.c
+  src/qs8-vaddc/gen/minmax-xop-mul32-ld32-x24.c
+  src/qs8-vaddc/gen/minmax-xop-mul32-ld32-x32.c)
 
 SET(XNNPACK_FMA3_MICROKERNEL_SRCS
   src/f32-dwconv/gen/up16x4-minmax-fma3-acc2.c