QS8 GEMM and IGEMM 3x8 3x16 and IGEMM 4x8 and 4x16

PiperOrigin-RevId: 352033627
diff --git a/BUILD.bazel b/BUILD.bazel
index 41bea3a..de772f3 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -1696,22 +1696,30 @@
     "src/qs8-gavgpool/gen/7x-minmax-neon-c16-acc2.c",
     "src/qs8-gavgpool/gen/7x-minmax-neon-c24-acc2.c",
     "src/qs8-gavgpool/gen/7x-minmax-neon-c32-acc2.c",
-    "src/qs8-gemm/gen/1x8-minmax-neon-mlal-lane.c",
     "src/qs8-gemm/gen/1x16-minmax-neon-mlal-lane.c",
-    "src/qs8-gemm/gen/2x8-minmax-neon-mlal-lane.c",
+    "src/qs8-gemm/gen/1x8-minmax-neon-mlal-lane.c",
     "src/qs8-gemm/gen/2x16-minmax-neon-mlal-lane.c",
-    "src/qs8-gemm/gen/4x8-minmax-neon-mlal-lane.c",
+    "src/qs8-gemm/gen/2x8-minmax-neon-mlal-lane.c",
+    "src/qs8-gemm/gen/3x16-minmax-neon-mlal-lane.c",
+    "src/qs8-gemm/gen/3x8-minmax-neon-mlal-lane.c",
     "src/qs8-gemm/gen/4x16-minmax-neon-mlal-lane.c",
-    "src/qs8-gemm/gen/1x8-minmax-neon-mull-addw-dup.c",
+    "src/qs8-gemm/gen/4x8-minmax-neon-mlal-lane.c",
     "src/qs8-gemm/gen/1x16-minmax-neon-mull-addw-dup.c",
-    "src/qs8-gemm/gen/2x8-minmax-neon-mull-addw-dup.c",
+    "src/qs8-gemm/gen/1x8-minmax-neon-mull-addw-dup.c",
     "src/qs8-gemm/gen/2x16-minmax-neon-mull-addw-dup.c",
-    "src/qs8-gemm/gen/4x8-minmax-neon-mull-addw-dup.c",
+    "src/qs8-gemm/gen/2x8-minmax-neon-mull-addw-dup.c",
+    "src/qs8-gemm/gen/3x16-minmax-neon-mull-addw-dup.c",
+    "src/qs8-gemm/gen/3x8-minmax-neon-mull-addw-dup.c",
     "src/qs8-gemm/gen/4x16-minmax-neon-mull-addw-dup.c",
-    "src/qs8-igemm/gen/1x8-minmax-neon-mlal-lane.c",
+    "src/qs8-gemm/gen/4x8-minmax-neon-mull-addw-dup.c",
     "src/qs8-igemm/gen/1x16-minmax-neon-mlal-lane.c",
-    "src/qs8-igemm/gen/2x8-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/1x8-minmax-neon-mlal-lane.c",
     "src/qs8-igemm/gen/2x16-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/2x8-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/3x16-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/3x8-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/4x16-minmax-neon-mlal-lane.c",
+    "src/qs8-igemm/gen/4x8-minmax-neon-mlal-lane.c",
     "src/qs8-requantization/fp32-neon.c",
     "src/qs8-requantization/precise-neon.c",
     "src/qs8-requantization/q31-neon.c",