NEON Dot Product implementations of QS8 FP32 c4 GEMM and IGEMM assembly microkernels

PiperOrigin-RevId: 382208248
diff --git a/BUILD.bazel b/BUILD.bazel
index 21c8af5..58f1281 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -4279,6 +4279,8 @@
     "src/qs8-gemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-prfm-cortex-a53.S",
     "src/qs8-gemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-prfm.S",
     "src/qs8-gemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal.S",
+    "src/qs8-gemm/gen/1x16c4-minmax-fp32-aarch64-neondot-ld32.S",
+    "src/qs8-gemm/gen/1x16c4-minmax-fp32-aarch64-neondot-ld64.S",
     "src/qs8-gemm/gen/1x16c4-minmax-gemmlowp-aarch64-neondot-ld32.S",
     "src/qs8-gemm/gen/1x16c4-minmax-gemmlowp-aarch64-neondot-ld64.S",
     "src/qs8-gemm/gen/2x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-cortex-a53.S",
@@ -4289,11 +4291,14 @@
     "src/qs8-gemm/gen/2x8c16-minmax-gemmlowp-aarch64-neon-mlal-padal.S",
     "src/qs8-gemm/gen/4x16-minmax-gemmlowp-aarch64-neon-mlal-lane-cortex-a53.S",
     "src/qs8-gemm/gen/4x16-minmax-gemmlowp-aarch64-neon-mlal-lane-prfm-cortex-a53.S",
+    "src/qs8-gemm/gen/4x16c4-minmax-fp32-aarch64-neondot-cortex-a55.S",
+    "src/qs8-gemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld32.S",
+    "src/qs8-gemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld64.S",
+    "src/qs8-gemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld128.S",
     "src/qs8-gemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-cortex-a55.S",
     "src/qs8-gemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-ld32.S",
     "src/qs8-gemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-ld64.S",
     "src/qs8-gemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-ld128.S",
-    "src/qs8-gemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld128.S",
     "src/qs8-igemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-cortex-a53.S",
     "src/qs8-igemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-prfm-cortex-a53.S",
     "src/qs8-igemm/gen/1x8c8-minmax-gemmlowp-aarch64-neon-mlal-padal-prfm.S",
@@ -4305,6 +4310,9 @@
     "src/qs8-igemm/gen/2x8c16-minmax-gemmlowp-aarch64-neon-mlal-padal.S",
     "src/qs8-igemm/gen/4x16-minmax-gemmlowp-aarch64-neon-mlal-lane-cortex-a53.S",
     "src/qs8-igemm/gen/4x16-minmax-gemmlowp-aarch64-neon-mlal-lane-prfm-cortex-a53.S",
+    "src/qs8-igemm/gen/4x16c4-minmax-fp32-aarch64-neondot-cortex-a55.S",
+    "src/qs8-igemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld64.S",
+    "src/qs8-igemm/gen/4x16c4-minmax-fp32-aarch64-neondot-ld128.S",
     "src/qs8-igemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-cortex-a55.S",
     "src/qs8-igemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-ld64.S",
     "src/qs8-igemm/gen/4x16c4-minmax-gemmlowp-aarch64-neondot-ld128.S",