QS8 4x8 dot product GEMM AArch32 microkernel for Cortex A55

PiperOrigin-RevId: 423856295
diff --git a/BUILD.bazel b/BUILD.bazel
index 7ff3445..78d4c29 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -7060,6 +7060,7 @@
     "src/qc8-igemm/gen/4x8c4-minmax-fp32-aarch32-neondot-ld64.S",
     "src/qs8-gemm/gen/4x8-minmax-rndnu-aarch32-neon-mlal-lane-ld64.S",
     "src/qs8-gemm/gen/4x8-minmax-rndnu-aarch32-neon-mlal-lane-prfm-ld64.S",
+    "src/qs8-gemm/gen/4x8c4-minmax-rndnu-aarch32-neondot-cortex-a55.S",
     "src/qs8-gemm/gen/4x8c4-minmax-rndnu-aarch32-neondot-ld64.S",
     "src/qs8-igemm/gen/4x8-minmax-rndnu-aarch32-neon-mlal-lane-ld64.S",
     "src/qs8-igemm/gen/4x8-minmax-rndnu-aarch32-neon-mlal-lane-prfm-ld64.S",
@@ -9162,9 +9163,9 @@
         "src/jit/memory.c",
     ],
     hdrs = INTERNAL_HDRS + [
-        "src/xnnpack/assembler.h",
         "src/xnnpack/aarch32-assembler.h",
         "src/xnnpack/aarch64-assembler.h",
+        "src/xnnpack/assembler.h",
     ],
     aarch32_srcs = JIT_AARCH32_SRCS,
     msvc_copts = xnnpack_msvc_std_copts(),