diff --git a/clang/lib/Headers/amxintrin.h b/clang/lib/Headers/amxintrin.h
--- a/clang/lib/Headers/amxintrin.h
+++ b/clang/lib/Headers/amxintrin.h
@@ -258,7 +258,7 @@
 }
 
 __DEFAULT_FN_ATTRS_INT8
-static void __tile_dpbsud(__tile1024i *dst, __tile1024i src1,
+static void __tile_dpbssd(__tile1024i *dst, __tile1024i src1,
                           __tile1024i src2) {
   dst->tile = _tile_dpbssd_internal(src1.row, src2.col, src1.col, dst->tile,
                                     src1.tile, src2.tile);
diff --git a/clang/test/CodeGen/X86/amx_api.c b/clang/test/CodeGen/X86/amx_api.c
--- a/clang/test/CodeGen/X86/amx_api.c
+++ b/clang/test/CodeGen/X86/amx_api.c
@@ -27,7 +27,7 @@
     __tile_loadd(&b, buf2, STRIDE);
     __tile_loadd(&c, buf2, STRIDE);
   }
-  __tile_dpbsud(&c, a, b);
+  __tile_dpbssd(&c, a, b);
   __tile_stored(buf, STRIDE, c);
 }
 
@@ -39,11 +39,11 @@
   __tile_loadd(&a, buf, STRIDE);
 }
 
-void test_tile_dpbsud(__tile1024i a, __tile1024i b, __tile1024i c) {
-  //CHECK-LABEL: @test_tile_dpbsud
+void test_tile_dpbssd(__tile1024i a, __tile1024i b, __tile1024i c) {
+  //CHECK-LABEL: @test_tile_dpbssd
   //CHECK: call x86_amx @llvm.x86.tdpbssd.internal
   //CHECK-NEXT: {{%.*}} = bitcast x86_amx {{%.*}} to <256 x i32>
-  __tile_dpbsud(&c, a, b);
+  __tile_dpbssd(&c, a, b);
 }
 
 void test_tile_stored(__tile1024i c) {