[Clang][AArch64]Remove _single from vg2x1 and vg4x1 svmla

This patch follows the PR#421[1] from the ACLE

These 2 FP8 intrinsics had single removed from them:
from ``svmla[_single]_za16[_mf8]_vg2x1_fpm`` to ``svmla_za16[_mf8]_vg2x1_fpm``
and  from ``svmla[_single]_za32[_mf8]_vg4x1_fpm`` to  ``svmla_za32[_mf8]_vg4x1_fpm``

[1]ARM-software/acle#421

Author: CarolineConcatto

clang/include/clang/Basic/arm_sme.td

@@ -992,7 +992,7 @@ let SMETargetGuard = "sme-f8f32" in {
   def SVMLA_FP8_LANE_ZA16_VG4x4 : Inst<"svmla_lane_za32[_mf8]_vg4x4", "vm4di>", "m", MergeNone, "aarch64_sme_fp8_fmlall_lane_za32_vg4x4",
                                        [IsStreaming, IsInOutZA, IsOverloadNone], [ImmCheck<3, ImmCheck0_15>]>;
   // FMLALL (single)
-  def SVMLA_FP8_SINGLE_ZA32_VG4x1 : Inst<"svmla[_single]_za32[_mf8]_vg4x1", "vmdd>", "m", MergeNone, "aarch64_sme_fp8_fmlall_single_za32_vg4x1",
+  def SVMLA_FP8_SINGLE_ZA32_VG4x1 : Inst<"svmla_za32[_mf8]_vg4x1", "vmdd>", "m", MergeNone, "aarch64_sme_fp8_fmlall_single_za32_vg4x1",
                                          [IsStreaming, IsInOutZA, IsOverloadNone], []>;
   def SVMLA_FP8_SINGLE_ZA32_VG4x2 : Inst<"svmla[_single]_za32[_mf8]_vg4x2", "vm2d>", "m", MergeNone, "aarch64_sme_fp8_fmlall_single_za32_vg4x2",
                                          [IsStreaming, IsInOutZA, IsOverloadNone], []>;
@@ -1016,7 +1016,7 @@ let SMETargetGuard = "sme-f8f16" in {
   def SVMLA_FP8_LANE_ZA16_VG2x4 : Inst<"svmla_lane_za16[_mf8]_vg2x4", "vm4di>", "m", MergeNone, "aarch64_sme_fp8_fmlal_lane_za16_vg2x4",
                                        [IsStreaming, IsInOutZA, IsOverloadNone], [ImmCheck<3, ImmCheck0_15>]>;
   // FMLAL (single)
-  def SVMLA_FP8_SINGLE_ZA16_VG2x1 : Inst<"svmla[_single]_za16[_mf8]_vg2x1", "vmdd>", "m", MergeNone, "aarch64_sme_fp8_fmlal_single_za16_vg2x1",
+  def SVMLA_FP8_SINGLE_ZA16_VG2x1 : Inst<"svmla_za16[_mf8]_vg2x1", "vmdd>", "m", MergeNone, "aarch64_sme_fp8_fmlal_single_za16_vg2x1",
                                          [IsStreaming, IsInOutZA, IsOverloadNone], []>;
   def SVMLA_FP8_SINGLE_ZA16_VG2x2 : Inst<"svmla[_single]_za16[_mf8]_vg2x2", "vm2d>", "m", MergeNone, "aarch64_sme_fp8_fmlal_single_za16_vg2x2",
                                          [IsStreaming, IsInOutZA, IsOverloadNone], []>;

clang/test/CodeGen/AArch64/fp8-intrinsics/acle_sme2_fp8_mla.c

@@ -144,7 +144,7 @@ void test_svmla_lane_za32_vg4x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t zm
 // CPP-CHECK-NEXT:    ret void
 //
 void test_svmla_single_za16_vg2x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
-    SME_ACLE_FUNC(svmla,_single,_za16,_mf8,_vg2x1_fpm)(slice, zn, zm, fpm);
+    SME_ACLE_FUNC(svmla_za16,_mf8,_vg2x1_fpm,,)(slice, zn, zm, fpm);
 }
 
 // CHECK-LABEL: define dso_local void @test_svmla_single_za16_vg2x2(
@@ -200,7 +200,7 @@ void test_svmla_single_za16_vg2x4(uint32_t slice, svmfloat8x4_t zn, svmfloat8_t
 // CPP-CHECK-NEXT:    ret void
 //
 void test_svmla_single_za32_vg4x1(uint32_t slice, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm) __arm_streaming __arm_inout("za") {
-    SME_ACLE_FUNC(svmla,_single,_za32,_mf8,_vg4x1_fpm)(slice, zn, zm, fpm);
+    SME_ACLE_FUNC(svmla_za32,_mf8,_vg4x1_fpm,,)(slice, zn, zm, fpm);
 }
 
 // CHECK-LABEL: define dso_local void @test_svmla_single_za32_vg4x2(

clang/test/Sema/AArch64/arm_sme_streaming_only_sme_AND_sme-f8f16.c

@@ -52,7 +52,7 @@ void test(void) __arm_inout("za"){
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_lane_za16_vg2x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
-  svmla_single_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_single_za16_mf8_vg2x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
@@ -107,7 +107,7 @@ void test_streaming(void) __arm_streaming __arm_inout("za"){
   svmla_lane_za16_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, 2, fpm_t_val);
   svmla_lane_za16_vg2x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, 2, fpm_t_val);
   svmla_lane_za16_vg2x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
-  svmla_single_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_single_za16_mf8_vg2x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_single_za16_mf8_vg2x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_za16_mf8_vg2x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8x2_t_val, fpm_t_val);
@@ -168,7 +168,7 @@ void test_streaming_compatible(void) __arm_streaming_compatible __arm_inout("za"
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_lane_za16_vg2x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
-  svmla_single_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za16_mf8_vg2x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_single_za16_mf8_vg2x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}

clang/test/Sema/AArch64/arm_sme_streaming_only_sme_AND_sme-f8f32.c

@@ -52,7 +52,7 @@ void test(void) __arm_inout("za"){
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_lane_za32_vg4x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
-  svmla_single_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_single_za32_mf8_vg4x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
@@ -111,7 +111,7 @@ void test_streaming(void) __arm_streaming __arm_inout("za"){
   svmla_lane_za32_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, 2, fpm_t_val);
   svmla_lane_za32_vg4x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, 2, fpm_t_val);
   svmla_lane_za32_vg4x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
-  svmla_single_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_single_za32_mf8_vg4x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_single_za32_mf8_vg4x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, fpm_t_val);
   svmla_za32_mf8_vg4x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8x2_t_val, fpm_t_val);
@@ -174,7 +174,7 @@ void test_streaming_compatible(void) __arm_streaming_compatible __arm_inout("za"
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_lane_za32_vg4x4_fpm(uint32_t_val, svmfloat8x4_t_val, svmfloat8_t_val, 2, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
-  svmla_single_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
+  svmla_za32_mf8_vg4x1_fpm(uint32_t_val, svmfloat8_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}
   svmla_single_za32_mf8_vg4x2_fpm(uint32_t_val, svmfloat8x2_t_val, svmfloat8_t_val, fpm_t_val);
   // streaming-guard-error@+1 {{builtin can only be called from a streaming function}}

clang/test/Sema/aarch64-fp8-intrinsics/acle_sme2_fp8_mla.c

@@ -24,17 +24,17 @@ void test_svmla(uint32_t slice, svmfloat8_t zn, svmfloat8x2_t znx2, svmfloat8x4_
     // expected-error@+1 {{'svmla_lane_za32_mf8_vg4x4_fpm' needs target feature sme,sme-f8f32}}
     svmla_lane_za32_mf8_vg4x4_fpm(slice, znx4, zn, 0, fpmr);
 
-    // expected-error@+1 {{'svmla_single_za16_mf8_vg2x1_fpm' needs target feature sme,sme-f8f16}}
-    svmla_single_za16_mf8_vg2x1_fpm(slice, zn, zn, fpmr);
+    // expected-error@+1 {{'svmla_za16_mf8_vg2x1_fpm' needs target feature sme,sme-f8f16}}
+    svmla_za16_mf8_vg2x1_fpm(slice, zn, zn, fpmr);
 
     // expected-error@+1 {{'svmla_single_za16_mf8_vg2x2_fpm' needs target feature sme,sme-f8f16}}
     svmla_single_za16_mf8_vg2x2_fpm(slice, znx2, zn, fpmr);
 
     // expected-error@+1 {{'svmla_single_za16_mf8_vg2x4_fpm' needs target feature sme,sme-f8f16}}
     svmla_single_za16_mf8_vg2x4_fpm(slice, znx4, zn, fpmr);
 
-    // expected-error@+1 {{'svmla_single_za32_mf8_vg4x1_fpm' needs target feature sme,sme-f8f32}}
-    svmla_single_za32_mf8_vg4x1_fpm(slice, zn, zn, fpmr);
+    // expected-error@+1 {{'svmla_za32_mf8_vg4x1_fpm' needs target feature sme,sme-f8f32}}
+    svmla_za32_mf8_vg4x1_fpm(slice, zn, zn, fpmr);
 
     // expected-error@+1 {{'svmla_single_za32_mf8_vg4x2_fpm' needs target feature sme,sme-f8f32}}
     svmla_single_za32_mf8_vg4x2_fpm(slice, znx2, zn, fpmr);
@@ -53,4 +53,4 @@ void test_svmla(uint32_t slice, svmfloat8_t zn, svmfloat8x2_t znx2, svmfloat8x4_
 
     // expected-error@+1 {{'svmla_za32_mf8_vg4x4_fpm' needs target feature sme,sme-f8f32}}
     svmla_za32_mf8_vg4x4_fpm(slice, znx4, znx4, fpmr);
-}
+}