[AArch64][llvm] Add support for vmmlaq_[f16,f32]_mf8 intrinsics

Add support for the following new intrinsics:
```
  float16x4_t vmmlaq_f16_mf8(float16x4_t, mfloat8x16_t, mfloat8x16_t, fpm_t);
  float32x2_t vmmlaq_f32_mf8(float32x2_t, mfloat8x16_t, mfloat8x16_t, fpm_t);
```

Author: jthackray

clang/include/clang/Basic/arm_neon.td

@@ -1896,6 +1896,14 @@ let ArchGuard = "defined(__aarch64__) || defined(__arm64ec__)", TargetGuard = "f
   def VFMLSL_LANEQ_HIGH : SOpInst<"vfmlsl_laneq_high", "(F>)(F>)F(FQ)I", "hQh", OP_FMLSL_LN_Hi>;
 }
 
+let ArchGuard = "defined(__aarch64__)", TargetGuard = "f8f16mm,neon" in {
+  def VMMLA_F16_MF8 : VInst<"vmmla_f16_mf8_fpm", "(>F)(>F)..V", "Qm">;
+}
+
+let ArchGuard = "defined(__aarch64__)", TargetGuard = "f8f32mm,neon" in {
+  def VMMLA_F32_MF8 : VInst<"vmmla_f32_mf8_fpm", "(>>F)(>>F)..V", "Qm">;
+}
+
 let TargetGuard = "i8mm,neon" in {
   def VMMLA   : SInst<"vmmla", "..(<<)(<<)", "QUiQi">;
   def VUSMMLA : SInst<"vusmmla", "..(<<U)(<<)", "Qi">;

clang/lib/CodeGen/TargetBuiltins/ARM.cpp

@@ -7793,6 +7793,14 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Int = Intrinsic::aarch64_neon_vluti4q_laneq_x2;
     return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vluti4q_laneq_x2");
   }
+  case NEON::BI__builtin_neon_vmmlaq_f16_mf8_fpm:
+    return EmitFP8NeonCall(Intrinsic::aarch64_neon_fmmla,
+                           {llvm::FixedVectorType::get(HalfTy, 8)}, Ops, E,
+                           "fmmla");
+  case NEON::BI__builtin_neon_vmmlaq_f32_mf8_fpm:
+    return EmitFP8NeonCall(Intrinsic::aarch64_neon_fmmla,
+                           {llvm::FixedVectorType::get(FloatTy, 4)}, Ops, E,
+                           "fmmla");
   case NEON::BI__builtin_neon_vcvt1_low_bf16_mf8_fpm:
     ExtractLow = true;
     [[fallthrough]];

clang/test/CodeGen/AArch64/v8.6a-neon-intrinsics.c

@@ -1,5 +1,5 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
-// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -target-feature +fullfp16 -target-feature +v8.6a -target-feature +i8mm \
+// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon -target-feature +fullfp16 -target-feature +v8.6a -target-feature +i8mm -target-feature +f8f16mm -target-feature +f8f32mm -target-feature +fp8 \
 // RUN: -disable-O0-optnone -emit-llvm -o - %s \
 // RUN: | opt -S -passes=mem2reg,sroa \
 // RUN: | FileCheck %s
@@ -32,6 +32,31 @@ uint32x4_t test_vmmlaq_u32(uint32x4_t r, uint8x16_t a, uint8x16_t b) {
   return vmmlaq_u32(r, a, b);
 }
 
+// CHECK-LABEL: define dso_local <8 x half> @test_vmmlaq_f16_mf8(
+// CHECK-SAME: <8 x half> noundef [[P0:%.*]], <16 x i8> [[P1:%.*]], <16 x i8> [[P2:%.*]], i64 noundef [[P3:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = bitcast <8 x half> [[P0]] to <8 x i16>
+// CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i16> [[TMP0]] to <16 x i8>
+// CHECK-NEXT:    call void @llvm.aarch64.set.fpmr(i64 [[P3]])
+// CHECK-NEXT:    [[FMMLA_I:%.*]] = bitcast <16 x i8> [[TMP1]] to <8 x half>
+// CHECK-NEXT:    [[FMMLA1_I:%.*]] = call <8 x half> @llvm.aarch64.neon.fmmla.v8f16(<8 x half> [[FMMLA_I]], <16 x i8> [[P1]], <16 x i8> [[P2]])
+// CHECK-NEXT:    ret <8 x half> [[FMMLA1_I]]
+//
+float16x8_t test_vmmlaq_f16_mf8(float16x8_t p0, mfloat8x16_t p1, mfloat8x16_t p2, fpm_t p3) {
+  return vmmlaq_f16_mf8_fpm(p0, p1, p2, p3);
+}
+
+// CHECK-LABEL: define dso_local <4 x float> @test_vmmlaq_f32_mf8(
+// CHECK-SAME: <4 x float> noundef [[P0:%.*]], <16 x i8> [[P1:%.*]], <16 x i8> [[P2:%.*]], i64 noundef [[P3:%.*]]) #[[ATTR0]] {
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    call void @llvm.aarch64.set.fpmr(i64 [[P3]])
+// CHECK-NEXT:    [[FMMLA_I:%.*]] = call <4 x float> @llvm.aarch64.neon.fmmla.v4f32(<4 x float> [[P0]], <16 x i8> [[P1]], <16 x i8> [[P2]])
+// CHECK-NEXT:    ret <4 x float> [[FMMLA_I]]
+//
+float32x4_t test_vmmlaq_f32_mf8(float32x4_t p0, mfloat8x16_t p1, mfloat8x16_t p2, fpm_t p3) {
+  return vmmlaq_f32_mf8_fpm(p0, p1, p2, p3);
+}
+
 // CHECK-LABEL: define dso_local <4 x i32> @test_vusmmlaq_s32(
 // CHECK-SAME: <4 x i32> noundef [[R:%.*]], <16 x i8> noundef [[A:%.*]], <16 x i8> noundef [[B:%.*]]) #[[ATTR0]] {
 // CHECK-NEXT:  [[ENTRY:.*:]]

llvm/include/llvm/IR/IntrinsicsAArch64.td

@@ -217,6 +217,11 @@ let TargetPrefix = "aarch64" in {  // All intrinsics start with "llvm.aarch64.".
     : DefaultAttrsIntrinsic<[llvm_v4f32_ty],
                 [llvm_v4f32_ty, llvm_v8bf16_ty, llvm_v8bf16_ty],
                 [IntrNoMem]>;
+
+  class AdvSIMD_MatMul_fpm_Intrinsic
+    : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
+                [LLVMMatchType<0>, llvm_v16i8_ty, llvm_v16i8_ty],
+                [IntrNoMem]>;
 }
 
 // Arithmetic ops
@@ -499,6 +504,7 @@ let TargetPrefix = "aarch64" in {
   def int_aarch64_neon_ummla : AdvSIMD_MatMul_Intrinsic;
   def int_aarch64_neon_smmla : AdvSIMD_MatMul_Intrinsic;
   def int_aarch64_neon_usmmla : AdvSIMD_MatMul_Intrinsic;
+  def int_aarch64_neon_fmmla : AdvSIMD_MatMul_fpm_Intrinsic;
   def int_aarch64_neon_usdot : AdvSIMD_Dot_Intrinsic;
   def int_aarch64_neon_bfdot : AdvSIMD_Dot_Intrinsic;
   def int_aarch64_neon_bfmmla