[AVX-512] Add scalar vfmsub/vfnmsub mask3 intrinsics

[craig.topper]

Summary

Clang's intrinsic header currently tries to negate the third operand of a vfmadd mask3 in order to create vfmsub, but this fails isel. This patch add scalar vfmsub mask3 that we can use instead to avoid the negate. This is consistent with the packed instructions.

[craig.topper]

Turns out we also need vfnmsub too. At least until we teach combineFMA to be called for FMSUB/FMSUB_RND.

include/llvm/IR/IntrinsicsX86.td

def int_x86_avx512_mask3_vfmadd_sd :
           llvm_i32_ty], [IntrNoMem]>;
 
   def int_x86_avx512_mask3_vfmadd_ss :
          GCCBuiltin<"__builtin_ia32_vfmaddss3_mask3">,
           Intrinsic<[llvm_v4f32_ty],
           [llvm_v4f32_ty, llvm_v4f32_ty, llvm_v4f32_ty,  llvm_i8_ty,
           llvm_i32_ty], [IntrNoMem]>;
 
+  def int_x86_avx512_mask3_vfmsub_sd :
+         GCCBuiltin<"__builtin_ia32_vfmsubsd3_mask3">,
+          Intrinsic<[llvm_v2f64_ty],
+          [llvm_v2f64_ty, llvm_v2f64_ty, llvm_v2f64_ty,  llvm_i8_ty,
+          llvm_i32_ty], [IntrNoMem]>;
+
+  def int_x86_avx512_mask3_vfmsub_ss :
+         GCCBuiltin<"__builtin_ia32_vfmsubss3_mask3">,
+          Intrinsic<[llvm_v4f32_ty],
+          [llvm_v4f32_ty, llvm_v4f32_ty, llvm_v4f32_ty,  llvm_i8_ty,
+          llvm_i32_ty], [IntrNoMem]>;
+
   def int_x86_avx512_mask3_vfmsub_pd_128 :
          GCCBuiltin<"__builtin_ia32_vfmsubpd128_mask3">,
           Intrinsic<[llvm_v2f64_ty],
           [llvm_v2f64_ty, llvm_v2f64_ty, llvm_v2f64_ty,  llvm_i8_ty],
           [IntrNoMem]>;
 
   def int_x86_avx512_mask3_vfmsub_pd_256 :
          GCCBuiltin<"__builtin_ia32_vfmsubpd256_mask3">,

lib/Target/X86/X86IntrinsicsInfo.h

   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_pd_128, FMA_OP_MASK3, X86ISD::FMSUB, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_pd_256, FMA_OP_MASK3, X86ISD::FMSUB, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_pd_512, FMA_OP_MASK3, X86ISD::FMSUB,
                      X86ISD::FMSUB_RND),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_ps_128, FMA_OP_MASK3, X86ISD::FMSUB, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_ps_256, FMA_OP_MASK3, X86ISD::FMSUB, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsub_ps_512, FMA_OP_MASK3, X86ISD::FMSUB,
                      X86ISD::FMSUB_RND),
+  X86_INTRINSIC_DATA(avx512_mask3_vfmsub_sd, FMA_OP_SCALAR_MASK3, X86ISD::FMSUB_RND, 0),
+  X86_INTRINSIC_DATA(avx512_mask3_vfmsub_ss, FMA_OP_SCALAR_MASK3, X86ISD::FMSUB_RND, 0),
 
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_pd_128, FMA_OP_MASK3, X86ISD::FMSUBADD, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_pd_256, FMA_OP_MASK3, X86ISD::FMSUBADD, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_pd_512, FMA_OP_MASK3, X86ISD::FMSUBADD,
                      X86ISD::FMSUBADD_RND),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_ps_128, FMA_OP_MASK3, X86ISD::FMSUBADD, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_ps_256, FMA_OP_MASK3, X86ISD::FMSUBADD, 0),
   X86_INTRINSIC_DATA(avx512_mask3_vfmsubadd_ps_512, FMA_OP_MASK3, X86ISD::FMSUBADD,

test/CodeGen/X86/avx512-intrinsics.ll

; CHECK-NEXT:    retq
   %res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
   %res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
   %res4 = fadd <4 x float> %res, %res1
   %res5 = fadd <4 x float> %res2, %res3
   %res6 = fadd <4 x float> %res4, %res5
   ret <4 x float> %res6
 }
 
+declare <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)
+
+define <2 x double>@test_int_x86_avx512_mask3_vfmsub_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3,i32 %x4 ){
+; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_sd:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    andl $1, %edi
+; CHECK-NEXT:    kmovw %edi, %k1
+; CHECK-NEXT:    vmovaps %xmm2, %xmm3
+; CHECK-NEXT:    vfmsub231sd %xmm1, %xmm0, %xmm3 {%k1}
+; CHECK-NEXT:    vmovaps %xmm1, %xmm4
+; CHECK-NEXT:    vfmsub213sd %xmm2, %xmm0, %xmm4
+; CHECK-NEXT:    vmovaps %xmm2, %xmm5
+; CHECK-NEXT:    vfmsub231sd {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
+; CHECK-NEXT:    vfmsub213sd {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT:    vaddpd %xmm3, %xmm4, %xmm0
+; CHECK-NEXT:    vaddpd %xmm5, %xmm1, %xmm1
+; CHECK-NEXT:    vaddpd %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %res = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
+  %res1 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
+  %res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
+  %res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
+  %res4 = fadd <2 x double> %res, %res1
+  %res5 = fadd <2 x double> %res2, %res3
+  %res6 = fadd <2 x double> %res4, %res5
+  ret <2 x double> %res6
+}
+
+declare <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
+
+define <4 x float>@test_int_x86_avx512_mask3_vfmsub_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3,i32 %x4 ){
+; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_ss:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    andl $1, %edi
+; CHECK-NEXT:    kmovw %edi, %k1
+; CHECK-NEXT:    vmovaps %xmm2, %xmm3
+; CHECK-NEXT:    vfmsub231ss %xmm1, %xmm0, %xmm3 {%k1}
+; CHECK-NEXT:    vmovaps %xmm1, %xmm4
+; CHECK-NEXT:    vfmsub213ss %xmm2, %xmm0, %xmm4
+; CHECK-NEXT:    vmovaps %xmm2, %xmm5
+; CHECK-NEXT:    vfmsub231ss {rz-sae}, %xmm1, %xmm0, %xmm5 {%k1}
+; CHECK-NEXT:    vfmsub213ss {rz-sae}, %xmm2, %xmm0, %xmm1
+; CHECK-NEXT:    vaddps %xmm3, %xmm4, %xmm0
+; CHECK-NEXT:    vaddps %xmm5, %xmm1, %xmm1
+; CHECK-NEXT:    vaddps %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %res = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
+  %res1 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
+  %res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
+  %res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
+  %res4 = fadd <4 x float> %res, %res1
+  %res5 = fadd <4 x float> %res2, %res3
+  %res6 = fadd <4 x float> %res4, %res5
+  ret <4 x float> %res6
+}
+
 define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss_rm(<4 x float> %x0, <4 x float> %x1, float *%ptr_b ,i8 %x3,i32 %x4) {
 ; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ss_rm:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    andl $1, %esi
 ; CHECK-NEXT:    kmovw %esi, %k1
 ; CHECK-NEXT:    vfmadd231ss (%rdi), %xmm0, %xmm1 {%k1}
 ; CHECK-NEXT:    vmovaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq