diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 2a3425a42607e..83bbe86392adf 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -17144,6 +17144,18 @@ SDValue DAGCombiner::visitFREM(SDNode *N) {
   if (SDValue NewSel = foldBinOpIntoSelect(N))
     return NewSel;
 
+  // (frem x, y) -> (fma (fneg (ftrunc (fdiv x, y))), y, x)
+  if (Flags.hasApproximateFuncs() && Flags.hasNoSignedZeros() &&
+      Flags.hasNoInfs() && !TLI.isOperationLegalOrCustom(ISD::FREM, VT) &&
+      TLI.isOperationLegalOrCustom(ISD::FTRUNC, VT) &&
+      TLI.isOperationLegalOrCustom(ISD::FMA, VT)) {
+    SDLoc Loc(N);
+    SDValue Div = DAG.getNode(ISD::FDIV, Loc, VT, N0, N1);
+    SDValue Trunc = DAG.getNode(ISD::FTRUNC, Loc, VT, Div);
+    return DAG.getNode(ISD::FMA, Loc, VT,
+                       DAG.getNode(ISD::FNEG, Loc, VT, Trunc), N1, N0);
+  }
+
   return SDValue();
 }
 
diff --git a/llvm/test/CodeGen/AArch64/frem.ll b/llvm/test/CodeGen/AArch64/frem.ll
index ed0f6c442ece1..e7021bbb05e29 100644
--- a/llvm/test/CodeGen/AArch64/frem.ll
+++ b/llvm/test/CodeGen/AArch64/frem.ll
@@ -1597,3 +1597,150 @@ entry:
   %c = frem <16 x half> %a, %b
   ret <16 x half> %c
 }
+
+define double @frem_f64_fast(double %a, double %b) {
+; CHECK-SD-LABEL: frem_f64_fast:
+; CHECK-SD:       // %bb.0: // %entry
+; CHECK-SD-NEXT:    fdiv d2, d0, d1
+; CHECK-SD-NEXT:    frintz d2, d2
+; CHECK-SD-NEXT:    fmsub d0, d2, d1, d0
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: frem_f64_fast:
+; CHECK-GI:       // %bb.0: // %entry
+; CHECK-GI-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-GI-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-GI-NEXT:    .cfi_offset w30, -16
+; CHECK-GI-NEXT:    bl fmod
+; CHECK-GI-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-GI-NEXT:    ret
+entry:
+  %c = frem fast double %a, %b
+  ret double %c
+}
+
+define float @frem_f32_fast(float %a, float %b) {
+; CHECK-SD-LABEL: frem_f32_fast:
+; CHECK-SD:       // %bb.0: // %entry
+; CHECK-SD-NEXT:    fdiv s2, s0, s1
+; CHECK-SD-NEXT:    frintz s2, s2
+; CHECK-SD-NEXT:    fmsub s0, s2, s1, s0
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: frem_f32_fast:
+; CHECK-GI:       // %bb.0: // %entry
+; CHECK-GI-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-GI-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-GI-NEXT:    .cfi_offset w30, -16
+; CHECK-GI-NEXT:    bl fmodf
+; CHECK-GI-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
+; CHECK-GI-NEXT:    ret
+entry:
+  %c = frem fast float %a, %b
+  ret float %c
+}
+
+define <2 x double> @frem_v2f64_fast(<2 x double> %a, <2 x double> %b) {
+; CHECK-SD-LABEL: frem_v2f64_fast:
+; CHECK-SD:       // %bb.0: // %entry
+; CHECK-SD-NEXT:    fdiv v2.2d, v0.2d, v1.2d
+; CHECK-SD-NEXT:    frintz v2.2d, v2.2d
+; CHECK-SD-NEXT:    fmls v0.2d, v1.2d, v2.2d
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: frem_v2f64_fast:
+; CHECK-GI:       // %bb.0: // %entry
+; CHECK-GI-NEXT:    sub sp, sp, #48
+; CHECK-GI-NEXT:    stp d9, d8, [sp, #16] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
+; CHECK-GI-NEXT:    .cfi_def_cfa_offset 48
+; CHECK-GI-NEXT:    .cfi_offset w30, -16
+; CHECK-GI-NEXT:    .cfi_offset b8, -24
+; CHECK-GI-NEXT:    .cfi_offset b9, -32
+; CHECK-GI-NEXT:    mov d8, v0.d[1]
+; CHECK-GI-NEXT:    mov d9, v1.d[1]
+; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 killed $q0
+; CHECK-GI-NEXT:    // kill: def $d1 killed $d1 killed $q1
+; CHECK-GI-NEXT:    bl fmod
+; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    fmov d1, d9
+; CHECK-GI-NEXT:    fmov d0, d8
+; CHECK-GI-NEXT:    bl fmod
+; CHECK-GI-NEXT:    ldr q1, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    // kill: def $d0 killed $d0 def $q0
+; CHECK-GI-NEXT:    ldp d9, d8, [sp, #16] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    ldr x30, [sp, #32] // 8-byte Folded Reload
+; CHECK-GI-NEXT:    mov v1.d[1], v0.d[0]
+; CHECK-GI-NEXT:    mov v0.16b, v1.16b
+; CHECK-GI-NEXT:    add sp, sp, #48
+; CHECK-GI-NEXT:    ret
+entry:
+  %c = frem fast <2 x double> %a, %b
+  ret <2 x double> %c
+}
+
+define <4 x float> @frem_v4f32_fast(<4 x float> %a, <4 x float> %b) {
+; CHECK-SD-LABEL: frem_v4f32_fast:
+; CHECK-SD:       // %bb.0: // %entry
+; CHECK-SD-NEXT:    fdiv v2.4s, v0.4s, v1.4s
+; CHECK-SD-NEXT:    frintz v2.4s, v2.4s
+; CHECK-SD-NEXT:    fmls v0.4s, v1.4s, v2.4s
+; CHECK-SD-NEXT:    ret
+;
+; CHECK-GI-LABEL: frem_v4f32_fast:
+; CHECK-GI:       // %bb.0: // %entry
+; CHECK-GI-NEXT:    sub sp, sp, #112
+; CHECK-GI-NEXT:    stp d13, d12, [sp, #48] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    stp d11, d10, [sp, #64] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    stp d9, d8, [sp, #80] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    str x30, [sp, #96] // 8-byte Folded Spill
+; CHECK-GI-NEXT:    .cfi_def_cfa_offset 112
+; CHECK-GI-NEXT:    .cfi_offset w30, -16
+; CHECK-GI-NEXT:    .cfi_offset b8, -24
+; CHECK-GI-NEXT:    .cfi_offset b9, -32
+; CHECK-GI-NEXT:    .cfi_offset b10, -40
+; CHECK-GI-NEXT:    .cfi_offset b11, -48
+; CHECK-GI-NEXT:    .cfi_offset b12, -56
+; CHECK-GI-NEXT:    .cfi_offset b13, -64
+; CHECK-GI-NEXT:    mov s8, v0.s[1]
+; CHECK-GI-NEXT:    mov s9, v0.s[2]
+; CHECK-GI-NEXT:    mov s10, v0.s[3]
+; CHECK-GI-NEXT:    mov s11, v1.s[1]
+; CHECK-GI-NEXT:    // kill: def $s0 killed $s0 killed $q0
+; CHECK-GI-NEXT:    mov s12, v1.s[2]
+; CHECK-GI-NEXT:    mov s13, v1.s[3]
+; CHECK-GI-NEXT:    // kill: def $s1 killed $s1 killed $q1
+; CHECK-GI-NEXT:    bl fmodf
+; CHECK-GI-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT:    str q0, [sp, #32] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    fmov s1, s11
+; CHECK-GI-NEXT:    fmov s0, s8
+; CHECK-GI-NEXT:    bl fmodf
+; CHECK-GI-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT:    str q0, [sp, #16] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    fmov s1, s12
+; CHECK-GI-NEXT:    fmov s0, s9
+; CHECK-GI-NEXT:    bl fmodf
+; CHECK-GI-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT:    str q0, [sp] // 16-byte Folded Spill
+; CHECK-GI-NEXT:    fmov s1, s13
+; CHECK-GI-NEXT:    fmov s0, s10
+; CHECK-GI-NEXT:    bl fmodf
+; CHECK-GI-NEXT:    ldp q2, q1, [sp, #16] // 32-byte Folded Reload
+; CHECK-GI-NEXT:    // kill: def $s0 killed $s0 def $q0
+; CHECK-GI-NEXT:    ldr x30, [sp, #96] // 8-byte Folded Reload
+; CHECK-GI-NEXT:    ldp d9, d8, [sp, #80] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    ldp d11, d10, [sp, #64] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    mov v1.s[1], v2.s[0]
+; CHECK-GI-NEXT:    ldr q2, [sp] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    ldp d13, d12, [sp, #48] // 16-byte Folded Reload
+; CHECK-GI-NEXT:    mov v1.s[2], v2.s[0]
+; CHECK-GI-NEXT:    mov v1.s[3], v0.s[0]
+; CHECK-GI-NEXT:    mov v0.16b, v1.16b
+; CHECK-GI-NEXT:    add sp, sp, #112
+; CHECK-GI-NEXT:    ret
+entry:
+  %c = frem fast <4 x float> %a, %b
+  ret <4 x float> %c
+}
diff --git a/llvm/test/CodeGen/PowerPC/frem.ll b/llvm/test/CodeGen/PowerPC/frem.ll
index 8cb68e60f7f9b..dff9c796289e9 100644
--- a/llvm/test/CodeGen/PowerPC/frem.ll
+++ b/llvm/test/CodeGen/PowerPC/frem.ll
@@ -4,16 +4,13 @@
 define float @frem32(float %a, float %b) {
 ; CHECK-LABEL: frem32:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    mflr 0
-; CHECK-NEXT:    stdu 1, -32(1)
-; CHECK-NEXT:    std 0, 48(1)
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
-; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    bl fmodf
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    addi 1, 1, 32
-; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:    xsresp 0, 2
+; CHECK-NEXT:    fmr 4, 1
+; CHECK-NEXT:    xsmulsp 3, 1, 0
+; CHECK-NEXT:    xsnmsubasp 4, 2, 3
+; CHECK-NEXT:    xsmaddasp 3, 0, 4
+; CHECK-NEXT:    xsrdpiz 0, 3
+; CHECK-NEXT:    xsnmsubasp 1, 0, 2
 ; CHECK-NEXT:    blr
 entry:
   %rem = frem fast float %a, %b
@@ -23,16 +20,17 @@ entry:
 define double @frem64(double %a, double %b) {
 ; CHECK-LABEL: frem64:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    mflr 0
-; CHECK-NEXT:    stdu 1, -32(1)
-; CHECK-NEXT:    std 0, 48(1)
-; CHECK-NEXT:    .cfi_def_cfa_offset 32
-; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    bl fmod
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    addi 1, 1, 32
-; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:    vspltisw 2, -1
+; CHECK-NEXT:    xsredp 0, 2
+; CHECK-NEXT:    fmr 4, 1
+; CHECK-NEXT:    xvcvsxwdp 3, 34
+; CHECK-NEXT:    xsmaddadp 3, 2, 0
+; CHECK-NEXT:    xsnmsubadp 0, 0, 3
+; CHECK-NEXT:    xsmuldp 3, 1, 0
+; CHECK-NEXT:    xsnmsubadp 4, 2, 3
+; CHECK-NEXT:    xsmaddadp 3, 0, 4
+; CHECK-NEXT:    xsrdpiz 0, 3
+; CHECK-NEXT:    xsnmsubadp 1, 0, 2
 ; CHECK-NEXT:    blr
 entry:
   %rem = frem fast double %a, %b
@@ -42,59 +40,13 @@ entry:
 define <4 x float> @frem4x32(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: frem4x32:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    mflr 0
-; CHECK-NEXT:    stdu 1, -96(1)
-; CHECK-NEXT:    std 0, 112(1)
-; CHECK-NEXT:    .cfi_def_cfa_offset 96
-; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    .cfi_offset v28, -64
-; CHECK-NEXT:    .cfi_offset v29, -48
-; CHECK-NEXT:    .cfi_offset v30, -32
-; CHECK-NEXT:    .cfi_offset v31, -16
-; CHECK-NEXT:    xxsldwi 0, 34, 34, 3
-; CHECK-NEXT:    stxv 60, 32(1) # 16-byte Folded Spill
-; CHECK-NEXT:    xscvspdpn 1, 0
-; CHECK-NEXT:    xxsldwi 0, 35, 35, 3
-; CHECK-NEXT:    stxv 61, 48(1) # 16-byte Folded Spill
-; CHECK-NEXT:    stxv 62, 64(1) # 16-byte Folded Spill
-; CHECK-NEXT:    stxv 63, 80(1) # 16-byte Folded Spill
-; CHECK-NEXT:    xscvspdpn 2, 0
-; CHECK-NEXT:    vmr 31, 3
-; CHECK-NEXT:    vmr 30, 2
-; CHECK-NEXT:    bl fmodf
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    xxsldwi 0, 62, 62, 1
-; CHECK-NEXT:    xscpsgndp 61, 1, 1
-; CHECK-NEXT:    xscvspdpn 1, 0
-; CHECK-NEXT:    xxsldwi 0, 63, 63, 1
-; CHECK-NEXT:    xscvspdpn 2, 0
-; CHECK-NEXT:    bl fmodf
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-NEXT:    xxmrghd 0, 1, 61
-; CHECK-NEXT:    xscvspdpn 1, 62
-; CHECK-NEXT:    xscvspdpn 2, 63
-; CHECK-NEXT:    xvcvdpsp 60, 0
-; CHECK-NEXT:    bl fmodf
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    xxswapd 0, 62
-; CHECK-NEXT:    xscpsgndp 61, 1, 1
-; CHECK-NEXT:    xscvspdpn 1, 0
-; CHECK-NEXT:    xxswapd 0, 63
-; CHECK-NEXT:    xscvspdpn 2, 0
-; CHECK-NEXT:    bl fmodf
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-NEXT:    xxmrghd 0, 61, 1
-; CHECK-NEXT:    lxv 63, 80(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 62, 64(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 61, 48(1) # 16-byte Folded Reload
-; CHECK-NEXT:    xvcvdpsp 34, 0
-; CHECK-NEXT:    vmrgew 2, 2, 28
-; CHECK-NEXT:    lxv 60, 32(1) # 16-byte Folded Reload
-; CHECK-NEXT:    addi 1, 1, 96
-; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:    xvresp 0, 35
+; CHECK-NEXT:    vmr 4, 2
+; CHECK-NEXT:    xvmulsp 1, 34, 0
+; CHECK-NEXT:    xvnmsubasp 36, 35, 1
+; CHECK-NEXT:    xvmaddasp 1, 0, 36
+; CHECK-NEXT:    xvrspiz 0, 1
+; CHECK-NEXT:    xvnmsubasp 34, 0, 35
 ; CHECK-NEXT:    blr
 entry:
   %rem = frem fast <4 x float> %a, %b
@@ -104,38 +56,18 @@ entry:
 define <2 x double> @frem2x64(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: frem2x64:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    mflr 0
-; CHECK-NEXT:    stdu 1, -80(1)
-; CHECK-NEXT:    std 0, 96(1)
-; CHECK-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-NEXT:    .cfi_offset lr, 16
-; CHECK-NEXT:    .cfi_offset v29, -48
-; CHECK-NEXT:    .cfi_offset v30, -32
-; CHECK-NEXT:    .cfi_offset v31, -16
-; CHECK-NEXT:    stxv 62, 48(1) # 16-byte Folded Spill
-; CHECK-NEXT:    stxv 63, 64(1) # 16-byte Folded Spill
-; CHECK-NEXT:    vmr 31, 3
-; CHECK-NEXT:    xscpsgndp 2, 63, 63
-; CHECK-NEXT:    vmr 30, 2
-; CHECK-NEXT:    xscpsgndp 1, 62, 62
-; CHECK-NEXT:    stxv 61, 32(1) # 16-byte Folded Spill
-; CHECK-NEXT:    bl fmod
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    xscpsgndp 61, 1, 1
-; CHECK-NEXT:    xxswapd 1, 62
-; CHECK-NEXT:    xxswapd 2, 63
-; CHECK-NEXT:    # kill: def $f1 killed $f1 killed $vsl1
-; CHECK-NEXT:    # kill: def $f2 killed $f2 killed $vsl2
-; CHECK-NEXT:    bl fmod
-; CHECK-NEXT:    nop
-; CHECK-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-NEXT:    xxmrghd 34, 61, 1
-; CHECK-NEXT:    lxv 63, 64(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 62, 48(1) # 16-byte Folded Reload
-; CHECK-NEXT:    lxv 61, 32(1) # 16-byte Folded Reload
-; CHECK-NEXT:    addi 1, 1, 80
-; CHECK-NEXT:    ld 0, 16(1)
-; CHECK-NEXT:    mtlr 0
+; CHECK-NEXT:    addis 3, 2, .LCPI3_0@toc@ha
+; CHECK-NEXT:    xvredp 0, 35
+; CHECK-NEXT:    vmr 4, 2
+; CHECK-NEXT:    addi 3, 3, .LCPI3_0@toc@l
+; CHECK-NEXT:    lxv 1, 0(3)
+; CHECK-NEXT:    xvmaddadp 1, 35, 0
+; CHECK-NEXT:    xvnmsubadp 0, 0, 1
+; CHECK-NEXT:    xvmuldp 1, 34, 0
+; CHECK-NEXT:    xvnmsubadp 36, 35, 1
+; CHECK-NEXT:    xvmaddadp 1, 0, 36
+; CHECK-NEXT:    xvrdpiz 0, 1
+; CHECK-NEXT:    xvnmsubadp 34, 0, 35
 ; CHECK-NEXT:    blr
 entry:
   %rem = frem fast <2 x double> %a, %b
diff --git a/llvm/test/CodeGen/X86/frem.ll b/llvm/test/CodeGen/X86/frem.ll
index d91d4289a5994..c2613dfa744f8 100644
--- a/llvm/test/CodeGen/X86/frem.ll
+++ b/llvm/test/CodeGen/X86/frem.ll
@@ -1448,3 +1448,135 @@ define void @frem_v4f80(<4 x x86_fp80> %a0, <4 x x86_fp80> %a1, ptr%p3) nounwind
   store <4 x x86_fp80> %frem, ptr%p3
   ret void
 }
+
+define void @frem_f32_fast(float %a0, float %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_f32_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vdivss %xmm1, %xmm0, %xmm2
+; CHECK-NEXT:    vroundss $11, %xmm2, %xmm2, %xmm2
+; CHECK-NEXT:    vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm0
+; CHECK-NEXT:    vmovss %xmm2, (%rdi)
+; CHECK-NEXT:    retq
+  %frem = frem fast float %a0, %a1
+  store float %frem, ptr%p3
+  ret void
+}
+
+define void @frem_f64_fast(double %a0, double %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_f64_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vdivsd %xmm1, %xmm0, %xmm2
+; CHECK-NEXT:    vroundsd $11, %xmm2, %xmm2, %xmm2
+; CHECK-NEXT:    vfnmadd213sd {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm0
+; CHECK-NEXT:    vmovsd %xmm2, (%rdi)
+; CHECK-NEXT:    retq
+  %frem = frem fast double %a0, %a1
+  store double %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v16f32_fast(<16 x float> %a0, <16 x float> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v16f32_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vrcpps %ymm3, %ymm4
+; CHECK-NEXT:    vmulps %ymm4, %ymm1, %ymm5
+; CHECK-NEXT:    vmovaps %ymm5, %ymm6
+; CHECK-NEXT:    vfmsub213ps {{.*#+}} ymm6 = (ymm3 * ymm6) - ymm1
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm6 = -(ymm4 * ymm6) + ymm5
+; CHECK-NEXT:    vrcpps %ymm2, %ymm4
+; CHECK-NEXT:    vmulps %ymm4, %ymm0, %ymm5
+; CHECK-NEXT:    vmovaps %ymm5, %ymm7
+; CHECK-NEXT:    vfmsub213ps {{.*#+}} ymm7 = (ymm2 * ymm7) - ymm0
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm7 = -(ymm4 * ymm7) + ymm5
+; CHECK-NEXT:    vroundps $11, %ymm7, %ymm4
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm4 = -(ymm2 * ymm4) + ymm0
+; CHECK-NEXT:    vroundps $11, %ymm6, %ymm0
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm1
+; CHECK-NEXT:    vmovaps %ymm0, 32(%rdi)
+; CHECK-NEXT:    vmovaps %ymm4, (%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %frem = frem fast <16 x float> %a0, %a1
+  store <16 x float> %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v8f32_fast(<8 x float> %a0, <8 x float> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v8f32_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vrcpps %ymm1, %ymm2
+; CHECK-NEXT:    vmulps %ymm2, %ymm0, %ymm3
+; CHECK-NEXT:    vmovaps %ymm3, %ymm4
+; CHECK-NEXT:    vfmsub213ps {{.*#+}} ymm4 = (ymm1 * ymm4) - ymm0
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm4 = -(ymm2 * ymm4) + ymm3
+; CHECK-NEXT:    vroundps $11, %ymm4, %ymm2
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} ymm2 = -(ymm1 * ymm2) + ymm0
+; CHECK-NEXT:    vmovaps %ymm2, (%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %frem = frem fast <8 x float> %a0, %a1
+  store <8 x float> %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v4f32_fast(<4 x float> %a0, <4 x float> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v4f32_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vrcpps %xmm1, %xmm2
+; CHECK-NEXT:    vmulps %xmm2, %xmm0, %xmm3
+; CHECK-NEXT:    vmovaps %xmm3, %xmm4
+; CHECK-NEXT:    vfmsub213ps {{.*#+}} xmm4 = (xmm1 * xmm4) - xmm0
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} xmm4 = -(xmm2 * xmm4) + xmm3
+; CHECK-NEXT:    vroundps $11, %xmm4, %xmm2
+; CHECK-NEXT:    vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm0
+; CHECK-NEXT:    vmovaps %xmm2, (%rdi)
+; CHECK-NEXT:    retq
+  %frem = frem fast <4 x float> %a0, %a1
+  store <4 x float> %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v8f64_fast(<8 x double> %a0, <8 x double> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v8f64_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vdivpd %ymm2, %ymm0, %ymm4
+; CHECK-NEXT:    vroundpd $11, %ymm4, %ymm4
+; CHECK-NEXT:    vfnmadd213pd {{.*#+}} ymm4 = -(ymm2 * ymm4) + ymm0
+; CHECK-NEXT:    vdivpd %ymm3, %ymm1, %ymm0
+; CHECK-NEXT:    vroundpd $11, %ymm0, %ymm0
+; CHECK-NEXT:    vfnmadd213pd {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm1
+; CHECK-NEXT:    vmovapd %ymm0, 32(%rdi)
+; CHECK-NEXT:    vmovapd %ymm4, (%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %frem = frem fast <8 x double> %a0, %a1
+  store <8 x double> %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v4f64_fast(<4 x double> %a0, <4 x double> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v4f64_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vdivpd %ymm1, %ymm0, %ymm2
+; CHECK-NEXT:    vroundpd $11, %ymm2, %ymm2
+; CHECK-NEXT:    vfnmadd213pd {{.*#+}} ymm2 = -(ymm1 * ymm2) + ymm0
+; CHECK-NEXT:    vmovapd %ymm2, (%rdi)
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %frem = frem fast <4 x double> %a0, %a1
+  store <4 x double> %frem, ptr%p3
+  ret void
+}
+
+define void @frem_v2f64_fast(<2 x double> %a0, <2 x double> %a1, ptr%p3) nounwind {
+; CHECK-LABEL: frem_v2f64_fast:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vdivpd %xmm1, %xmm0, %xmm2
+; CHECK-NEXT:    vroundpd $11, %xmm2, %xmm2
+; CHECK-NEXT:    vfnmadd213pd {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm0
+; CHECK-NEXT:    vmovapd %xmm2, (%rdi)
+; CHECK-NEXT:    retq
+  %frem = frem fast <2 x double> %a0, %a1
+  store <2 x double> %frem, ptr%p3
+  ret void
+}