[LoopVectorize] Loop vectorization for minimum and maximum

[tlively]

Summary

Depends on D52766.

[hsaito]

LGTM

lib/Analysis/VectorUtils.cpp

bool llvm::isTriviallyVectorizable(Intrinsic::ID ID) {
   case Intrinsic::exp:
   case Intrinsic::exp2:
   case Intrinsic::log:
   case Intrinsic::log10:
   case Intrinsic::log2:
   case Intrinsic::fabs:
   case Intrinsic::minnum:
   case Intrinsic::maxnum:
+  case Intrinsic::minimum:
+  case Intrinsic::maximum:
   case Intrinsic::copysign:
   case Intrinsic::floor:
   case Intrinsic::ceil:
   case Intrinsic::trunc:
   case Intrinsic::rint:
   case Intrinsic::nearbyint:
   case Intrinsic::round:
   case Intrinsic::bswap:

test/Transforms/LoopVectorize/intrinsic.ll

for.body:                                         ; preds = %entry, %for.body
   %indvars.iv.next = add i64 %indvars.iv, 1
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, %n
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body, %entry
   ret void
 }
+
+declare float @llvm.minimum.f32(float, float) nounwind readnone
+
+;CHECK-LABEL: @minimum_f32(
+;CHECK: llvm.minimum.v4f32
+;CHECK: ret void
+define void @minimum_f32(i32 %n, float* noalias %y, float* noalias %x, float* noalias %z) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
+  %0 = load float, float* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds float, float* %z, i64 %indvars.iv
+  %1 = load float, float* %arrayidx2, align 4
+  %call = tail call float @llvm.minimum.f32(float %0, float %1) nounwind readnone
+  %arrayidx4 = getelementptr inbounds float, float* %x, i64 %indvars.iv
+  store float %call, float* %arrayidx4, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+declare float @llvm.maximum.f32(float, float) nounwind readnone
+
+;CHECK-LABEL: @maximum_f32(
+;CHECK: llvm.maximum.v4f32
+;CHECK: ret void
+define void @maximum_f32(i32 %n, float* noalias %y, float* noalias %x, float* noalias %z) nounwind uwtable {
+entry:
+  %cmp9 = icmp sgt i32 %n, 0
+  br i1 %cmp9, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
+  %0 = load float, float* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds float, float* %z, i64 %indvars.iv
+  %1 = load float, float* %arrayidx2, align 4
+  %call = tail call float @llvm.maximum.f32(float %0, float %1) nounwind readnone
+  %arrayidx4 = getelementptr inbounds float, float* %x, i64 %indvars.iv
+  store float %call, float* %arrayidx4, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}

test/Transforms/Scalarizer/intrinsics.ll

 ; RUN: opt -S -scalarizer %s | FileCheck %s
 
 ; Unary fp
 declare <2 x float> @llvm.sqrt.v2f32(<2 x float>)
 
 ; Binary fp
 declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>)
+declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>)
+declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)
 
 ; Ternary fp
 declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>)
 
 ; Binary int
 declare <2 x i32> @llvm.bswap.v2i32(<2 x i32>)
 
 ; Unary int plus constant scalar operand

 ; CHECK: %minnum.upto0 = insertelement <2 x float> undef, float %minnum.i0, i32 0
 ; CHECK: %minnum = insertelement <2 x float> %minnum.upto0, float %minnum.i1, i32 1
 ; CHECK: ret <2 x float> %minnum
 define <2 x float> @scalarize_minnum_v2f32(<2 x float> %x, <2 x float> %y) #0 {
   %minnum = call <2 x float> @llvm.minnum.v2f32(<2 x float> %x, <2 x float> %y)
   ret <2 x float> %minnum
 }
 
+; CHECK-LABEL: @scalarize_minimum_v2f32(
+; CHECK: %minimum.i0 = call float @llvm.minimum.f32(float %x.i0, float %y.i0)
+; CHECK: %minimum.i1 = call float @llvm.minimum.f32(float %x.i1, float %y.i1)
+; CHECK: %minimum.upto0 = insertelement <2 x float> undef, float %minimum.i0, i32 0
+; CHECK: %minimum = insertelement <2 x float> %minimum.upto0, float %minimum.i1, i32 1
+; CHECK: ret <2 x float> %minimum
+define <2 x float> @scalarize_minimum_v2f32(<2 x float> %x, <2 x float> %y) #0 {
+  %minimum = call <2 x float> @llvm.minimum.v2f32(<2 x float> %x, <2 x float> %y)
+  ret <2 x float> %minimum
+}
+
+; CHECK-LABEL: @scalarize_maximum_v2f32(
+; CHECK: %maximum.i0 = call float @llvm.maximum.f32(float %x.i0, float %y.i0)
+; CHECK: %maximum.i1 = call float @llvm.maximum.f32(float %x.i1, float %y.i1)
+; CHECK: %maximum.upto0 = insertelement <2 x float> undef, float %maximum.i0, i32 0
+; CHECK: %maximum = insertelement <2 x float> %maximum.upto0, float %maximum.i1, i32 1
+; CHECK: ret <2 x float> %maximum
+define <2 x float> @scalarize_maximum_v2f32(<2 x float> %x, <2 x float> %y) #0 {
+  %maximum = call <2 x float> @llvm.maximum.v2f32(<2 x float> %x, <2 x float> %y)
+  ret <2 x float> %maximum
+}
+
 ; CHECK-LABEL: @scalarize_fma_v2f32(
 ; CHECK: %fma.i0 = call float @llvm.fma.f32(float %x.i0, float %y.i0, float %z.i0)
 ; CHECK: %fma.i1 = call float @llvm.fma.f32(float %x.i1, float %y.i1, float %z.i1)
 ; CHECK: %fma.upto0 = insertelement <2 x float> undef, float %fma.i0, i32 0
 ; CHECK: %fma = insertelement <2 x float> %fma.upto0, float %fma.i1, i32 1
 ; CHECK: ret <2 x float> %fma
 define <2 x float> @scalarize_fma_v2f32(<2 x float> %x, <2 x float> %y, <2 x float> %z) #0 {
   %fma = call <2 x float> @llvm.fma.v2f32(<2 x float> %x, <2 x float> %y, <2 x float> %z)