; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -O3 -S | FileCheck %s
; RUN: opt < %s -passes="default<O3>" -S | FileCheck %s
; Test that IR is optimal after vectorization/unrolling/CSE/canonicalization.
; In particular, there should be no fdivs inside loops because that is expensive.
; TODO: There is a CSE opportunity to reduce the hoisted fdivs after vectorization/unrolling.
; PR46115 - https://llvm.org/PR46115
target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.15.0"
define void @vdiv(ptr %x, ptr %y, double %a, i32 %N) #0 {
; CHECK-LABEL: @vdiv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[X4:%.*]] = ptrtoint ptr [[X:%.*]] to i64
; CHECK-NEXT: [[Y5:%.*]] = ptrtoint ptr [[Y:%.*]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[N]] to i64
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 16
; CHECK-NEXT: [[TMP0:%.*]] = sub i64 [[X4]], [[Y5]]
; CHECK-NEXT: [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP0]], 128
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[MIN_ITERS_CHECK]], i1 true, i1 [[DIFF_CHECK]]
; CHECK-NEXT: br i1 [[OR_COND]], label [[FOR_BODY_PREHEADER9:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[WIDE_TRIP_COUNT]], 2147483632
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x double> poison, double [[A:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x double> [[BROADCAST_SPLATINSERT]], <4 x double> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP2:%.*]] = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP3:%.*]] = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP4:%.*]] = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[BROADCAST_SPLAT]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i64 32
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i64 64
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i64 96
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x double>, ptr [[TMP5]], align 8, !tbaa [[TBAA3:![0-9]+]]
; CHECK-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x double>, ptr [[TMP6]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[WIDE_LOAD7:%.*]] = load <4 x double>, ptr [[TMP7]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[WIDE_LOAD8:%.*]] = load <4 x double>, ptr [[TMP8]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP9:%.*]] = fmul fast <4 x double> [[WIDE_LOAD]], [[TMP1]]
; CHECK-NEXT: [[TMP10:%.*]] = fmul fast <4 x double> [[WIDE_LOAD6]], [[TMP2]]
; CHECK-NEXT: [[TMP11:%.*]] = fmul fast <4 x double> [[WIDE_LOAD7]], [[TMP3]]
; CHECK-NEXT: [[TMP12:%.*]] = fmul fast <4 x double> [[WIDE_LOAD8]], [[TMP4]]
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i64 32
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i64 64
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[TMP13]], i64 96
; CHECK-NEXT: store <4 x double> [[TMP9]], ptr [[TMP13]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: store <4 x double> [[TMP10]], ptr [[TMP14]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: store <4 x double> [[TMP11]], ptr [[TMP15]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: store <4 x double> [[TMP12]], ptr [[TMP16]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N_VEC]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END]], label [[FOR_BODY_PREHEADER9]]
; CHECK: for.body.preheader9:
; CHECK-NEXT: [[INDVARS_IV_PH:%.*]] = phi i64 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[N_VEC]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: [[XTRAITER:%.*]] = and i64 [[WIDE_TRIP_COUNT]], 7
; CHECK-NEXT: [[LCMP_MOD_NOT:%.*]] = icmp eq i64 [[XTRAITER]], 0
; CHECK-NEXT: br i1 [[LCMP_MOD_NOT]], label [[FOR_BODY_PROL_LOOPEXIT:%.*]], label [[FOR_BODY_PROL_PREHEADER:%.*]]
; CHECK: for.body.prol.preheader:
; CHECK-NEXT: [[TMP18:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: br label [[FOR_BODY_PROL:%.*]]
; CHECK: for.body.prol:
; CHECK-NEXT: [[INDVARS_IV_PROL:%.*]] = phi i64 [ [[INDVARS_IV_NEXT_PROL:%.*]], [[FOR_BODY_PROL]] ], [ [[INDVARS_IV_PH]], [[FOR_BODY_PROL_PREHEADER]] ]
; CHECK-NEXT: [[PROL_ITER:%.*]] = phi i64 [ [[PROL_ITER_NEXT:%.*]], [[FOR_BODY_PROL]] ], [ 0, [[FOR_BODY_PROL_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX_PROL:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_PROL]]
; CHECK-NEXT: [[T0_PROL:%.*]] = load double, ptr [[ARRAYIDX_PROL]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP19:%.*]] = fmul fast double [[T0_PROL]], [[TMP18]]
; CHECK-NEXT: [[ARRAYIDX2_PROL:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_PROL]]
; CHECK-NEXT: store double [[TMP19]], ptr [[ARRAYIDX2_PROL]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_PROL]] = add nuw nsw i64 [[INDVARS_IV_PROL]], 1
; CHECK-NEXT: [[PROL_ITER_NEXT]] = add i64 [[PROL_ITER]], 1
; CHECK-NEXT: [[PROL_ITER_CMP_NOT:%.*]] = icmp eq i64 [[PROL_ITER_NEXT]], [[XTRAITER]]
; CHECK-NEXT: br i1 [[PROL_ITER_CMP_NOT]], label [[FOR_BODY_PROL_LOOPEXIT]], label [[FOR_BODY_PROL]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: for.body.prol.loopexit:
; CHECK-NEXT: [[INDVARS_IV_UNR:%.*]] = phi i64 [ [[INDVARS_IV_PH]], [[FOR_BODY_PREHEADER9]] ], [ [[INDVARS_IV_NEXT_PROL]], [[FOR_BODY_PROL]] ]
; CHECK-NEXT: [[TMP20:%.*]] = sub nsw i64 [[INDVARS_IV_PH]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: [[TMP21:%.*]] = icmp ugt i64 [[TMP20]], -8
; CHECK-NEXT: br i1 [[TMP21]], label [[FOR_END]], label [[FOR_BODY_PREHEADER9_NEW:%.*]]
; CHECK: for.body.preheader9.new:
; CHECK-NEXT: [[TMP22:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP23:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP24:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP25:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP26:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP27:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP28:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: [[TMP29:%.*]] = fdiv fast double 1.000000e+00, [[A]]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_UNR]], [[FOR_BODY_PREHEADER9_NEW]] ], [ [[INDVARS_IV_NEXT_7:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[T0:%.*]] = load double, ptr [[ARRAYIDX]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP30:%.*]] = fmul fast double [[T0]], [[TMP22]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store double [[TMP30]], ptr [[ARRAYIDX2]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[T0_1:%.*]] = load double, ptr [[ARRAYIDX_1]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP31:%.*]] = fmul fast double [[T0_1]], [[TMP23]]
; CHECK-NEXT: [[ARRAYIDX2_1:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT]]
; CHECK-NEXT: store double [[TMP31]], ptr [[ARRAYIDX2_1]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_1:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_1]]
; CHECK-NEXT: [[T0_2:%.*]] = load double, ptr [[ARRAYIDX_2]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP32:%.*]] = fmul fast double [[T0_2]], [[TMP24]]
; CHECK-NEXT: [[ARRAYIDX2_2:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_1]]
; CHECK-NEXT: store double [[TMP32]], ptr [[ARRAYIDX2_2]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_2:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_2]]
; CHECK-NEXT: [[T0_3:%.*]] = load double, ptr [[ARRAYIDX_3]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP33:%.*]] = fmul fast double [[T0_3]], [[TMP25]]
; CHECK-NEXT: [[ARRAYIDX2_3:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_2]]
; CHECK-NEXT: store double [[TMP33]], ptr [[ARRAYIDX2_3]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_3:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 4
; CHECK-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_3]]
; CHECK-NEXT: [[T0_4:%.*]] = load double, ptr [[ARRAYIDX_4]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP34:%.*]] = fmul fast double [[T0_4]], [[TMP26]]
; CHECK-NEXT: [[ARRAYIDX2_4:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_3]]
; CHECK-NEXT: store double [[TMP34]], ptr [[ARRAYIDX2_4]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_4:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 5
; CHECK-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_4]]
; CHECK-NEXT: [[T0_5:%.*]] = load double, ptr [[ARRAYIDX_5]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP35:%.*]] = fmul fast double [[T0_5]], [[TMP27]]
; CHECK-NEXT: [[ARRAYIDX2_5:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_4]]
; CHECK-NEXT: store double [[TMP35]], ptr [[ARRAYIDX2_5]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_5:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 6
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_5]]
; CHECK-NEXT: [[T0_6:%.*]] = load double, ptr [[ARRAYIDX_6]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP36:%.*]] = fmul fast double [[T0_6]], [[TMP28]]
; CHECK-NEXT: [[ARRAYIDX2_6:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_5]]
; CHECK-NEXT: store double [[TMP36]], ptr [[ARRAYIDX2_6]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_6:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 7
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds double, ptr [[Y]], i64 [[INDVARS_IV_NEXT_6]]
; CHECK-NEXT: [[T0_7:%.*]] = load double, ptr [[ARRAYIDX_7]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[TMP37:%.*]] = fmul fast double [[T0_7]], [[TMP29]]
; CHECK-NEXT: [[ARRAYIDX2_7:%.*]] = getelementptr inbounds double, ptr [[X]], i64 [[INDVARS_IV_NEXT_6]]
; CHECK-NEXT: store double [[TMP37]], ptr [[ARRAYIDX2_7]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[INDVARS_IV_NEXT_7]] = add nuw nsw i64 [[INDVARS_IV]], 8
; CHECK-NEXT: [[EXITCOND_NOT_7:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT_7]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND_NOT_7]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%div = fdiv fast double 1.0, %a
br label %for.cond
for.cond:
%n.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %n.0, %N
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %n.0 to i64
%arrayidx = getelementptr inbounds double, ptr %y, i64 %idxprom
%t0 = load double, ptr %arrayidx, align 8, !tbaa !3
%mul = fmul fast double %t0, %div
%idxprom1 = sext i32 %n.0 to i64
%arrayidx2 = getelementptr inbounds double, ptr %x, i64 %idxprom1
store double %mul, ptr %arrayidx2, align 8, !tbaa !3
br label %for.inc
for.inc:
%inc = add nsw i32 %n.0, 1
br label %for.cond
for.end:
ret void
}
attributes #0 = { nounwind ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="all" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "no-infs-fp-math"="true" "no-jump-tables"="false" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="skylake-avx512" "target-features"="+adx,+aes,+avx,+avx2,+avx512bw,+avx512cd,+avx512dq,+avx512f,+avx512vl,+bmi,+bmi2,+clflushopt,+clwb,+cx16,+cx8,+f16c,+fma,+fsgsbase,+fxsr,+invpcid,+lzcnt,+mmx,+movbe,+pclmul,+pku,+popcnt,+prfchw,+rdrnd,+rdseed,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsavec,+xsaveopt,+xsaves" "unsafe-fp-math"="true" "use-soft-float"="false" }
!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"PIC Level", i32 2}
!2 = !{!"clang version 11.0.0 (https://github.com/llvm/llvm-project.git 45ebe38ffc40bb7221fc587bfb4481cf7f53ebbc)"}
!3 = !{!4, !4, i64 0}
!4 = !{!"double", !5, i64 0}
!5 = !{!"omnipotent char", !6, i64 0}
!6 = !{!"Simple C/C++ TBAA"}
Codebase Browser
llvm