4a8e6ed2f7
This patch makes SLP and LV emit operations with initial vectors set to poison constant instead of undef. This is a part of efforts for using poison vector instead of undef to represent "doesn't care" vector. The goal is to make nice shufflevector optimizations valid that is currently incorrect due to the tricky interaction between undef and poison (see https://bugs.llvm.org/show_bug.cgi?id=44185 ). Reviewed By: fhahn Differential Revision: https://reviews.llvm.org/D94061
82 lines
4.2 KiB
LLVM
82 lines
4.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -basic-aa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.7.0"
|
|
|
|
@.str = private unnamed_addr constant [6 x i8] c"bingo\00", align 1
|
|
|
|
; Uses inside the tree must be scheduled after the corresponding tree bundle.
|
|
define void @in_tree_user(double* nocapture %A, i32 %n) {
|
|
; CHECK-LABEL: @in_tree_user(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[N:%.*]] to double
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[CONV]], i32 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[CONV]], i32 1
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shl nsw i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 [[TMP2]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
|
|
; CHECK-NEXT: [[TMP4:%.*]] = load <2 x double>, <2 x double>* [[TMP3]], align 8
|
|
; CHECK-NEXT: [[TMP5:%.*]] = fmul <2 x double> [[TMP1]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP6:%.*]] = fmul <2 x double> [[TMP5]], <double 7.000000e+00, double 4.000000e+00>
|
|
; CHECK-NEXT: [[TMP7:%.*]] = fadd <2 x double> [[TMP6]], <double 5.000000e+00, double 9.000000e+00>
|
|
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[TMP7]], i32 0
|
|
; CHECK-NEXT: [[INTREEUSER:%.*]] = fadd double [[TMP8]], [[TMP8]]
|
|
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x double> [[TMP7]], i32 1
|
|
; CHECK-NEXT: [[CMP11:%.*]] = fcmp ogt double [[TMP8]], [[TMP9]]
|
|
; CHECK-NEXT: br i1 [[CMP11]], label [[IF_THEN:%.*]], label [[FOR_INC]]
|
|
; CHECK: if.then:
|
|
; CHECK-NEXT: [[CALL:%.*]] = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
|
|
; CHECK-NEXT: br label [[FOR_INC]]
|
|
; CHECK: for.inc:
|
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 100
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: store double [[INTREEUSER]], double* [[A]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%conv = sitofp i32 %n to double
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.inc, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
|
|
%0 = shl nsw i64 %indvars.iv, 1
|
|
%arrayidx = getelementptr inbounds double, double* %A, i64 %0
|
|
%1 = load double, double* %arrayidx, align 8
|
|
%mul1 = fmul double %conv, %1
|
|
%mul2 = fmul double %mul1, 7.000000e+00
|
|
%add = fadd double %mul2, 5.000000e+00
|
|
%InTreeUser = fadd double %add, %add ; <------------------ In tree user.
|
|
%2 = or i64 %0, 1
|
|
%arrayidx6 = getelementptr inbounds double, double* %A, i64 %2
|
|
%3 = load double, double* %arrayidx6, align 8
|
|
%mul8 = fmul double %conv, %3
|
|
%mul9 = fmul double %mul8, 4.000000e+00
|
|
%add10 = fadd double %mul9, 9.000000e+00
|
|
%cmp11 = fcmp ogt double %add, %add10
|
|
br i1 %cmp11, label %if.then, label %for.inc
|
|
|
|
if.then: ; preds = %for.body
|
|
%call = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
|
|
br label %for.inc
|
|
|
|
for.inc: ; preds = %for.body, %if.then
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 100
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.inc
|
|
store double %InTreeUser, double* %A, align 8 ; Avoid dead code elimination of the InTreeUser.
|
|
ret void
|
|
}
|
|
|
|
declare i32 @printf(i8* nocapture, ...)
|
|
|