caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ef2cdfe393d01cd4935c806387ac912b5a2c8ced
clang-p2996/llvm/test/Transforms/PhaseOrdering/X86/vector-reductions.ll
Roman Lebedev d7378259aa [SimplifyCFG] SimplifyCondBranchToTwoReturns(): really only deal with different ret blocks 
This function is called when some predecessor of an empty return block
ends with a conditional branch, with both successors being empty ret blocks.

Now, because of the way SimplifyCFG works, it might happen to simplify
one of the blocks in a way that makes a conditional branch
into an unconditional one, since it's destinations are now identical,
but it might not have actually simplified said conditional branch
into an unconditional one yet.

So, we have to check that ourselves first,
especially now that SimplifyCFG aggressively tail-merges
all ret and resume blocks.

Even if it was an unconditional branch already,
`SimplifyCFGOpt::simplifyReturn()` doesn't call `FoldReturnIntoUncondBranch()`
by default.
2021-07-23 00:36:59 +03:00

339 lines
12 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -O2 -S -mattr=avx < %s | FileCheck %s
; RUN: opt -passes='default<O2>' -S -mattr=avx < %s | FileCheck %s
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define i32 @ext_ext_or_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @ext_ext_or_reduction_v4i32(
; CHECK-NEXT: [[Z:%.*]] = and <4 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> [[Z]])
; CHECK-NEXT: ret i32 [[TMP1]]
;
%z = and <4 x i32> %x, %y
%z0 = extractelement <4 x i32> %z, i32 0
%z1 = extractelement <4 x i32> %z, i32 1
%z01 = or i32 %z0, %z1
%z2 = extractelement <4 x i32> %z, i32 2
%z012 = or i32 %z01, %z2
%z3 = extractelement <4 x i32> %z, i32 3
%z0123 = or i32 %z3, %z012
ret i32 %z0123
}
define i32 @ext_ext_partial_add_reduction_v4i32(<4 x i32> %x) {
; CHECK-LABEL: @ext_ext_partial_add_reduction_v4i32(
; CHECK-NEXT: [[SHIFT:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> poison, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[SHIFT]], [[X]]
; CHECK-NEXT: [[SHIFT1:%.*]] = shufflevector <4 x i32> [[X]], <4 x i32> poison, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[TMP1]], [[SHIFT1]]
; CHECK-NEXT: [[X210:%.*]] = extractelement <4 x i32> [[TMP2]], i64 0
; CHECK-NEXT: ret i32 [[X210]]
;
%x0 = extractelement <4 x i32> %x, i32 0
%x1 = extractelement <4 x i32> %x, i32 1
%x10 = add i32 %x1, %x0
%x2 = extractelement <4 x i32> %x, i32 2
%x210 = add i32 %x2, %x10
ret i32 %x210
}
define i32 @ext_ext_partial_add_reduction_and_extra_add_v4i32(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @ext_ext_partial_add_reduction_and_extra_add_v4i32(
; CHECK-NEXT: [[SHIFT:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> poison, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[SHIFT]], [[Y:%.*]]
; CHECK-NEXT: [[SHIFT1:%.*]] = shufflevector <4 x i32> [[Y]], <4 x i32> poison, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[TMP1]], [[SHIFT1]]
; CHECK-NEXT: [[SHIFT2:%.*]] = shufflevector <4 x i32> [[Y]], <4 x i32> poison, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP3:%.*]] = add <4 x i32> [[TMP2]], [[SHIFT2]]
; CHECK-NEXT: [[X2Y210:%.*]] = extractelement <4 x i32> [[TMP3]], i32 0
; CHECK-NEXT: ret i32 [[X2Y210]]
;
%y0 = extractelement <4 x i32> %y, i32 0
%y1 = extractelement <4 x i32> %y, i32 1
%y10 = add i32 %y1, %y0
%y2 = extractelement <4 x i32> %y, i32 2
%y210 = add i32 %y2, %y10
%x2 = extractelement <4 x i32> %x, i32 2
%x2y210 = add i32 %x2, %y210
ret i32 %x2y210
}
; PR43953 - https://bugs.llvm.org/show_bug.cgi?id=43953
; We want to end up with a single reduction on the next 4 tests.
define i32 @TestVectorsEqual(i32* noalias %Vec0, i32* noalias %Vec1, i32 %Tolerance) {
; CHECK-LABEL: @TestVectorsEqual(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[VEC0:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[VEC1:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = sub nsw <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i32> @llvm.abs.v4i32(<4 x i32> [[TMP4]], i1 true)
; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT: [[CMP5_NOT:%.*]] = icmp sle i32 [[TMP6]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND6:%.*]] = zext i1 [[CMP5_NOT]] to i32
; CHECK-NEXT: ret i32 [[COND6]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %Vec0, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds i32, i32* %Vec1, i64 %idxprom1
%1 = load i32, i32* %arrayidx2, align 4
%sub = sub nsw i32 %0, %1
%cmp3 = icmp sge i32 %sub, 0
br i1 %cmp3, label %cond.true, label %cond.false
cond.true:
br label %cond.end
cond.false:
%sub4 = sub nsw i32 0, %sub
br label %cond.end
cond.end:
%cond = phi i32 [ %sub, %cond.true ], [ %sub4, %cond.false ]
%add = add nsw i32 %sum.0, %cond
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp5 = icmp sle i32 %sum.0, %Tolerance
%2 = zext i1 %cmp5 to i64
%cond6 = select i1 %cmp5, i32 1, i32 0
ret i32 %cond6
}
define i32 @TestVectorsEqual_alt(i32* noalias %Vec0, i32* noalias %Vec1, i32 %Tolerance) {
; CHECK-LABEL: @TestVectorsEqual_alt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[VEC0:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[VEC1:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = sub <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP4]])
; CHECK-NEXT: [[CMP3_NOT:%.*]] = icmp ule i32 [[TMP5]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND:%.*]] = zext i1 [[CMP3_NOT]] to i32
; CHECK-NEXT: ret i32 [[COND]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %Vec0, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds i32, i32* %Vec1, i64 %idxprom1
%1 = load i32, i32* %arrayidx2, align 4
%sub = sub i32 %0, %1
%add = add i32 %sum.0, %sub
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp3 = icmp ule i32 %sum.0, %Tolerance
%2 = zext i1 %cmp3 to i64
%cond = select i1 %cmp3, i32 1, i32 0
ret i32 %cond
}
define i32 @TestVectorsEqualFP(float* noalias %Vec0, float* noalias %Vec1, float %Tolerance) {
; CHECK-LABEL: @TestVectorsEqualFP(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[VEC0:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[VEC1:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fsub fast <4 x float> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP5]])
; CHECK-NEXT: [[CMP4:%.*]] = fcmp fast ole float [[TMP6]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND5:%.*]] = zext i1 [[CMP4]] to i32
; CHECK-NEXT: ret i32 [[COND5]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi float [ 0.000000e+00, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds float, float* %Vec0, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds float, float* %Vec1, i64 %idxprom1
%1 = load float, float* %arrayidx2, align 4
%sub = fsub fast float %0, %1
%cmp3 = fcmp fast oge float %sub, 0.000000e+00
br i1 %cmp3, label %cond.true, label %cond.false
cond.true:
br label %cond.end
cond.false:
%fneg = fneg fast float %sub
br label %cond.end
cond.end:
%cond = phi fast float [ %sub, %cond.true ], [ %fneg, %cond.false ]
%add = fadd fast float %sum.0, %cond
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp4 = fcmp fast ole float %sum.0, %Tolerance
%2 = zext i1 %cmp4 to i64
%cond5 = select i1 %cmp4, i32 1, i32 0
ret i32 %cond5
}
define i32 @TestVectorsEqualFP_alt(float* noalias %Vec0, float* noalias %Vec1, float %Tolerance) {
; CHECK-LABEL: @TestVectorsEqualFP_alt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[VEC0:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[VEC1:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fsub fast <4 x float> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP4]])
; CHECK-NEXT: [[CMP3:%.*]] = fcmp fast ole float [[TMP5]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND:%.*]] = zext i1 [[CMP3]] to i32
; CHECK-NEXT: ret i32 [[COND]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi float [ 0.000000e+00, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds float, float* %Vec0, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds float, float* %Vec1, i64 %idxprom1
%1 = load float, float* %arrayidx2, align 4
%sub = fsub fast float %0, %1
%add = fadd fast float %sum.0, %sub
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp3 = fcmp fast ole float %sum.0, %Tolerance
%2 = zext i1 %cmp3 to i64
%cond = select i1 %cmp3, i32 1, i32 0
ret i32 %cond
}
; PR43745 - https://bugs.llvm.org/show_bug.cgi?id=43745
; FIXME: this should be vectorized
define i1 @cmp_lt_gt(double %a, double %b, double %c) {
; CHECK-LABEL: @cmp_lt_gt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[FNEG:%.*]] = fneg double [[B:%.*]]
; CHECK-NEXT: [[ADD:%.*]] = fsub double [[C:%.*]], [[B]]
; CHECK-NEXT: [[MUL:%.*]] = fmul double [[A:%.*]], 2.000000e+00
; CHECK-NEXT: [[DIV:%.*]] = fdiv double [[ADD]], [[MUL]]
; CHECK-NEXT: [[SUB:%.*]] = fsub double [[FNEG]], [[C]]
; CHECK-NEXT: [[DIV3:%.*]] = fdiv double [[SUB]], [[MUL]]
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt double [[DIV]], 0x3EB0C6F7A0B5ED8D
; CHECK-NEXT: [[CMP4:%.*]] = fcmp olt double [[DIV3]], 0x3EB0C6F7A0B5ED8D
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP]], i1 [[CMP4]], i1 false
; CHECK-NEXT: br i1 [[OR_COND]], label [[CLEANUP:%.*]], label [[LOR_LHS_FALSE:%.*]]
; CHECK: lor.lhs.false:
; CHECK-NEXT: [[CMP5:%.*]] = fcmp ule double [[DIV]], 1.000000e+00
; CHECK-NEXT: [[CMP7:%.*]] = fcmp ule double [[DIV3]], 1.000000e+00
; CHECK-NEXT: [[OR_COND1:%.*]] = select i1 [[CMP5]], i1 true, i1 [[CMP7]]
; CHECK-NEXT: br label [[CLEANUP]]
; CHECK: cleanup:
; CHECK-NEXT: [[RETVAL_0:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[OR_COND1]], [[LOR_LHS_FALSE]] ]
; CHECK-NEXT: ret i1 [[RETVAL_0]]
;
entry:
%fneg = fneg double %b
%add = fadd double %fneg, %c
%mul = fmul double 2.0, %a
%div = fdiv double %add, %mul
%fneg1 = fneg double %b
%sub = fsub double %fneg1, %c
%mul2 = fmul double 2.0, %a
%div3 = fdiv double %sub, %mul2
%cmp = fcmp olt double %div, 0x3EB0C6F7A0B5ED8D
br i1 %cmp, label %land.lhs.true, label %lor.lhs.false
land.lhs.true:
%cmp4 = fcmp olt double %div3, 0x3EB0C6F7A0B5ED8D
br i1 %cmp4, label %if.then, label %lor.lhs.false
lor.lhs.false:
%cmp5 = fcmp ogt double %div, 1.0
br i1 %cmp5, label %land.lhs.true6, label %if.end
land.lhs.true6:
%cmp7 = fcmp ogt double %div3, 1.0
br i1 %cmp7, label %if.then, label %if.end
if.then:
br label %cleanup
if.end:
br label %cleanup
cleanup:
%retval.0 = phi i1 [ false, %if.then ], [ true, %if.end ]
ret i1 %retval.0
}
Reference in New Issue View Git Blame Copy Permalink