2ac5ebedea
SLP vectorizer emits extracts for externally used vectorized scalars and estimates the cost for each such extract. But in many cases these scalars are input for insertelement instructions, forming buildvector, and instead of extractelement/insertelement pair we can emit/cost estimate shuffle(s) cost and generate series of shuffles, which can be further optimized. Tested using test-suite (+SPEC2017), the tests passed, SLP was able to generate/vectorize more instructions in many cases and it allowed to reduce number of re-vectorization attempts (where we could try to vectorize buildector insertelements again and again). Differential Revision: https://reviews.llvm.org/D107966
73 lines
3.5 KiB
LLVM
73 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -mtriple=i386-linux-gnu -slp-vectorizer -S %s | FileCheck %s
|
|
|
|
%struct.a = type { [2 x i64] }
|
|
|
|
@a = external global %struct.a
|
|
@b = external global %struct.a
|
|
@c = external global %struct.a
|
|
|
|
define void @f(i1 %x) #0 {
|
|
; CHECK-LABEL: @f(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* bitcast (%struct.a* @a to <2 x i64>*), align 8
|
|
; CHECK-NEXT: br i1 [[X:%.*]], label [[WHILE_BODY_LR_PH:%.*]], label [[WHILE_END:%.*]]
|
|
; CHECK: while.body.lr.ph:
|
|
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x i64> [[TMP0]], i32 1
|
|
; CHECK-NEXT: [[ICMP_A1:%.*]] = icmp eq i64 [[TMP1]], 0
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load <2 x i64>, <2 x i64>* bitcast (%struct.a* @b to <2 x i64>*), align 8
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x i1> poison, i1 [[ICMP_A1]], i32 0
|
|
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x i1> [[TMP3]], i1 [[ICMP_A1]], i32 1
|
|
; CHECK-NEXT: [[TMP5:%.*]] = select <2 x i1> [[TMP4]], <2 x i64> [[TMP2]], <2 x i64> [[TMP0]]
|
|
; CHECK-NEXT: br label [[WHILE_END]]
|
|
; CHECK: while.end:
|
|
; CHECK-NEXT: [[TMP6:%.*]] = phi <2 x i64> [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP5]], [[WHILE_BODY_LR_PH]] ]
|
|
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* bitcast (%struct.a* @c to <2 x i64>*), align 8
|
|
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x i64> [[TMP6]], i32 0
|
|
; CHECK-NEXT: [[ICMP_D0:%.*]] = icmp eq i64 [[TMP8]], 0
|
|
; CHECK-NEXT: br i1 [[ICMP_D0]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
|
|
; CHECK: if.then:
|
|
; CHECK-NEXT: [[AND0_TMP:%.*]] = and i64 [[TMP8]], 8
|
|
; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x i64> poison, i64 [[AND0_TMP]], i32 0
|
|
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP9]], <2 x i64> [[TMP6]], <2 x i32> <i32 0, i32 3>
|
|
; CHECK-NEXT: [[TMP11:%.*]] = and <2 x i64> [[TMP10]], [[TMP7]]
|
|
; CHECK-NEXT: store <2 x i64> [[TMP11]], <2 x i64>* bitcast (%struct.a* @a to <2 x i64>*), align 8
|
|
; CHECK-NEXT: br label [[IF_END]]
|
|
; CHECK: if.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a0 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 0), align 8
|
|
%a1 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 1), align 8
|
|
br i1 %x, label %while.body.lr.ph, label %while.end
|
|
|
|
while.body.lr.ph:
|
|
%icmp.a1 = icmp eq i64 %a1, 0
|
|
%b0 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @b, i32 0, i32 0, i32 0), align 8
|
|
%b1 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @b, i32 0, i32 0, i32 1), align 8
|
|
%c0 = select i1 %icmp.a1, i64 %b0, i64 %a0
|
|
%c1 = select i1 %icmp.a1, i64 %b1, i64 %a1
|
|
br label %while.end
|
|
|
|
while.end:
|
|
%d0 = phi i64 [ %a0, %entry ], [ %c0, %while.body.lr.ph ]
|
|
%d1 = phi i64 [ %a1, %entry ], [ %c1, %while.body.lr.ph ]
|
|
%e0 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @c, i32 0, i32 0, i32 0), align 8
|
|
%e1 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @c, i32 0, i32 0, i32 1), align 8
|
|
%icmp.d0 = icmp eq i64 %d0, 0
|
|
br i1 %icmp.d0, label %if.end, label %if.then
|
|
|
|
if.then:
|
|
%and0.tmp = and i64 %d0, 8
|
|
%and0 = and i64 %and0.tmp, %e0
|
|
%and1 = and i64 %e1, %d1
|
|
store i64 %and0, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 0), align 8
|
|
store i64 %and1, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 1), align 8
|
|
br label %if.end
|
|
|
|
if.end:
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "target-features"="+sse2" }
|