maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64][SVE] Convert SRSHL to LSL when the fed from an ABS intrinsic 

Differential Revision: https://reviews.llvm.org/D125233
This commit is contained in:
Bradley Smith 2022-05-06 14:45:56 +00:00
parent 5bbf6ad5b6
commit 5f4541fefb
2 changed files with 188 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -1229,6 +1229,42 @@ static Optional<Instruction *> instCombineMaxMinNM(InstCombiner &IC,
return None;
}
static Optional<Instruction *> instCombineSVESrshl(InstCombiner &IC,
IntrinsicInst &II) {
IRBuilder<> Builder(&II);
Value *Pred = II.getOperand(0);
Value *Vec = II.getOperand(1);
Value *Shift = II.getOperand(2);
// Convert SRSHL into the simpler LSL intrinsic when fed by an ABS intrinsic.
Value *AbsPred, *MergedValue;
if (!match(Vec, m_Intrinsic<Intrinsic::aarch64_sve_sqabs>(
m_Value(MergedValue), m_Value(AbsPred), m_Value())) &&
!match(Vec, m_Intrinsic<Intrinsic::aarch64_sve_abs>(
m_Value(MergedValue), m_Value(AbsPred), m_Value())))
return None;
// Transform is valid if any of the following are true:
// * The ABS merge value is an undef or non-negative
// * The ABS predicate is all active
// * The ABS predicate and the SRSHL predicates are the same
if (!isa<UndefValue>(MergedValue) &&
!match(MergedValue, m_NonNegative()) &&
AbsPred != Pred && !isAllActivePredicate(AbsPred))
return None;
// Only valid when the shift amount is non-negative, otherwise the rounding
// behaviour of SRSHL cannot be ignored.
if (!match(Shift, m_NonNegative()))
return None;
auto LSL = Builder.CreateIntrinsic(Intrinsic::aarch64_sve_lsl, {II.getType()},
{Pred, Vec, Shift});
return IC.replaceInstUsesWith(II, LSL);
}
Optional<Instruction *>
AArch64TTIImpl::instCombineIntrinsic(InstCombiner &IC,
IntrinsicInst &II) const {
@ -1296,6 +1332,8 @@ AArch64TTIImpl::instCombineIntrinsic(InstCombiner &IC,
return instCombineSVESDIV(IC, II);
case Intrinsic::aarch64_sve_sel:
return instCombineSVESel(IC, II);
case Intrinsic::aarch64_sve_srshl:
return instCombineSVESrshl(IC, II);
}
return None;

150
llvm/test/Transforms/InstCombine/AArch64/sve-intrinsic-abs-srshl.ll Normal file
View File

@ -0,0 +1,150 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=instcombine < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
define <vscale x 8 x i16> @srshl_abs_undef_merge(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_undef_merge(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_zero_merge(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_zero_merge(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_positive_merge(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_positive_merge(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer), <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%absmerge = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %absmerge, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_all_active_pred(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_all_active_pred(
; CHECK-NEXT: [[PG:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i1> [[PG]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%pg = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_same_pred(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i1> %pg) #0 {
; CHECK-LABEL: @srshl_abs_same_pred(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_sqabs(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_sqabs(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqabs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.lsl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[TMP1]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.sqabs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_negative_merge(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_negative_merge(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 -1, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer), <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[SHR:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[SHR]]
;
%absmerge = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 -1)
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %absmerge, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_nonconst_merge(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_nonconst_merge(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[SHR:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[SHR]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_not_all_active_pred(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_not_all_active_pred(
; CHECK-NEXT: [[PG:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 8)
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i1> [[PG]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[SHR:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[SHR]]
;
%pg = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 8)
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_diff_pred(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_diff_pred(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> [[B:%.*]], <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[SHR:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[SHR]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> %b, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
define <vscale x 8 x i16> @srshl_abs_negative_shift(<vscale x 8 x i16> %a, <vscale x 8 x i1> %pg, <vscale x 8 x i1> %pg2) #0 {
; CHECK-LABEL: @srshl_abs_negative_shift(
; CHECK-NEXT: [[ABS:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x i16> [[A:%.*]])
; CHECK-NEXT: [[SHR:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> [[PG2:%.*]], <vscale x 8 x i16> [[ABS]], <vscale x 8 x i16> shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> poison, i16 -2, i32 0), <vscale x 8 x i16> poison, <vscale x 8 x i32> zeroinitializer))
; CHECK-NEXT: ret <vscale x 8 x i16> [[SHR]]
;
%abs = tail call <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> %pg, <vscale x 8 x i16> %a)
%splat = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 -2)
%shr = tail call <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1> %pg2, <vscale x 8 x i16> %abs, <vscale x 8 x i16> %splat)
ret <vscale x 8 x i16> %shr
}
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 immarg)
declare <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16)
declare <vscale x 8 x i16> @llvm.aarch64.sve.abs.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x i16>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.sqabs.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, <vscale x 8 x i16>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.srshl.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
attributes #0 = { "target-features"="+sve,+sve2" }