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

[InstCombine] fold icmp slt/sgt of offset value with constant 

This follows up patches for the unsigned siblings:
0c400e8953
c7b658aeb5

We are translating an offset signed compare to its
unsigned equivalent when one end of the range is
at the limit (zero or unsigned max).

(X + C2) >s C --> X <u (SMAX - C) (if C == C2 - 1)
(X + C2) <s C --> X >u (C ^ SMAX) (if C == C2)

This probably does not show up much in IR derived
from C/C++ source because that would likely have
'nsw', and we have folds for that already.

As with the previous unsigned transforms, the folds
could be generalized to handle non-constant patterns:

https://alive2.llvm.org/ce/z/Y8Xrrm

  ; sgt
  define i1 @src(i8 %a, i8 %c) {
    %c2 = add i8 %c, 1
    %t = add i8 %a, %c2
    %ov = icmp sgt i8 %t, %c
    ret i1 %ov
  }

  define i1 @tgt(i8 %a, i8 %c) {
    %c_off = sub i8 127, %c ; SMAX
    %ov = icmp ult i8 %a, %c_off
    ret i1 %ov
  }

https://alive2.llvm.org/ce/z/c8uhnk

  ; slt
  define i1 @src(i8 %a, i8 %c) {
    %t = add i8 %a, %c
    %ov = icmp slt i8 %t, %c
    ret i1 %ov
  }

  define i1 @tgt(i8 %a, i8 %c) {
    %c_offnot = xor i8 %c, 127 ; SMAX
    %ov = icmp ugt i8 %a, %c_offnot
    ret i1 %ov
  }
This commit is contained in:
Sanjay Patel 2021-07-05 09:57:39 -04:00
parent 32dd914f71
commit 40b752d28d
2 changed files with 24 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
View File

@ -2636,20 +2636,27 @@ Instruction *InstCombinerImpl::foldICmpAddConstant(ICmpInst &Cmp,
// Fold icmp pred (add X, C2), C.
Value *X = Add->getOperand(0);
Type *Ty = Add->getType();
CmpInst::Predicate Pred = Cmp.getPredicate();
const CmpInst::Predicate Pred = Cmp.getPredicate();
const APInt SMax = APInt::getSignedMaxValue(Ty->getScalarSizeInBits());
const APInt SMin = APInt::getSignedMinValue(Ty->getScalarSizeInBits());
// Fold an unsigned compare with offset to signed compare:
// Fold compare with offset to opposite sign compare if it eliminates offset:
// (X + C2) >u C --> X <s -C2 (if C == C2 + SMAX)
// TODO: Find the signed predicate siblings.
if (Pred == CmpInst::ICMP_UGT &&
C == *C2 + APInt::getSignedMaxValue(Ty->getScalarSizeInBits()))
if (Pred == CmpInst::ICMP_UGT && C == *C2 + SMax)
return new ICmpInst(ICmpInst::ICMP_SLT, X, ConstantInt::get(Ty, -(*C2)));
// (X + C2) <u C --> X >s ~C2 (if C == C2 + SMIN)
if (Pred == CmpInst::ICMP_ULT &&
C == *C2 + APInt::getSignedMinValue(Ty->getScalarSizeInBits()))
if (Pred == CmpInst::ICMP_ULT && C == *C2 + SMin)
return new ICmpInst(ICmpInst::ICMP_SGT, X, ConstantInt::get(Ty, ~(*C2)));
// (X + C2) >s C --> X <u (SMAX - C) (if C == C2 - 1)
if (Pred == CmpInst::ICMP_SGT && C == *C2 - 1)
return new ICmpInst(ICmpInst::ICMP_ULT, X, ConstantInt::get(Ty, SMax - C));
// (X + C2) <s C --> X >u (C ^ SMAX) (if C == C2)
if (Pred == CmpInst::ICMP_SLT && C == *C2)
return new ICmpInst(ICmpInst::ICMP_UGT, X, ConstantInt::get(Ty, C ^ SMax));
// If the add does not wrap, we can always adjust the compare by subtracting
// the constants. Equality comparisons are handled elsewhere. SGE/SLE/UGE/ULE
// are canonicalized to SGT/SLT/UGT/ULT.

20
llvm/test/Transforms/InstCombine/icmp-add.ll
View File

@ -842,8 +842,7 @@ define i1 @ult_wrong_offset(i8 %a) {
define i1 @sgt_offset(i8 %a) {
; CHECK-LABEL: @sgt_offset(
; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6
; CHECK-NEXT: [[OV:%.*]] = icmp sgt i8 [[T]], -7
; CHECK-NEXT: [[OV:%.*]] = icmp ult i8 [[A:%.*]], -122
; CHECK-NEXT: ret i1 [[OV]]
;
%t = add i8 %a, -6
@ -855,7 +854,7 @@ define i1 @sgt_offset_use(i32 %a) {
; CHECK-LABEL: @sgt_offset_use(
; CHECK-NEXT: [[T:%.*]] = add i32 [[A:%.*]], 42
; CHECK-NEXT: call void @use(i32 [[T]])
; CHECK-NEXT: [[OV:%.*]] = icmp sgt i32 [[T]], 41
; CHECK-NEXT: [[OV:%.*]] = icmp ult i32 [[A]], 2147483606
; CHECK-NEXT: ret i1 [[OV]]
;
%t = add i32 %a, 42
@ -866,8 +865,7 @@ define i1 @sgt_offset_use(i32 %a) {
define <2 x i1> @sgt_offset_splat(<2 x i5> %a) {
; CHECK-LABEL: @sgt_offset_splat(
; CHECK-NEXT: [[T:%.*]] = add <2 x i5> [[A:%.*]], <i5 9, i5 9>
; CHECK-NEXT: [[OV:%.*]] = icmp sgt <2 x i5> [[T]], <i5 8, i5 8>
; CHECK-NEXT: [[OV:%.*]] = icmp ult <2 x i5> [[A:%.*]], <i5 7, i5 7>
; CHECK-NEXT: ret <2 x i1> [[OV]]
;
%t = add <2 x i5> %a, <i5 9, i5 9>
@ -875,6 +873,8 @@ define <2 x i1> @sgt_offset_splat(<2 x i5> %a) {
ret <2 x i1> %ov
}
; negative test - constants must differ by 1
define i1 @sgt_wrong_offset(i8 %a) {
; CHECK-LABEL: @sgt_wrong_offset(
; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -7
@ -888,8 +888,7 @@ define i1 @sgt_wrong_offset(i8 %a) {
define i1 @slt_offset(i8 %a) {
; CHECK-LABEL: @slt_offset(
; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6
; CHECK-NEXT: [[OV:%.*]] = icmp slt i8 [[T]], -6
; CHECK-NEXT: [[OV:%.*]] = icmp ugt i8 [[A:%.*]], -123
; CHECK-NEXT: ret i1 [[OV]]
;
%t = add i8 %a, -6
@ -901,7 +900,7 @@ define i1 @slt_offset_use(i32 %a) {
; CHECK-LABEL: @slt_offset_use(
; CHECK-NEXT: [[T:%.*]] = add i32 [[A:%.*]], 42
; CHECK-NEXT: call void @use(i32 [[T]])
; CHECK-NEXT: [[OV:%.*]] = icmp slt i32 [[T]], 42
; CHECK-NEXT: [[OV:%.*]] = icmp ugt i32 [[A]], 2147483605
; CHECK-NEXT: ret i1 [[OV]]
;
%t = add i32 %a, 42
@ -912,8 +911,7 @@ define i1 @slt_offset_use(i32 %a) {
define <2 x i1> @slt_offset_splat(<2 x i5> %a) {
; CHECK-LABEL: @slt_offset_splat(
; CHECK-NEXT: [[T:%.*]] = add <2 x i5> [[A:%.*]], <i5 9, i5 9>
; CHECK-NEXT: [[OV:%.*]] = icmp slt <2 x i5> [[T]], <i5 9, i5 9>
; CHECK-NEXT: [[OV:%.*]] = icmp ugt <2 x i5> [[A:%.*]], <i5 6, i5 6>
; CHECK-NEXT: ret <2 x i1> [[OV]]
;
%t = add <2 x i5> %a, <i5 9, i5 9>
@ -921,6 +919,8 @@ define <2 x i1> @slt_offset_splat(<2 x i5> %a) {
ret <2 x i1> %ov
}
; negative test - constants must be equal
define i1 @slt_wrong_offset(i8 %a) {
; CHECK-LABEL: @slt_wrong_offset(
; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6