RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
Code Issues Projects Releases Wiki Activity

Reapply [InstCombine] Fold multiuse shr eq zero

Browse Source 
This was reverted due to performance regressions in ARM benchmarks,
which have since been addressed by D101196 (SCEV analysis improvement)
and D101778 (CGP reverse transform).

-----

The single-use case is handled implicity by converting the icmp
into a mask check first. When comparing with zero in particular,
we don't need the one-use restriction, as we only produce a single
icmp.

https://alive2.llvm.org/ce/z/MSixcm
https://alive2.llvm.org/ce/z/GwpG0M
This commit is contained in:
Nikita Popov 2021-04-19 22:09:15 +02:00
parent aca1951bd7
commit 8c07a78a96
4 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lib/Transforms/InstCombine/InstCombineCompares.cpp
View File

@ -2280,6 +2280,16 @@ Instruction *InstCombinerImpl::foldICmpShrConstant(ICmpInst &Cmp,
if (Shr->isExact())
return new ICmpInst(Pred, X, ConstantInt::get(ShrTy, C << ShAmtVal));
if (C.isNullValue()) {
// == 0 is u< 1.
if (Pred == CmpInst::ICMP_EQ)
return new ICmpInst(CmpInst::ICMP_ULT, X,
ConstantInt::get(ShrTy, (C + 1).shl(ShAmtVal)));
else
return new ICmpInst(CmpInst::ICMP_UGT, X,
ConstantInt::get(ShrTy, (C + 1).shl(ShAmtVal) - 1));
}
if (Shr->hasOneUse()) {
// Canonicalize the shift into an 'and':
// icmp eq/ne (shr X, ShAmt), C --> icmp eq/ne (and X, HiMask), (C << ShAmt)

8
test/Transforms/InstCombine/icmp-shr.ll
View File

@ -875,7 +875,7 @@ define i1 @lshr_eq_0_multiuse(i8 %x) {
; CHECK-LABEL: @lshr_eq_0_multiuse(
; CHECK-NEXT: [[S:%.*]] = lshr i8 [[X:%.*]], 2
; CHECK-NEXT: call void @use(i8 [[S]])
; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[S]], 0
; CHECK-NEXT: [[C:%.*]] = icmp ult i8 [[X]], 4
; CHECK-NEXT: ret i1 [[C]]
;
%s = lshr i8 %x, 2
@ -888,7 +888,7 @@ define i1 @lshr_ne_0_multiuse(i8 %x) {
; CHECK-LABEL: @lshr_ne_0_multiuse(
; CHECK-NEXT: [[S:%.*]] = lshr i8 [[X:%.*]], 2
; CHECK-NEXT: call void @use(i8 [[S]])
; CHECK-NEXT: [[C:%.*]] = icmp ne i8 [[S]], 0
; CHECK-NEXT: [[C:%.*]] = icmp ugt i8 [[X]], 3
; CHECK-NEXT: ret i1 [[C]]
;
%s = lshr i8 %x, 2
@ -901,7 +901,7 @@ define i1 @ashr_eq_0_multiuse(i8 %x) {
; CHECK-LABEL: @ashr_eq_0_multiuse(
; CHECK-NEXT: [[S:%.*]] = ashr i8 [[X:%.*]], 2
; CHECK-NEXT: call void @use(i8 [[S]])
; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[S]], 0
; CHECK-NEXT: [[C:%.*]] = icmp ult i8 [[X]], 4
; CHECK-NEXT: ret i1 [[C]]
;
%s = ashr i8 %x, 2
@ -914,7 +914,7 @@ define i1 @ashr_ne_0_multiuse(i8 %x) {
; CHECK-LABEL: @ashr_ne_0_multiuse(
; CHECK-NEXT: [[S:%.*]] = ashr i8 [[X:%.*]], 2
; CHECK-NEXT: call void @use(i8 [[S]])
; CHECK-NEXT: [[C:%.*]] = icmp ne i8 [[S]], 0
; CHECK-NEXT: [[C:%.*]] = icmp ugt i8 [[X]], 3
; CHECK-NEXT: ret i1 [[C]]
;
%s = ashr i8 %x, 2

7
test/Transforms/InstCombine/icmp_sdiv_with_and_without_range.ll
View File

@ -2,7 +2,7 @@
; RUN: opt -instcombine -S < %s | FileCheck %s
; Test that presence of range does not cause unprofitable transforms with bit
; arithmetics, and instcombine behaves exactly the same as without the range.
; arithmetics.
define i1 @without_range(i32* %A) {
; CHECK-LABEL: @without_range(
@ -18,9 +18,8 @@ define i1 @without_range(i32* %A) {
define i1 @with_range(i32* %A) {
; CHECK-LABEL: @with_range(
; CHECK-NEXT: [[A_VAL:%.*]] = load i32, i32* [[A:%.*]], align 8, !range !0
; CHECK-NEXT: [[B_MASK:%.*]] = and i32 [[A_VAL]], 2147483646
; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[B_MASK]], 0
; CHECK-NEXT: [[A_VAL:%.*]] = load i32, i32* [[A:%.*]], align 8, !range [[RNG0:![0-9]+]]
; CHECK-NEXT: [[C:%.*]] = icmp ult i32 [[A_VAL]], 2
; CHECK-NEXT: ret i1 [[C]]
;
%A.val = load i32, i32* %A, align 8, !range !0

2
test/Transforms/PhaseOrdering/X86/ctlz-loop.ll
View File

@ -32,7 +32,7 @@ define i32 @ctlz_loop_with_abs(i32 %n) {
; CHECK-NEXT: [[I_02:%.*]] = phi i32 [ [[INC:%.*]], [[WHILE_BODY]] ], [ 0, [[WHILE_BODY_PREHEADER]] ]
; CHECK-NEXT: [[TMP1]] = lshr i32 [[N_ADDR_03]], 1
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_02]], 1
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP1]], 0
; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp ult i32 [[N_ADDR_03]], 2
; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label [[WHILE_END]], label [[WHILE_BODY]]
; CHECK: while.end:
; CHECK-NEXT: [[I_0_LCSSA:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC]], [[WHILE_BODY]] ]