896ece41e4
Summary:
I found the following case having tail blocks with no successors merging opportunities after block placement.
Before block placement:
bb0:
...
bne a0, 0, bb2:
bb1:
mv a0, 1
ret
bb2:
...
bb3:
mv a0, 1
ret
bb4:
mv a0, -1
ret
The conditional branch bne in bb0 is opposite to beq.
After block placement:
bb0:
...
beq a0, 0, bb1
bb2:
...
bb4:
mv a0, -1
ret
bb1:
mv a0, 1
ret
bb3:
mv a0, 1
ret
After block placement, that appears new tail merging opportunity, bb1 and bb3 can be merged as one block. So the conditional constraint for merging tail blocks with no successors should be removed. In my experiment for RISC-V, it decreases code size.
Author of original patch: Jim Lin
Reviewers: haicheng, aheejin, craig.topper, rnk, RKSimon, Jim, dmgreen
Reviewed By: Jim, dmgreen
Subscribers: xbolva00, dschuff, javed.absar, sbc100, jgravelle-google, aheejin, kito-cheng, dmgreen, PkmX, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D54411
llvm-svn: 363284
61 lines
2.3 KiB
LLVM
61 lines
2.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
|
|
|
|
; This test comes from PR27136
|
|
; We should hoist loop constant invariant
|
|
|
|
define zeroext i1 @search(i32 %needle, i32* nocapture readonly %haystack, i32 %count) {
|
|
; CHECK-LABEL: search:
|
|
; CHECK: ## %bb.0: ## %entry
|
|
; CHECK-NEXT: testl %edx, %edx
|
|
; CHECK-NEXT: jle LBB0_5
|
|
; CHECK-NEXT: ## %bb.1: ## %for.body.preheader
|
|
; CHECK-NEXT: movslq %edx, %rax
|
|
; CHECK-NEXT: xorl %ecx, %ecx
|
|
; CHECK-NEXT: .p2align 4, 0x90
|
|
; CHECK-NEXT: LBB0_2: ## %for.body
|
|
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: cmpl %edi, (%rsi,%rcx,4)
|
|
; CHECK-NEXT: je LBB0_6
|
|
; CHECK-NEXT: ## %bb.3: ## %for.cond
|
|
; CHECK-NEXT: ## in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: incq %rcx
|
|
; CHECK-NEXT: cmpq %rax, %rcx
|
|
; CHECK-NEXT: jl LBB0_2
|
|
; CHECK-NEXT: LBB0_5:
|
|
; CHECK-NEXT: xorl %eax, %eax
|
|
; CHECK-NEXT: ## kill: def $al killed $al killed $eax
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: LBB0_6:
|
|
; CHECK-NEXT: movb $1, %al
|
|
; CHECK-NEXT: ## kill: def $al killed $al killed $eax
|
|
; CHECK-NEXT: retq
|
|
entry:
|
|
%cmp5 = icmp sgt i32 %count, 0
|
|
br i1 %cmp5, label %for.body.preheader, label %cleanup
|
|
|
|
for.body.preheader: ; preds = %entry
|
|
%0 = sext i32 %count to i64
|
|
br label %for.body
|
|
|
|
for.cond: ; preds = %for.body
|
|
%cmp = icmp slt i64 %indvars.iv.next, %0
|
|
br i1 %cmp, label %for.body, label %cleanup.loopexit
|
|
|
|
for.body: ; preds = %for.body.preheader, %for.cond
|
|
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.cond ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %haystack, i64 %indvars.iv
|
|
%1 = load i32, i32* %arrayidx, align 4
|
|
%cmp1 = icmp eq i32 %1, %needle
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
br i1 %cmp1, label %cleanup.loopexit, label %for.cond
|
|
|
|
cleanup.loopexit: ; preds = %for.cond, %for.body
|
|
%.ph = phi i1 [ false, %for.cond ], [ true, %for.body ]
|
|
br label %cleanup
|
|
|
|
cleanup: ; preds = %cleanup.loopexit, %entry
|
|
%2 = phi i1 [ false, %entry ], [ %.ph, %cleanup.loopexit ]
|
|
ret i1 %2
|
|
}
|