428f36401b
This reverts commit37b8f09a4b, and returns commit1bd0b82e50. The miscompile was in InstCombine, and it has been addressed. This tries to approach the problem noted by @arsenm: terrible codegen for `__builtin_fpclassify()`: https://godbolt.org/z/388zqdE37 Just because the PHI in the common successor happens to have different incoming values for these two blocks, doesn't mean we have to give up. It's quite easy to deal with this, we just need to produce a select: https://alive2.llvm.org/ce/z/000srb Now, the cost model for this transform is rather overly strict, so this will basically never fire. We tally all (over all preds) the selects needed to the NumBonusInsts Differential Revision: https://reviews.llvm.org/D139275
66 lines
2.4 KiB
LLVM
66 lines
2.4 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, ptr 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, %rcx
|
|
; CHECK-NEXT: movl $1, %edx
|
|
; CHECK-NEXT: .p2align 4, 0x90
|
|
; CHECK-NEXT: LBB0_2: ## %for.body
|
|
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: movl -4(%rsi,%rdx,4), %r8d
|
|
; CHECK-NEXT: cmpl %edi, %r8d
|
|
; CHECK-NEXT: sete %al
|
|
; CHECK-NEXT: negb %al
|
|
; CHECK-NEXT: cmpl %edi, %r8d
|
|
; CHECK-NEXT: je LBB0_4
|
|
; CHECK-NEXT: ## %bb.3: ## %for.body
|
|
; CHECK-NEXT: ## in Loop: Header=BB0_2 Depth=1
|
|
; CHECK-NEXT: cmpq %rcx, %rdx
|
|
; CHECK-NEXT: leaq 1(%rdx), %rdx
|
|
; CHECK-NEXT: jl LBB0_2
|
|
; CHECK-NEXT: LBB0_4: ## %cleanup
|
|
; CHECK-NEXT: andb $1, %al
|
|
; CHECK-NEXT: ## kill: def $al killed $al killed $eax
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: LBB0_5:
|
|
; CHECK-NEXT: xorl %eax, %eax
|
|
; CHECK-NEXT: andb $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, ptr %haystack, i64 %indvars.iv
|
|
%1 = load i32, ptr %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
|
|
}
|