mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-20 19:42:54 +02:00
13c5bb4a2e
Presently, CodeGenPrepare deletes all nearly empty (only phi and branch) basic blocks. This pass can delete loop preheaders which frequently creates critical edges. A preheader can be a convenient place to spill registers to the stack. If the entrance to a loop body is a critical edge, then spills may occur in the loop body rather than immediately before it. This patch protects loop preheaders from deletion in CodeGenPrepare even if they are nearly empty. Since the patch alters the CFG, it affects a large number of test cases. In most cases, the changes are merely cosmetic (basic blocks have different names or instruction orders change slightly). I am somewhat concerned about the test/CodeGen/Mips/brdelayslot.ll test case. If the loop preheader is not deleted, then the MIPS backend does not take advantage of a branch delay slot. Consequently, I would like some close review by a MIPS expert. The patch also partially subsumes D16893 from George Burgess IV. George correctly notes that CodeGenPrepare does not actually preserve the dominator tree. I think the dominator tree was usually not valid when CodeGenPrepare ran, but I am using LoopInfo to mark preheaders, so the dominator tree is now always valid before CodeGenPrepare. Author: Tom Jablin (tjablin) Reviewers: hfinkel george.burgess.iv vkalintiris dsanders kbarton cycheng http://reviews.llvm.org/D16984 llvm-svn: 265397
43 lines
1.2 KiB
LLVM
43 lines
1.2 KiB
LLVM
; RUN: llc -march=x86-64 -mcpu=generic -mtriple=x86_64-unknown-linux-gnu -relocation-model=static -asm-verbose=false < %s | FileCheck %s
|
|
; RUN: llc -march=x86-64 -mcpu=atom -mtriple=x86_64-unknown-linux-gnu -relocation-model=static -asm-verbose=false < %s | FileCheck -check-prefix=ATOM %s
|
|
|
|
; CHECK: xorl %eax, %eax
|
|
; CHECK: movsd .LCPI0_0(%rip), %xmm0
|
|
; CHECK: align
|
|
; CHECK-NEXT: BB0_2:
|
|
; CHECK-NEXT: movsd A(,%rax,8)
|
|
; CHECK-NEXT: mulsd
|
|
; CHECK-NEXT: movsd
|
|
; CHECK-NEXT: incq %rax
|
|
|
|
|
|
; ATOM: movsd .LCPI0_0(%rip), %xmm0
|
|
; ATOM: xorl %eax, %eax
|
|
; ATOM: align
|
|
; ATOM-NEXT: BB0_2:
|
|
; ATOM-NEXT: movsd A(,%rax,8)
|
|
; ATOM-NEXT: mulsd
|
|
; ATOM-NEXT: movsd
|
|
; ATOM-NEXT: incq %rax
|
|
|
|
@A = external global [0 x double]
|
|
|
|
define void @foo(i64 %n) nounwind {
|
|
entry:
|
|
%cmp5 = icmp sgt i64 %n, 0
|
|
br i1 %cmp5, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%i.06 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr [0 x double], [0 x double]* @A, i64 0, i64 %i.06
|
|
%tmp3 = load double, double* %arrayidx, align 8
|
|
%mul = fmul double %tmp3, 2.300000e+00
|
|
store double %mul, double* %arrayidx, align 8
|
|
%inc = add nsw i64 %i.06, 1
|
|
%exitcond = icmp eq i64 %inc, %n
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|