mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
a67cf70e74
Summary: Make isGuaranteedToExecute use the isGuaranteedToTransferExecutionToSuccessor helper, and make that helper a bit more accurate. There's a potential performance impact here from assuming that arbitrary calls might not return. This probably has little impact on loads and stores to a pointer because most things alias analysis can reason about are dereferenceable anyway. The other impacts, like less aggressive hoisting of sdiv by a variable and less aggressive hoisting around volatile memory operations, are unlikely to matter for real code. This also impacts SCEV, which uses the same helper. It's a minor improvement there because we can tell that, for example, memcpy always returns normally. Strictly speaking, it's also introducing a bug, but it's not any worse than everywhere else we assume readonly functions terminate. Fixes http://llvm.org/PR27857. Reviewers: hfinkel, reames, chandlerc, sanjoy Subscribers: broune, llvm-commits Differential Revision: http://reviews.llvm.org/D21167 llvm-svn: 272489
134 lines
3.9 KiB
LLVM
134 lines
3.9 KiB
LLVM
; RUN: opt -tbaa -basicaa -licm -S < %s | FileCheck %s
|
|
|
|
; If we can prove a local is thread local, we can insert stores during
|
|
; promotion which wouldn't be legal otherwise.
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-linux-generic"
|
|
|
|
@p = external global i8*
|
|
|
|
declare i8* @malloc(i64)
|
|
|
|
; Exercise the TLS case
|
|
define i32* @test(i32 %n) {
|
|
entry:
|
|
;; ignore the required null check for simplicity
|
|
%mem = call dereferenceable(16) noalias i8* @malloc(i64 16)
|
|
%addr = bitcast i8* %mem to i32*
|
|
br label %for.body.lr.ph
|
|
|
|
for.body.lr.ph: ; preds = %entry
|
|
br label %for.header
|
|
|
|
for.header:
|
|
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
|
|
%old = load i32, i32* %addr, align 4
|
|
; deliberate impossible to analyze branch
|
|
%guard = load atomic i8*, i8** @p monotonic, align 8
|
|
%exitcmp = icmp eq i8* %guard, null
|
|
br i1 %exitcmp, label %for.body, label %early-exit
|
|
|
|
early-exit:
|
|
; CHECK-LABEL: early-exit:
|
|
; CHECK: store i32 %new1.lcssa, i32* %addr, align 1
|
|
ret i32* null
|
|
|
|
for.body:
|
|
%new = add i32 %old, 1
|
|
store i32 %new, i32* %addr, align 4
|
|
%inc = add nsw i32 %i.02, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %for.header, label %for.cond.for.end_crit_edge
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
; CHECK-LABEL: for.cond.for.end_crit_edge:
|
|
; CHECK: store i32 %new.lcssa, i32* %addr, align 1
|
|
%split = phi i32* [ %addr, %for.body ]
|
|
ret i32* null
|
|
}
|
|
|
|
declare i8* @not_malloc(i64)
|
|
|
|
; Negative test - not TLS
|
|
define i32* @test_neg(i32 %n) {
|
|
entry:
|
|
;; ignore the required null check for simplicity
|
|
%mem = call dereferenceable(16) noalias i8* @not_malloc(i64 16)
|
|
%addr = bitcast i8* %mem to i32*
|
|
br label %for.body.lr.ph
|
|
|
|
for.body.lr.ph: ; preds = %entry
|
|
br label %for.header
|
|
|
|
for.header:
|
|
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
|
|
%old = load i32, i32* %addr, align 4
|
|
; deliberate impossible to analyze branch
|
|
%guard = load volatile i8*, i8** @p
|
|
%exitcmp = icmp eq i8* %guard, null
|
|
br i1 %exitcmp, label %for.body, label %early-exit
|
|
|
|
early-exit:
|
|
; CHECK-LABEL: early-exit:
|
|
; CHECK-NOT: store
|
|
ret i32* null
|
|
|
|
for.body:
|
|
; CHECK-LABEL: for.body:
|
|
; CHECK: store i32 %new, i32* %addr, align 4
|
|
%new = add i32 %old, 1
|
|
store i32 %new, i32* %addr, align 4
|
|
%inc = add nsw i32 %i.02, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %for.header, label %for.cond.for.end_crit_edge
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
; CHECK-LABEL: for.cond.for.end_crit_edge:
|
|
; CHECK-NOT: store
|
|
%split = phi i32* [ %addr, %for.body ]
|
|
ret i32* null
|
|
}
|
|
|
|
; Negative test - can't speculate load since branch
|
|
; may control alignment
|
|
define i32* @test_neg2(i32 %n) {
|
|
entry:
|
|
;; ignore the required null check for simplicity
|
|
%mem = call dereferenceable(16) noalias i8* @malloc(i64 16)
|
|
%addr = bitcast i8* %mem to i32*
|
|
br label %for.body.lr.ph
|
|
|
|
for.body.lr.ph: ; preds = %entry
|
|
br label %for.header
|
|
|
|
for.header:
|
|
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
|
|
; deliberate impossible to analyze branch
|
|
%guard = load volatile i8*, i8** @p
|
|
%exitcmp = icmp eq i8* %guard, null
|
|
br i1 %exitcmp, label %for.body, label %early-exit
|
|
|
|
early-exit:
|
|
; CHECK-LABEL: early-exit:
|
|
; CHECK-NOT: store
|
|
ret i32* null
|
|
|
|
for.body:
|
|
; CHECK-LABEL: for.body:
|
|
; CHECK: store i32 %new, i32* %addr, align 4
|
|
%old = load i32, i32* %addr, align 4
|
|
%new = add i32 %old, 1
|
|
store i32 %new, i32* %addr, align 4
|
|
%inc = add nsw i32 %i.02, 1
|
|
%cmp = icmp slt i32 %inc, %n
|
|
br i1 %cmp, label %for.header, label %for.cond.for.end_crit_edge
|
|
|
|
for.cond.for.end_crit_edge: ; preds = %for.body
|
|
; CHECK-LABEL: for.cond.for.end_crit_edge:
|
|
; CHECK-NOT: store
|
|
%split = phi i32* [ %addr, %for.body ]
|
|
ret i32* null
|
|
}
|
|
|