maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert r163761 "Don't fold indexed loads into TCRETURNmi64." 

The patch caused "Wrong topological sorting" assertions.

llvm-svn: 163810
This commit is contained in:
Jakob Stoklund Olesen 2012-09-13 16:52:17 +00:00
parent 15a257dadd
commit 78b9f8fc67
4 changed files with 2 additions and 74 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
View File

@ -204,9 +204,6 @@ namespace {
bool SelectAddr(SDNode *Parent, SDValue N, SDValue &Base,
SDValue &Scale, SDValue &Index, SDValue &Disp,
SDValue &Segment);
bool SelectSingleRegAddr(SDNode *Parent, SDValue N, SDValue &Base,
SDValue &Scale, SDValue &Index, SDValue &Disp,
SDValue &Segment);
bool SelectLEAAddr(SDValue N, SDValue &Base,
SDValue &Scale, SDValue &Index, SDValue &Disp,
SDValue &Segment);
@ -1322,31 +1319,6 @@ bool X86DAGToDAGISel::SelectAddr(SDNode *Parent, SDValue N, SDValue &Base,
return true;
}
/// SelectSingleRegAddr - Like SelectAddr, but reject any address that would
/// require more than one allocatable register.
///
/// This is used for a TCRETURNmi64 instruction when used to tail call a
/// variadic function with 6 arguments: Only %r11 is available from GR64_TC.
/// The other scratch register, %rax, is needed to pass in the number of vector
/// registers used in the variadic arguments.
///
bool X86DAGToDAGISel::SelectSingleRegAddr(SDNode *Parent, SDValue N,
SDValue &Base,
SDValue &Scale, SDValue &Index,
SDValue &Disp, SDValue &Segment) {
if (!SelectAddr(Parent, N, Base, Scale, Index, Disp, Segment))
return false;
// Anything %RIP relative is fine.
if (RegisterSDNode *Reg = dyn_cast<RegisterSDNode>(Base))
if (Reg->getReg() == X86::RIP)
return true;
// Check that the index register is 0.
if (RegisterSDNode *Reg = dyn_cast<RegisterSDNode>(Index))
if (Reg->getReg() == 0)
return true;
return false;
}
/// SelectScalarSSELoad - Match a scalar SSE load. In particular, we want to
/// match a load whose top elements are either undef or zeros. The load flavor
/// is derived from the type of N, which is either v4f32 or v2f64.

8
llvm/lib/Target/X86/X86InstrCompiler.td
View File

@ -1041,13 +1041,7 @@ def : Pat<(X86tcret ptr_rc_tailcall:$dst, imm:$off),
(TCRETURNri64 ptr_rc_tailcall:$dst, imm:$off)>,
Requires<[In64BitMode]>;
// When calling a variadic function with 6 arguments, 7 scratch registers are
// needed since %al holds the number of vector registers used. That leaves %r11
// as the only remaining GR64_TC register for the addressing mode.
//
// The single_reg_addr pattern rejects any addressing modes that would need
// more than one register.
def : Pat<(X86tcret (load single_reg_addr:$dst), imm:$off),
def : Pat<(X86tcret (load addr:$dst), imm:$off),
(TCRETURNmi64 addr:$dst, imm:$off)>,
Requires<[In64BitMode]>;

4
llvm/lib/Target/X86/X86InstrInfo.td
View File

@ -543,10 +543,6 @@ def tls64addr : ComplexPattern<i64, 5, "SelectTLSADDRAddr",
def tls64baseaddr : ComplexPattern<i64, 5, "SelectTLSADDRAddr",
[tglobaltlsaddr], []>;
// Same as addr, but reject addressing modes requiring more than one register.
def single_reg_addr : ComplexPattern<iPTR, 5, "SelectSingleRegAddr", [],
[SDNPWantParent]>;
//===----------------------------------------------------------------------===//
// X86 Instruction Predicate Definitions.
def HasCMov : Predicate<"Subtarget->hasCMov()">;

36
llvm/test/CodeGen/X86/tailcall-64.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -verify-machineinstrs | FileCheck %s
; RUN: llc < %s | FileCheck %s
target datalayout = "e-p:64:64:64-S128-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f16:16:16-f32:32:32-f64:64:64-f128:128:128-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-apple-darwin11.4.0"
@ -93,38 +93,4 @@ define { i64, i64 } @crash(i8* %this) {
ret { i64, i64 } %mrv7
}
; <rdar://problem/12282281> Fold an indexed load into the tail call instruction.
; Calling a varargs function with 6 arguments requires 7 registers (%al is the
; vector count for varargs functions). This leaves %r11 as the only available
; scratch register.
;
; It is not possible to fold an indexed load into TCRETURNmi64 in that case.
;
; typedef int (*funcptr)(void*, ...);
; extern const funcptr funcs[];
; int f(int n) {
; return funcs[n](0, 0, 0, 0, 0, 0);
; }
;
; CHECK: rdar12282281
; CHECK: jmpq *%r11 # TAILCALL
@funcs = external constant [0 x i32 (i8*, ...)*]
define i32 @rdar12282281(i32 %n) nounwind uwtable ssp {
entry:
%idxprom = sext i32 %n to i64
%arrayidx = getelementptr inbounds [0 x i32 (i8*, ...)*]* @funcs, i64 0, i64 %idxprom
%0 = load i32 (i8*, ...)** %arrayidx, align 8
%call = tail call i32 (i8*, ...)* %0(i8* null, i32 0, i32 0, i32 0, i32 0, i32 0) nounwind
ret i32 %call
}
; Same thing, using a fixed offset. The load should foid.
; CHECK: rdar12282281fixed
; CHECK: jmpq *8(%r11) # TAILCALL
define i32 @rdar12282281fixed() nounwind uwtable ssp {
entry:
%0 = load i32 (i8*, ...)** getelementptr inbounds ([0 x i32 (i8*, ...)*]* @funcs, i64 0, i64 1), align 8
%call.i = tail call i32 (i8*, ...)* %0(i8* null, i32 0, i32 0, i32 0, i32 0, i32 0) nounwind
ret i32 %call.i
}