[X86] Add a flag to guard the wide load

As shown in http://lists.llvm.org/pipermail/llvm-dev/2020-May/141854.html,
widen load can also cause stall. Add a flag to guard the widening code,
so users can disable it and evaluate its performance impact.

Differential Revision: https://reviews.llvm.org/D80943
This commit is contained in:
Guozhi Wei 2020-06-02 16:12:50 -07:00
parent 5138a91ef4
commit 587af86f1d
3 changed files with 28 additions and 2 deletions

View File

@ -40,6 +40,10 @@ static cl::opt<bool> AndImmShrink("x86-and-imm-shrink", cl::init(true),
cl::desc("Enable setting constant bits to reduce size of mask immediates"),
cl::Hidden);
static cl::opt<bool> EnablePromoteAnyextLoad(
"x86-promote-anyext-load", cl::init(true),
cl::desc("Enable promoting aligned anyext load to wider load"), cl::Hidden);
//===----------------------------------------------------------------------===//
// Pattern Matcher Implementation
//===----------------------------------------------------------------------===//

View File

@ -1122,7 +1122,7 @@ def loadi16 : PatFrag<(ops node:$ptr), (i16 (unindexedload node:$ptr)), [{
ISD::LoadExtType ExtType = LD->getExtensionType();
if (ExtType == ISD::NON_EXTLOAD)
return true;
if (ExtType == ISD::EXTLOAD)
if (ExtType == ISD::EXTLOAD && EnablePromoteAnyextLoad)
return LD->getAlignment() >= 2 && LD->isSimple();
return false;
}]>;
@ -1132,7 +1132,7 @@ def loadi32 : PatFrag<(ops node:$ptr), (i32 (unindexedload node:$ptr)), [{
ISD::LoadExtType ExtType = LD->getExtensionType();
if (ExtType == ISD::NON_EXTLOAD)
return true;
if (ExtType == ISD::EXTLOAD)
if (ExtType == ISD::EXTLOAD && EnablePromoteAnyextLoad)
return LD->getAlignment() >= 4 && LD->isSimple();
return false;
}]>;

View File

@ -0,0 +1,22 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-- -x86-promote-anyext-load=false | FileCheck %s
%struct.S = type { i32, i16, i16 }
define void @foo(%struct.S* %p, i16 signext %s) {
; CHECK-LABEL: foo:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movzwl 4(%rdi), %eax
; CHECK-NEXT: andl $-1121, %eax # imm = 0xFB9F
; CHECK-NEXT: orl $1024, %eax # imm = 0x400
; CHECK-NEXT: movw %ax, 4(%rdi)
; CHECK-NEXT: retq
entry:
%f2 = getelementptr inbounds %struct.S, %struct.S* %p, i64 0, i32 1
%0 = load i16, i16* %f2, align 4
%1 = and i16 %0, -1121
%2 = or i16 %1, 1024
store i16 %2, i16* %f2, align 4
ret void
}