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

ARM: use litpools for normal i32 imms when compiling minsize. 

With constant-sharing, litpool loads consume 4 + N*2 bytes of code, but
movw/movt pairs consume 8*N. This means litpools are better than movw/movt even
with just one use. Other materialisation strategies can still be better though,
so the logic is a little odd.

llvm-svn: 199891
This commit is contained in:
Tim Northover 2014-01-23 13:43:47 +00:00
parent e1b5bddca4
commit 55c625f222
4 changed files with 70 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp
View File

@ -2472,19 +2472,21 @@ SDNode *ARMDAGToDAGISel::Select(SDNode *N) {
case ISD::Constant: {
unsigned Val = cast<ConstantSDNode>(N)->getZExtValue();
bool UseCP = true;
if (Subtarget->hasThumb2())
if (Subtarget->useMovt())
// Thumb2-aware targets have the MOVT instruction, so all immediates can
// be done with MOV + MOVT, at worst.
UseCP = 0;
UseCP = false;
else {
if (Subtarget->isThumb()) {
UseCP = (Val > 255 && // MOV
~Val > 255 && // MOV + MVN
!ARM_AM::isThumbImmShiftedVal(Val)); // MOV + LSL
UseCP = (Val > 255 && // MOV
~Val > 255 && // MOV + MVN
!ARM_AM::isThumbImmShiftedVal(Val) && // MOV + LSL
!(Subtarget->hasV6T2Ops() && Val <= 0xffff)); // MOVW
} else
UseCP = (ARM_AM::getSOImmVal(Val) == -1 && // MOV
ARM_AM::getSOImmVal(~Val) == -1 && // MVN
!ARM_AM::isSOImmTwoPartVal(Val)); // two instrs.
UseCP = (ARM_AM::getSOImmVal(Val) == -1 && // MOV
ARM_AM::getSOImmVal(~Val) == -1 && // MVN
!ARM_AM::isSOImmTwoPartVal(Val) && // two instrs.
!(Subtarget->hasV6T2Ops() && Val <= 0xffff)); // MOVW
}
if (UseCP) {
@ -2494,7 +2496,7 @@ SDNode *ARMDAGToDAGISel::Select(SDNode *N) {
getTargetLowering()->getPointerTy());
SDNode *ResNode;
if (Subtarget->isThumb1Only()) {
if (Subtarget->isThumb()) {
SDValue Pred = getAL(CurDAG);
SDValue PredReg = CurDAG->getRegister(0, MVT::i32);
SDValue Ops[] = { CPIdx, Pred, PredReg, CurDAG->getEntryNode() };

2
llvm/lib/Target/ARM/ARMInstrInfo.td
View File

@ -593,7 +593,7 @@ def so_imm2part : PatLeaf<(imm), [{
/// arm_i32imm - True for +V6T2, or true only if so_imm2part is true.
///
def arm_i32imm : PatLeaf<(imm), [{
if (Subtarget->hasV6T2Ops())
if (Subtarget->useMovt())
return true;
return ARM_AM::isSOImmTwoPartVal((unsigned)N->getZExtValue());
}]>;

2
llvm/lib/Target/ARM/ARMInstrThumb2.td
View File

@ -3781,7 +3781,7 @@ def t2SUBS_PC_LR : T2I <(outs), (ins imm0_255:$imm), NoItinerary,
let isReMaterializable = 1, isMoveImm = 1 in
def t2MOVi32imm : PseudoInst<(outs rGPR:$dst), (ins i32imm:$src), IIC_iMOVix2,
[(set rGPR:$dst, (i32 imm:$src))]>,
Requires<[IsThumb, HasV6T2]>;
Requires<[IsThumb, UseMovt]>;
// Pseudo instruction that combines movw + movt + add pc (if pic).
// It also makes it possible to rematerialize the instructions.

57
llvm/test/CodeGen/ARM/minsize-imms.ll Normal file
View File

@ -0,0 +1,57 @@
; RUN: llc -mtriple=thumbv7m-macho -o - -show-mc-encoding %s | FileCheck %s
; RUN: llc -mtriple=thumbv6m-macho -o - -show-mc-encoding %s | FileCheck %s --check-prefix=CHECK-V6M
; RUN: llc -mtriple=armv6-macho -o - -show-mc-encoding %s | FileCheck %s --check-prefix=CHECK-ARM
define i32 @test_mov() minsize {
; CHECK-LABEL: test_mov:
; CHECK: movs r0, #255 @ encoding: [0xff,0x20]
ret i32 255
}
define i32 @test_mov_mvn() minsize {
; CHECK-LABEL: test_mov_mvn:
; CHECK: mvn r0, #203 @ encoding: [0x6f,0xf0,0xcb,0x00]
; CHECK-V6M-LABEL: test_mov_mvn:
; CHECK-V6M: movs [[TMP:r[0-7]]], #203 @ encoding: [0xcb,0x20]
; CHECK-V6M: mvns r0, [[TMP]] @ encoding: [0xc0,0x43]
; CHECK-ARM-LABEL: test_mov_mvn:
; CHECK-ARM: mvn r0, #203 @ encoding: [0xcb,0x00,0xe0,0xe3]
ret i32 4294967092
}
define i32 @test_mov_lsl() minsize {
; CHECK-LABEL: test_mov_lsl:
; CHECK: mov.w r0, #589824 @ encoding: [0x4f,0xf4,0x10,0x20]
; CHECK-V6M-LABEL: test_mov_lsl:
; CHECK-V6M: movs [[TMP:r[0-7]]], #9 @ encoding: [0x09,0x20]
; CHECK-V6M: lsls r0, [[TMP]], #16 @ encoding: [0x00,0x04]
; CHECK-ARM-LABEL: test_mov_lsl:
; CHECK-ARM: mov r0, #589824 @ encoding: [0x09,0x08,0xa0,0xe3]
ret i32 589824
}
define i32 @test_movw() minsize {
; CHECK-LABEL: test_movw:
; CHECK: movw r0, #65535
; CHECK-V6M-LABEL: test_movw:
; CHECK-V6M: ldr r0, [[CONSTPOOL:LCPI[0-9]+_[0-9]+]] @ encoding: [A,0x48]
; CHECK-V6M: [[CONSTPOOL]]:
; CHECK-V6M-NEXT: .long 65535
; CHECK-ARM-LABEL: test_movw:
; CHECK-ARM: mov r0, #255 @ encoding: [0xff,0x00,0xa0,0xe3]
; CHECK-ARM: orr r0, r0, #65280 @ encoding: [0xff,0x0c,0x80,0xe3]
ret i32 65535
}
define i32 @test_regress1() {
; CHECK-ARM-LABEL: test_regress1:
; CHECK-ARM: mov r0, #248 @ encoding: [0xf8,0x00,0xa0,0xe3]
; CHECK-ARM: orr r0, r0, #16252928 @ encoding: [0x3e,0x07,0x80,0xe3]
ret i32 16253176
}