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

R600: optimize the UDIVREM 64 algorithm 

This is a squash of several optimization commits:
 - calculate DIV_Lo and DIV_Hi separately
 - use BFE_U32 if we are operating on 32bit values
 - use precomputed constants instead of shifting in UDVIREM
 - skip the first 32 iterations of udivrem

v2: Check whether BFE is supported before using it

Patch by: Jan Vesely

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 207589
This commit is contained in:
Tom Stellard 2014-04-29 23:12:46 +00:00
parent bcd318fc76
commit 676f571999
2 changed files with 128 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
llvm/lib/Target/R600/AMDGPUISelLowering.cpp
View File

@ -433,46 +433,68 @@ void AMDGPUTargetLowering::ReplaceNodeResults(SDNode *N,
EVT VT = Op.getValueType();
EVT HalfVT = VT.getHalfSizedIntegerVT(*DAG.getContext());
SDValue one = DAG.getConstant(1, HalfVT);
SDValue zero = DAG.getConstant(0, HalfVT);
//HiLo split
SDValue LHS_Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT,
N->getOperand(0), DAG.getConstant(0, HalfVT));
SDValue LHS_Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT,
N->getOperand(0), DAG.getConstant(1, HalfVT));
SDValue LHS = N->getOperand(0);
SDValue LHS_Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, LHS, zero);
SDValue LHS_Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, LHS, one);
SDValue RHS = N->getOperand(1);
SDValue RHS_Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, RHS, zero);
SDValue RHS_Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, RHS, one);
SDValue DIV = DAG.getConstant(0, VT);
SDValue REM = DAG.getConstant(0, VT);
// Get Speculative values
SDValue DIV_Part = DAG.getNode(ISD::UDIV, DL, HalfVT, LHS_Hi, RHS_Lo);
SDValue REM_Part = DAG.getNode(ISD::UREM, DL, HalfVT, LHS_Hi, RHS_Lo);
SDValue REM_Hi = zero;
SDValue REM_Lo = DAG.getSelectCC(DL, RHS_Hi, zero, REM_Part, LHS_Hi, ISD::SETEQ);
SDValue DIV_Hi = DAG.getSelectCC(DL, RHS_Hi, zero, DIV_Part, zero, ISD::SETEQ);
SDValue DIV_Lo = zero;
const unsigned bitWidth = VT.getSizeInBits();
const unsigned halfBitWidth = HalfVT.getSizeInBits();
SDValue one = DAG.getConstant(1, HalfVT);
SDValue one_VT = DAG.getConstant(1, VT);
for (unsigned i = 0; i < bitWidth; ++i) {
SDValue POS = DAG.getConstant((bitWidth - i - 1) % halfBitWidth, HalfVT);
for (unsigned i = 0; i < halfBitWidth; ++i) {
SDValue POS = DAG.getConstant(halfBitWidth - i - 1, HalfVT);
// Get Value of high bit
SDValue HBit = DAG.getNode(ISD::SRL, DL, HalfVT,
i < halfBitWidth ? LHS_Hi : LHS_Lo, POS);
HBit = DAG.getNode(ISD::AND, DL, HalfVT, HBit, one);
HBit = DAG.getNode(ISD::ZERO_EXTEND, DL, VT, HBit);
SDValue HBit;
if (halfBitWidth == 32 && Subtarget->hasBFE()) {
HBit = DAG.getNode(AMDGPUISD::BFE_U32, DL, HalfVT, LHS_Lo, POS, one);
} else {
HBit = DAG.getNode(ISD::SRL, DL, HalfVT, LHS_Lo, POS);
HBit = DAG.getNode(ISD::AND, DL, HalfVT, HBit, one);
}
// Add the high bit to shifted remainder
REM = DAG.getNode(ISD::SHL, DL, VT, REM, one);
REM = DAG.getNode(ISD::OR, DL, VT, REM, HBit);
SDValue Carry = DAG.getNode(ISD::SRL, DL, HalfVT, REM_Lo,
DAG.getConstant(halfBitWidth - 1, HalfVT));
REM_Hi = DAG.getNode(ISD::SHL, DL, HalfVT, REM_Hi, one);
REM_Hi = DAG.getNode(ISD::OR, DL, HalfVT, REM_Hi, Carry);
// Update DIV
SDValue ShDIV = DAG.getNode(ISD::SHL, DL, VT, DIV, one);
SDValue ShDIV_plus = DAG.getNode(ISD::OR, DL, VT, ShDIV, one_VT);
REM_Lo = DAG.getNode(ISD::SHL, DL, HalfVT, REM_Lo, one);
REM_Lo = DAG.getNode(ISD::OR, DL, HalfVT, REM_Lo, HBit);
DIV = DAG.getSelectCC(DL, REM, RHS, ShDIV_plus, ShDIV, ISD::SETGE);
SDValue REM = DAG.getNode(ISD::BUILD_PAIR, DL, VT, REM_Lo, REM_Hi);
SDValue BIT = DAG.getConstant(1 << (halfBitWidth - i - 1), HalfVT);
SDValue realBIT = DAG.getSelectCC(DL, REM, RHS, BIT, zero, ISD::SETGE);
DIV_Lo = DAG.getNode(ISD::OR, DL, HalfVT, DIV_Lo, realBIT);
// Update REM
SDValue REM_sub = DAG.getNode(ISD::SUB, DL, VT, REM, RHS);
REM = DAG.getSelectCC(DL, REM, RHS, REM_sub, REM, ISD::SETGE);
REM_Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, REM, zero);
REM_Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, HalfVT, REM, one);
}
SDValue REM = DAG.getNode(ISD::BUILD_PAIR, DL, VT, REM_Lo, REM_Hi);
SDValue DIV = DAG.getNode(ISD::BUILD_PAIR, DL, VT, DIV_Lo, DIV_Hi);
Results.push_back(DIV);
Results.push_back(REM);
break;

84
llvm/test/CodeGen/R600/udivrem64.ll Normal file
View File

@ -0,0 +1,84 @@
;XUN: llc < %s -march=r600 -mcpu=SI | FileCheck --check-prefix=SI --check-prefix=FUNC %s
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG --check-prefix=FUNC %s
;FUNC-LABEL: @test_udiv
;EG: RECIP_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;SI: S_ENDPGM
define void @test_udiv(i64 addrspace(1)* %out, i64 %x, i64 %y) {
%result = udiv i64 %x, %y
store i64 %result, i64 addrspace(1)* %out
ret void
}
;FUNC-LABEL: @test_urem
;EG: RECIP_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;EG: BFE_UINT
;SI: S_ENDPGM
define void @test_urem(i64 addrspace(1)* %out, i64 %x, i64 %y) {
%result = urem i64 %x, %y
store i64 %result, i64 addrspace(1)* %out
ret void
}