2012-12-12 05:25:42 +08:00
|
|
|
//===-- SIISelLowering.cpp - SI DAG Lowering Implementation ---------------===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
/// \file
|
|
|
|
/// \brief Custom DAG lowering for SI
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2014-07-20 19:15:07 +08:00
|
|
|
#ifdef _MSC_VER
|
|
|
|
// Provide M_PI.
|
|
|
|
#define _USE_MATH_DEFINES
|
|
|
|
#include <cmath>
|
|
|
|
#endif
|
|
|
|
|
2013-03-07 17:04:14 +08:00
|
|
|
#include "AMDGPU.h"
|
2014-06-24 02:00:31 +08:00
|
|
|
#include "AMDGPUIntrinsicInfo.h"
|
2014-02-25 05:01:28 +08:00
|
|
|
#include "AMDGPUSubtarget.h"
|
2016-04-18 17:17:29 +08:00
|
|
|
#include "SIISelLowering.h"
|
2012-12-12 05:25:42 +08:00
|
|
|
#include "SIInstrInfo.h"
|
|
|
|
#include "SIMachineFunctionInfo.h"
|
|
|
|
#include "SIRegisterInfo.h"
|
2014-08-28 03:36:53 +08:00
|
|
|
#include "llvm/ADT/BitVector.h"
|
2016-01-26 12:29:24 +08:00
|
|
|
#include "llvm/ADT/StringSwitch.h"
|
2013-03-07 17:03:52 +08:00
|
|
|
#include "llvm/CodeGen/CallingConvLower.h"
|
2012-12-12 05:25:42 +08:00
|
|
|
#include "llvm/CodeGen/MachineInstrBuilder.h"
|
|
|
|
#include "llvm/CodeGen/MachineRegisterInfo.h"
|
|
|
|
#include "llvm/CodeGen/SelectionDAG.h"
|
2016-02-02 21:52:43 +08:00
|
|
|
#include "llvm/IR/DiagnosticInfo.h"
|
2013-05-24 01:10:37 +08:00
|
|
|
#include "llvm/IR/Function.h"
|
2012-12-12 05:25:42 +08:00
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
// -amdgpu-fast-fdiv - Command line option to enable faster 2.5 ulp fdiv.
|
|
|
|
static cl::opt<bool> EnableAMDGPUFastFDIV(
|
2016-06-10 10:18:02 +08:00
|
|
|
"amdgpu-fast-fdiv",
|
|
|
|
cl::desc("Enable faster 2.5 ulp fdiv"),
|
2016-06-10 03:17:15 +08:00
|
|
|
cl::init(false));
|
|
|
|
|
2016-04-15 00:27:03 +08:00
|
|
|
static unsigned findFirstFreeSGPR(CCState &CCInfo) {
|
|
|
|
unsigned NumSGPRs = AMDGPU::SGPR_32RegClass.getNumRegs();
|
|
|
|
for (unsigned Reg = 0; Reg < NumSGPRs; ++Reg) {
|
|
|
|
if (!CCInfo.isAllocated(AMDGPU::SGPR0 + Reg)) {
|
|
|
|
return AMDGPU::SGPR0 + Reg;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
llvm_unreachable("Cannot allocate sgpr");
|
|
|
|
}
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
SITargetLowering::SITargetLowering(const TargetMachine &TM,
|
|
|
|
const SISubtarget &STI)
|
2015-01-31 07:24:40 +08:00
|
|
|
: AMDGPUTargetLowering(TM, STI) {
|
2014-04-30 23:31:33 +08:00
|
|
|
addRegisterClass(MVT::i1, &AMDGPU::VReg_1RegClass);
|
2014-05-15 22:41:57 +08:00
|
|
|
addRegisterClass(MVT::i64, &AMDGPU::SReg_64RegClass);
|
2013-03-07 17:03:38 +08:00
|
|
|
|
2014-04-18 05:00:09 +08:00
|
|
|
addRegisterClass(MVT::i32, &AMDGPU::SReg_32RegClass);
|
2015-01-08 04:59:25 +08:00
|
|
|
addRegisterClass(MVT::f32, &AMDGPU::VGPR_32RegClass);
|
2012-12-12 05:25:42 +08:00
|
|
|
|
2014-05-15 22:41:57 +08:00
|
|
|
addRegisterClass(MVT::f64, &AMDGPU::VReg_64RegClass);
|
|
|
|
addRegisterClass(MVT::v2i32, &AMDGPU::SReg_64RegClass);
|
|
|
|
addRegisterClass(MVT::v2f32, &AMDGPU::VReg_64RegClass);
|
2013-03-07 17:03:38 +08:00
|
|
|
|
2015-11-26 03:58:34 +08:00
|
|
|
addRegisterClass(MVT::v2i64, &AMDGPU::SReg_128RegClass);
|
|
|
|
addRegisterClass(MVT::v2f64, &AMDGPU::SReg_128RegClass);
|
|
|
|
|
2014-05-15 22:41:57 +08:00
|
|
|
addRegisterClass(MVT::v4i32, &AMDGPU::SReg_128RegClass);
|
|
|
|
addRegisterClass(MVT::v4f32, &AMDGPU::VReg_128RegClass);
|
2013-03-07 17:03:38 +08:00
|
|
|
|
2014-11-19 04:39:39 +08:00
|
|
|
addRegisterClass(MVT::v8i32, &AMDGPU::SReg_256RegClass);
|
2013-03-07 17:03:38 +08:00
|
|
|
addRegisterClass(MVT::v8f32, &AMDGPU::VReg_256RegClass);
|
|
|
|
|
2014-11-19 04:39:39 +08:00
|
|
|
addRegisterClass(MVT::v16i32, &AMDGPU::SReg_512RegClass);
|
2013-03-07 17:03:38 +08:00
|
|
|
addRegisterClass(MVT::v16f32, &AMDGPU::VReg_512RegClass);
|
2012-12-12 05:25:42 +08:00
|
|
|
|
2015-02-26 08:00:24 +08:00
|
|
|
computeRegisterProperties(STI.getRegisterInfo());
|
2012-12-12 05:25:42 +08:00
|
|
|
|
2013-08-26 23:06:04 +08:00
|
|
|
// We need to custom lower vector stores from local memory
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::LOAD, MVT::v2i32, Custom);
|
2013-08-26 23:06:04 +08:00
|
|
|
setOperationAction(ISD::LOAD, MVT::v4i32, Custom);
|
2013-10-23 08:44:32 +08:00
|
|
|
setOperationAction(ISD::LOAD, MVT::v8i32, Custom);
|
|
|
|
setOperationAction(ISD::LOAD, MVT::v16i32, Custom);
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::LOAD, MVT::i1, Custom);
|
2013-10-23 08:44:32 +08:00
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::STORE, MVT::v2i32, Custom);
|
|
|
|
setOperationAction(ISD::STORE, MVT::v4i32, Custom);
|
2013-10-23 08:44:32 +08:00
|
|
|
setOperationAction(ISD::STORE, MVT::v8i32, Custom);
|
|
|
|
setOperationAction(ISD::STORE, MVT::v16i32, Custom);
|
2014-03-08 04:12:33 +08:00
|
|
|
setOperationAction(ISD::STORE, MVT::i1, Custom);
|
2016-05-03 04:07:26 +08:00
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::GlobalAddress, MVT::i32, Custom);
|
|
|
|
setOperationAction(ISD::GlobalAddress, MVT::i64, Custom);
|
|
|
|
setOperationAction(ISD::FrameIndex, MVT::i32, Custom);
|
|
|
|
setOperationAction(ISD::ConstantPool, MVT::v2i64, Expand);
|
2016-05-03 04:13:51 +08:00
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::SELECT, MVT::i1, Promote);
|
2014-02-05 01:18:40 +08:00
|
|
|
setOperationAction(ISD::SELECT, MVT::i64, Custom);
|
2014-03-25 00:07:30 +08:00
|
|
|
setOperationAction(ISD::SELECT, MVT::f64, Promote);
|
|
|
|
AddPromotedToType(ISD::SELECT, MVT::f64, MVT::i64);
|
2013-11-14 07:36:50 +08:00
|
|
|
|
2014-06-11 00:01:22 +08:00
|
|
|
setOperationAction(ISD::SELECT_CC, MVT::f32, Expand);
|
|
|
|
setOperationAction(ISD::SELECT_CC, MVT::i32, Expand);
|
|
|
|
setOperationAction(ISD::SELECT_CC, MVT::i64, Expand);
|
|
|
|
setOperationAction(ISD::SELECT_CC, MVT::f64, Expand);
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::SELECT_CC, MVT::i1, Expand);
|
2013-04-06 07:31:51 +08:00
|
|
|
|
2016-01-21 05:48:24 +08:00
|
|
|
setOperationAction(ISD::SETCC, MVT::i1, Promote);
|
2013-07-19 05:43:53 +08:00
|
|
|
setOperationAction(ISD::SETCC, MVT::v2i1, Expand);
|
|
|
|
setOperationAction(ISD::SETCC, MVT::v4i1, Expand);
|
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::TRUNCATE, MVT::v2i32, Expand);
|
|
|
|
setOperationAction(ISD::FP_ROUND, MVT::v2f32, Expand);
|
2014-10-22 00:25:08 +08:00
|
|
|
|
2014-04-16 09:41:30 +08:00
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v2i1, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v4i1, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v2i8, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v4i8, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v2i16, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::v4i16, Custom);
|
|
|
|
setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::Other, Custom);
|
|
|
|
|
2013-08-15 07:24:45 +08:00
|
|
|
setOperationAction(ISD::INTRINSIC_WO_CHAIN, MVT::f32, Custom);
|
|
|
|
setOperationAction(ISD::INTRINSIC_WO_CHAIN, MVT::v4f32, Custom);
|
2016-04-12 22:05:04 +08:00
|
|
|
setOperationAction(ISD::INTRINSIC_W_CHAIN, MVT::Other, Custom);
|
|
|
|
|
2014-06-24 02:00:44 +08:00
|
|
|
setOperationAction(ISD::BRCOND, MVT::Other, Custom);
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::BR_CC, MVT::i1, Expand);
|
2016-02-13 07:45:29 +08:00
|
|
|
setOperationAction(ISD::BR_CC, MVT::i32, Expand);
|
|
|
|
setOperationAction(ISD::BR_CC, MVT::i64, Expand);
|
|
|
|
setOperationAction(ISD::BR_CC, MVT::f32, Expand);
|
|
|
|
setOperationAction(ISD::BR_CC, MVT::f64, Expand);
|
2013-09-12 10:55:14 +08:00
|
|
|
|
2015-03-08 01:41:00 +08:00
|
|
|
// We only support LOAD/STORE and vector manipulation ops for vectors
|
|
|
|
// with > 4 elements.
|
2015-11-26 03:58:34 +08:00
|
|
|
for (MVT VT : {MVT::v8i32, MVT::v8f32, MVT::v16i32, MVT::v16f32, MVT::v2i64, MVT::v2f64}) {
|
2014-02-14 07:34:15 +08:00
|
|
|
for (unsigned Op = 0; Op < ISD::BUILTIN_OP_END; ++Op) {
|
2016-05-21 10:27:49 +08:00
|
|
|
switch (Op) {
|
2014-02-14 07:34:15 +08:00
|
|
|
case ISD::LOAD:
|
|
|
|
case ISD::STORE:
|
|
|
|
case ISD::BUILD_VECTOR:
|
|
|
|
case ISD::BITCAST:
|
|
|
|
case ISD::EXTRACT_VECTOR_ELT:
|
|
|
|
case ISD::INSERT_VECTOR_ELT:
|
|
|
|
case ISD::INSERT_SUBVECTOR:
|
|
|
|
case ISD::EXTRACT_SUBVECTOR:
|
2015-11-26 03:58:34 +08:00
|
|
|
case ISD::SCALAR_TO_VECTOR:
|
2014-02-14 07:34:15 +08:00
|
|
|
break;
|
2014-08-09 09:06:56 +08:00
|
|
|
case ISD::CONCAT_VECTORS:
|
|
|
|
setOperationAction(Op, VT, Custom);
|
|
|
|
break;
|
2014-02-14 07:34:15 +08:00
|
|
|
default:
|
2014-05-16 05:44:05 +08:00
|
|
|
setOperationAction(Op, VT, Expand);
|
2014-02-14 07:34:15 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-11-26 03:58:34 +08:00
|
|
|
// Most operations are naturally 32-bit vector operations. We only support
|
|
|
|
// load and store of i64 vectors, so promote v2i64 vector operations to v4i32.
|
|
|
|
for (MVT Vec64 : { MVT::v2i64, MVT::v2f64 }) {
|
|
|
|
setOperationAction(ISD::BUILD_VECTOR, Vec64, Promote);
|
|
|
|
AddPromotedToType(ISD::BUILD_VECTOR, Vec64, MVT::v4i32);
|
|
|
|
|
|
|
|
setOperationAction(ISD::EXTRACT_VECTOR_ELT, Vec64, Promote);
|
|
|
|
AddPromotedToType(ISD::EXTRACT_VECTOR_ELT, Vec64, MVT::v4i32);
|
|
|
|
|
|
|
|
setOperationAction(ISD::INSERT_VECTOR_ELT, Vec64, Promote);
|
|
|
|
AddPromotedToType(ISD::INSERT_VECTOR_ELT, Vec64, MVT::v4i32);
|
|
|
|
|
|
|
|
setOperationAction(ISD::SCALAR_TO_VECTOR, Vec64, Promote);
|
|
|
|
AddPromotedToType(ISD::SCALAR_TO_VECTOR, Vec64, MVT::v4i32);
|
|
|
|
}
|
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::VECTOR_SHUFFLE, MVT::v8i32, Expand);
|
|
|
|
setOperationAction(ISD::VECTOR_SHUFFLE, MVT::v8f32, Expand);
|
|
|
|
setOperationAction(ISD::VECTOR_SHUFFLE, MVT::v16i32, Expand);
|
|
|
|
setOperationAction(ISD::VECTOR_SHUFFLE, MVT::v16f32, Expand);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
// BUFFER/FLAT_ATOMIC_CMP_SWAP on GCN GPUs needs input marshalling,
|
|
|
|
// and output demarshalling
|
|
|
|
setOperationAction(ISD::ATOMIC_CMP_SWAP, MVT::i32, Custom);
|
|
|
|
setOperationAction(ISD::ATOMIC_CMP_SWAP, MVT::i64, Custom);
|
|
|
|
|
|
|
|
// We can't return success/failure, only the old value,
|
|
|
|
// let LLVM add the comparison
|
|
|
|
setOperationAction(ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS, MVT::i32, Expand);
|
|
|
|
setOperationAction(ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS, MVT::i64, Expand);
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
if (getSubtarget()->hasFlatAddressSpace()) {
|
2016-04-26 03:27:24 +08:00
|
|
|
setOperationAction(ISD::ADDRSPACECAST, MVT::i32, Custom);
|
|
|
|
setOperationAction(ISD::ADDRSPACECAST, MVT::i64, Custom);
|
|
|
|
}
|
|
|
|
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::BSWAP, MVT::i32, Legal);
|
|
|
|
setOperationAction(ISD::BITREVERSE, MVT::i32, Legal);
|
|
|
|
|
|
|
|
// On SI this is s_memtime and s_memrealtime on VI.
|
|
|
|
setOperationAction(ISD::READCYCLECOUNTER, MVT::i64, Legal);
|
2016-06-18 06:27:03 +08:00
|
|
|
setOperationAction(ISD::TRAP, MVT::Other, Custom);
|
2016-05-21 10:27:49 +08:00
|
|
|
|
|
|
|
setOperationAction(ISD::FMINNUM, MVT::f64, Legal);
|
|
|
|
setOperationAction(ISD::FMAXNUM, MVT::f64, Legal);
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() >= SISubtarget::SEA_ISLANDS) {
|
2016-05-21 10:27:49 +08:00
|
|
|
setOperationAction(ISD::FTRUNC, MVT::f64, Legal);
|
|
|
|
setOperationAction(ISD::FCEIL, MVT::f64, Legal);
|
|
|
|
setOperationAction(ISD::FRINT, MVT::f64, Legal);
|
|
|
|
}
|
|
|
|
|
|
|
|
setOperationAction(ISD::FFLOOR, MVT::f64, Legal);
|
|
|
|
|
|
|
|
setOperationAction(ISD::FSIN, MVT::f32, Custom);
|
|
|
|
setOperationAction(ISD::FCOS, MVT::f32, Custom);
|
|
|
|
setOperationAction(ISD::FDIV, MVT::f32, Custom);
|
|
|
|
setOperationAction(ISD::FDIV, MVT::f64, Custom);
|
|
|
|
|
2014-09-29 22:59:34 +08:00
|
|
|
setTargetDAGCombine(ISD::FADD);
|
2014-08-30 00:01:14 +08:00
|
|
|
setTargetDAGCombine(ISD::FSUB);
|
2014-11-15 04:08:52 +08:00
|
|
|
setTargetDAGCombine(ISD::FMINNUM);
|
|
|
|
setTargetDAGCombine(ISD::FMAXNUM);
|
2015-06-09 08:52:37 +08:00
|
|
|
setTargetDAGCombine(ISD::SMIN);
|
|
|
|
setTargetDAGCombine(ISD::SMAX);
|
|
|
|
setTargetDAGCombine(ISD::UMIN);
|
|
|
|
setTargetDAGCombine(ISD::UMAX);
|
2012-12-12 05:25:42 +08:00
|
|
|
setTargetDAGCombine(ISD::SETCC);
|
2015-01-07 07:00:46 +08:00
|
|
|
setTargetDAGCombine(ISD::AND);
|
2015-01-07 07:00:39 +08:00
|
|
|
setTargetDAGCombine(ISD::OR);
|
2014-06-12 01:50:44 +08:00
|
|
|
setTargetDAGCombine(ISD::UINT_TO_FP);
|
2016-04-14 09:42:16 +08:00
|
|
|
setTargetDAGCombine(ISD::FCANONICALIZE);
|
2014-06-12 01:50:44 +08:00
|
|
|
|
2014-08-16 01:49:05 +08:00
|
|
|
// All memory operations. Some folding on the pointer operand is done to help
|
|
|
|
// matching the constant offsets in the addressing modes.
|
|
|
|
setTargetDAGCombine(ISD::LOAD);
|
|
|
|
setTargetDAGCombine(ISD::STORE);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_STORE);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_CMP_SWAP);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_SWAP);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_ADD);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_SUB);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_AND);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_OR);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_XOR);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_NAND);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_MIN);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_MAX);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_UMIN);
|
|
|
|
setTargetDAGCombine(ISD::ATOMIC_LOAD_UMAX);
|
|
|
|
|
2013-03-26 22:04:02 +08:00
|
|
|
setSchedulingPreference(Sched::RegPressure);
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
const SISubtarget *SITargetLowering::getSubtarget() const {
|
|
|
|
return static_cast<const SISubtarget *>(Subtarget);
|
|
|
|
}
|
|
|
|
|
2013-06-25 10:39:35 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// TargetLowering queries
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2016-04-12 22:05:04 +08:00
|
|
|
bool SITargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
|
|
|
|
const CallInst &CI,
|
|
|
|
unsigned IntrID) const {
|
|
|
|
switch (IntrID) {
|
|
|
|
case Intrinsic::amdgcn_atomic_inc:
|
|
|
|
case Intrinsic::amdgcn_atomic_dec:
|
|
|
|
Info.opc = ISD::INTRINSIC_W_CHAIN;
|
|
|
|
Info.memVT = MVT::getVT(CI.getType());
|
|
|
|
Info.ptrVal = CI.getOperand(0);
|
|
|
|
Info.align = 0;
|
|
|
|
Info.vol = false;
|
|
|
|
Info.readMem = true;
|
|
|
|
Info.writeMem = true;
|
|
|
|
return true;
|
|
|
|
default:
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-10-22 00:25:08 +08:00
|
|
|
bool SITargetLowering::isShuffleMaskLegal(const SmallVectorImpl<int> &,
|
|
|
|
EVT) const {
|
|
|
|
// SI has some legal vector types, but no legal vector operations. Say no
|
|
|
|
// shuffles are legal in order to prefer scalarizing some vector operations.
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2015-07-20 22:28:41 +08:00
|
|
|
bool SITargetLowering::isLegalFlatAddressingMode(const AddrMode &AM) const {
|
|
|
|
// Flat instructions do not have offsets, and only have the register
|
|
|
|
// address.
|
|
|
|
return AM.BaseOffs == 0 && (AM.Scale == 0 || AM.Scale == 1);
|
|
|
|
}
|
|
|
|
|
2015-08-08 04:18:34 +08:00
|
|
|
bool SITargetLowering::isLegalMUBUFAddressingMode(const AddrMode &AM) const {
|
|
|
|
// MUBUF / MTBUF instructions have a 12-bit unsigned byte offset, and
|
|
|
|
// additionally can do r + r + i with addr64. 32-bit has more addressing
|
|
|
|
// mode options. Depending on the resource constant, it can also do
|
|
|
|
// (i64 r0) + (i32 r1) * (i14 i).
|
|
|
|
//
|
|
|
|
// Private arrays end up using a scratch buffer most of the time, so also
|
|
|
|
// assume those use MUBUF instructions. Scratch loads / stores are currently
|
|
|
|
// implemented as mubuf instructions with offen bit set, so slightly
|
|
|
|
// different than the normal addr64.
|
|
|
|
if (!isUInt<12>(AM.BaseOffs))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
// FIXME: Since we can split immediate into soffset and immediate offset,
|
|
|
|
// would it make sense to allow any immediate?
|
|
|
|
|
|
|
|
switch (AM.Scale) {
|
|
|
|
case 0: // r + i or just i, depending on HasBaseReg.
|
|
|
|
return true;
|
|
|
|
case 1:
|
|
|
|
return true; // We have r + r or r + i.
|
|
|
|
case 2:
|
|
|
|
if (AM.HasBaseReg) {
|
|
|
|
// Reject 2 * r + r.
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Allow 2 * r as r + r
|
|
|
|
// Or 2 * r + i is allowed as r + r + i.
|
|
|
|
return true;
|
|
|
|
default: // Don't allow n * r
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-07-09 10:09:40 +08:00
|
|
|
bool SITargetLowering::isLegalAddressingMode(const DataLayout &DL,
|
|
|
|
const AddrMode &AM, Type *Ty,
|
|
|
|
unsigned AS) const {
|
2014-08-16 01:17:07 +08:00
|
|
|
// No global is ever allowed as a base.
|
|
|
|
if (AM.BaseGV)
|
|
|
|
return false;
|
|
|
|
|
2015-06-05 00:17:42 +08:00
|
|
|
switch (AS) {
|
2015-08-08 04:18:34 +08:00
|
|
|
case AMDGPUAS::GLOBAL_ADDRESS: {
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() >= SISubtarget::VOLCANIC_ISLANDS) {
|
2015-07-20 22:28:41 +08:00
|
|
|
// Assume the we will use FLAT for all global memory accesses
|
|
|
|
// on VI.
|
|
|
|
// FIXME: This assumption is currently wrong. On VI we still use
|
|
|
|
// MUBUF instructions for the r + i addressing mode. As currently
|
|
|
|
// implemented, the MUBUF instructions only work on buffer < 4GB.
|
|
|
|
// It may be possible to support > 4GB buffers with MUBUF instructions,
|
|
|
|
// by setting the stride value in the resource descriptor which would
|
|
|
|
// increase the size limit to (stride * 4GB). However, this is risky,
|
|
|
|
// because it has never been validated.
|
|
|
|
return isLegalFlatAddressingMode(AM);
|
|
|
|
}
|
2015-06-05 00:17:42 +08:00
|
|
|
|
2015-08-08 04:18:34 +08:00
|
|
|
return isLegalMUBUFAddressingMode(AM);
|
|
|
|
}
|
|
|
|
case AMDGPUAS::CONSTANT_ADDRESS: {
|
|
|
|
// If the offset isn't a multiple of 4, it probably isn't going to be
|
|
|
|
// correctly aligned.
|
|
|
|
if (AM.BaseOffs % 4 != 0)
|
|
|
|
return isLegalMUBUFAddressingMode(AM);
|
|
|
|
|
|
|
|
// There are no SMRD extloads, so if we have to do a small type access we
|
|
|
|
// will use a MUBUF load.
|
|
|
|
// FIXME?: We also need to do this if unaligned, but we don't know the
|
|
|
|
// alignment here.
|
|
|
|
if (DL.getTypeStoreSize(Ty) < 4)
|
|
|
|
return isLegalMUBUFAddressingMode(AM);
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() == SISubtarget::SOUTHERN_ISLANDS) {
|
2015-08-08 04:18:34 +08:00
|
|
|
// SMRD instructions have an 8-bit, dword offset on SI.
|
|
|
|
if (!isUInt<8>(AM.BaseOffs / 4))
|
|
|
|
return false;
|
2016-06-24 14:30:11 +08:00
|
|
|
} else if (Subtarget->getGeneration() == SISubtarget::SEA_ISLANDS) {
|
2015-08-08 04:18:34 +08:00
|
|
|
// On CI+, this can also be a 32-bit literal constant offset. If it fits
|
|
|
|
// in 8-bits, it can use a smaller encoding.
|
|
|
|
if (!isUInt<32>(AM.BaseOffs / 4))
|
|
|
|
return false;
|
2016-06-24 14:30:11 +08:00
|
|
|
} else if (Subtarget->getGeneration() == SISubtarget::VOLCANIC_ISLANDS) {
|
2015-08-08 04:18:34 +08:00
|
|
|
// On VI, these use the SMEM format and the offset is 20-bit in bytes.
|
|
|
|
if (!isUInt<20>(AM.BaseOffs))
|
|
|
|
return false;
|
|
|
|
} else
|
|
|
|
llvm_unreachable("unhandled generation");
|
2015-06-05 00:17:42 +08:00
|
|
|
|
2015-08-08 04:18:34 +08:00
|
|
|
if (AM.Scale == 0) // r + i or just i, depending on HasBaseReg.
|
2015-06-05 00:17:42 +08:00
|
|
|
return true;
|
2014-08-16 01:17:07 +08:00
|
|
|
|
2015-08-08 04:18:34 +08:00
|
|
|
if (AM.Scale == 1 && AM.HasBaseReg)
|
2015-06-05 00:17:42 +08:00
|
|
|
return true;
|
2015-08-08 04:18:34 +08:00
|
|
|
|
|
|
|
return false;
|
2015-06-05 00:17:42 +08:00
|
|
|
}
|
2015-08-08 04:18:34 +08:00
|
|
|
|
|
|
|
case AMDGPUAS::PRIVATE_ADDRESS:
|
|
|
|
return isLegalMUBUFAddressingMode(AM);
|
|
|
|
|
2015-06-05 00:17:42 +08:00
|
|
|
case AMDGPUAS::LOCAL_ADDRESS:
|
|
|
|
case AMDGPUAS::REGION_ADDRESS: {
|
|
|
|
// Basic, single offset DS instructions allow a 16-bit unsigned immediate
|
|
|
|
// field.
|
|
|
|
// XXX - If doing a 4-byte aligned 8-byte type access, we effectively have
|
|
|
|
// an 8-bit dword offset but we don't know the alignment here.
|
|
|
|
if (!isUInt<16>(AM.BaseOffs))
|
2014-08-16 01:17:07 +08:00
|
|
|
return false;
|
2015-06-05 00:17:42 +08:00
|
|
|
|
|
|
|
if (AM.Scale == 0) // r + i or just i, depending on HasBaseReg.
|
|
|
|
return true;
|
|
|
|
|
|
|
|
if (AM.Scale == 1 && AM.HasBaseReg)
|
|
|
|
return true;
|
|
|
|
|
2014-08-16 01:17:07 +08:00
|
|
|
return false;
|
|
|
|
}
|
2015-07-20 22:28:41 +08:00
|
|
|
case AMDGPUAS::FLAT_ADDRESS:
|
2016-04-29 14:25:10 +08:00
|
|
|
case AMDGPUAS::UNKNOWN_ADDRESS_SPACE:
|
|
|
|
// For an unknown address space, this usually means that this is for some
|
|
|
|
// reason being used for pure arithmetic, and not based on some addressing
|
|
|
|
// computation. We don't have instructions that compute pointers with any
|
|
|
|
// addressing modes, so treat them as having no offset like flat
|
|
|
|
// instructions.
|
2015-07-20 22:28:41 +08:00
|
|
|
return isLegalFlatAddressingMode(AM);
|
|
|
|
|
2015-06-05 00:17:42 +08:00
|
|
|
default:
|
|
|
|
llvm_unreachable("unhandled address space");
|
|
|
|
}
|
2014-08-16 01:17:07 +08:00
|
|
|
}
|
|
|
|
|
2015-01-14 09:35:22 +08:00
|
|
|
bool SITargetLowering::allowsMisalignedMemoryAccesses(EVT VT,
|
2014-07-28 01:46:40 +08:00
|
|
|
unsigned AddrSpace,
|
|
|
|
unsigned Align,
|
|
|
|
bool *IsFast) const {
|
2014-04-25 01:08:26 +08:00
|
|
|
if (IsFast)
|
|
|
|
*IsFast = false;
|
|
|
|
|
|
|
|
// TODO: I think v3i32 should allow unaligned accesses on CI with DS_READ_B96,
|
|
|
|
// which isn't a simple VT.
|
2013-11-14 07:36:50 +08:00
|
|
|
if (!VT.isSimple() || VT == MVT::Other)
|
|
|
|
return false;
|
2014-04-25 01:08:26 +08:00
|
|
|
|
2016-07-02 07:03:44 +08:00
|
|
|
if (AddrSpace == AMDGPUAS::LOCAL_ADDRESS ||
|
|
|
|
AddrSpace == AMDGPUAS::REGION_ADDRESS) {
|
2014-07-28 01:46:40 +08:00
|
|
|
// ds_read/write_b64 require 8-byte alignment, but we can do a 4 byte
|
|
|
|
// aligned, 8 byte access in a single operation using ds_read2/write2_b32
|
|
|
|
// with adjacent offsets.
|
2015-09-03 23:03:19 +08:00
|
|
|
bool AlignedBy4 = (Align % 4 == 0);
|
|
|
|
if (IsFast)
|
|
|
|
*IsFast = AlignedBy4;
|
2016-07-02 07:03:44 +08:00
|
|
|
|
2015-09-03 23:03:19 +08:00
|
|
|
return AlignedBy4;
|
2014-07-28 01:46:40 +08:00
|
|
|
}
|
2014-04-25 01:08:26 +08:00
|
|
|
|
2016-07-02 07:03:44 +08:00
|
|
|
if (Subtarget->hasUnalignedBufferAccess()) {
|
|
|
|
// If we have an uniform constant load, it still requires using a slow
|
|
|
|
// buffer instruction if unaligned.
|
|
|
|
if (IsFast) {
|
|
|
|
*IsFast = (AddrSpace == AMDGPUAS::CONSTANT_ADDRESS) ?
|
|
|
|
(Align % 4 == 0) : true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2015-02-05 04:49:52 +08:00
|
|
|
// Smaller than dword value must be aligned.
|
|
|
|
if (VT.bitsLT(MVT::i32))
|
|
|
|
return false;
|
|
|
|
|
2014-04-25 01:08:26 +08:00
|
|
|
// 8.1.6 - For Dword or larger reads or writes, the two LSBs of the
|
|
|
|
// byte-address are ignored, thus forcing Dword alignment.
|
2014-07-21 23:45:06 +08:00
|
|
|
// This applies to private, global, and constant memory.
|
2014-04-25 01:08:26 +08:00
|
|
|
if (IsFast)
|
|
|
|
*IsFast = true;
|
2015-02-03 02:02:28 +08:00
|
|
|
|
|
|
|
return VT.bitsGT(MVT::i32) && Align % 4 == 0;
|
2013-06-25 10:39:35 +08:00
|
|
|
}
|
|
|
|
|
2014-07-29 01:49:26 +08:00
|
|
|
EVT SITargetLowering::getOptimalMemOpType(uint64_t Size, unsigned DstAlign,
|
|
|
|
unsigned SrcAlign, bool IsMemset,
|
|
|
|
bool ZeroMemset,
|
|
|
|
bool MemcpyStrSrc,
|
|
|
|
MachineFunction &MF) const {
|
|
|
|
// FIXME: Should account for address space here.
|
|
|
|
|
|
|
|
// The default fallback uses the private pointer size as a guess for a type to
|
|
|
|
// use. Make sure we switch these to 64-bit accesses.
|
|
|
|
|
|
|
|
if (Size >= 16 && DstAlign >= 4) // XXX: Should only do for global
|
|
|
|
return MVT::v4i32;
|
|
|
|
|
|
|
|
if (Size >= 8 && DstAlign >= 4)
|
|
|
|
return MVT::v2i32;
|
|
|
|
|
|
|
|
// Use the default.
|
|
|
|
return MVT::Other;
|
|
|
|
}
|
|
|
|
|
2015-12-02 07:04:00 +08:00
|
|
|
static bool isFlatGlobalAddrSpace(unsigned AS) {
|
|
|
|
return AS == AMDGPUAS::GLOBAL_ADDRESS ||
|
|
|
|
AS == AMDGPUAS::FLAT_ADDRESS ||
|
|
|
|
AS == AMDGPUAS::CONSTANT_ADDRESS;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool SITargetLowering::isNoopAddrSpaceCast(unsigned SrcAS,
|
|
|
|
unsigned DestAS) const {
|
2016-06-10 10:18:02 +08:00
|
|
|
return isFlatGlobalAddrSpace(SrcAS) && isFlatGlobalAddrSpace(DestAS);
|
2015-12-02 07:04:00 +08:00
|
|
|
}
|
|
|
|
|
2015-12-16 04:55:55 +08:00
|
|
|
bool SITargetLowering::isMemOpUniform(const SDNode *N) const {
|
|
|
|
const MemSDNode *MemNode = cast<MemSDNode>(N);
|
|
|
|
const Value *Ptr = MemNode->getMemOperand()->getValue();
|
|
|
|
|
|
|
|
// UndefValue means this is a load of a kernel input. These are uniform.
|
|
|
|
// Sometimes LDS instructions have constant pointers
|
|
|
|
if (isa<UndefValue>(Ptr) || isa<Argument>(Ptr) || isa<Constant>(Ptr) ||
|
|
|
|
isa<GlobalValue>(Ptr))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
const Instruction *I = dyn_cast_or_null<Instruction>(Ptr);
|
|
|
|
return I && I->getMetadata("amdgpu.uniform");
|
|
|
|
}
|
|
|
|
|
2014-07-03 08:23:43 +08:00
|
|
|
TargetLoweringBase::LegalizeTypeAction
|
|
|
|
SITargetLowering::getPreferredVectorAction(EVT VT) const {
|
|
|
|
if (VT.getVectorNumElements() != 1 && VT.getScalarType().bitsLE(MVT::i16))
|
|
|
|
return TypeSplitVector;
|
|
|
|
|
|
|
|
return TargetLoweringBase::getPreferredVectorAction(VT);
|
2013-08-15 07:25:00 +08:00
|
|
|
}
|
2013-06-25 10:39:35 +08:00
|
|
|
|
2014-04-01 03:54:27 +08:00
|
|
|
bool SITargetLowering::shouldConvertConstantLoadToIntImm(const APInt &Imm,
|
|
|
|
Type *Ty) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2014-04-01 03:54:27 +08:00
|
|
|
return TII->isInlineConstant(Imm);
|
|
|
|
}
|
|
|
|
|
2016-01-20 08:13:22 +08:00
|
|
|
bool SITargetLowering::isTypeDesirableForOp(unsigned Op, EVT VT) const {
|
|
|
|
|
|
|
|
// SimplifySetCC uses this function to determine whether or not it should
|
|
|
|
// create setcc with i1 operands. We don't have instructions for i1 setcc.
|
|
|
|
if (VT == MVT::i1 && Op == ISD::SETCC)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return TargetLowering::isTypeDesirableForOp(Op, VT);
|
|
|
|
}
|
|
|
|
|
2016-06-22 04:46:20 +08:00
|
|
|
SDValue SITargetLowering::LowerParameterPtr(SelectionDAG &DAG,
|
|
|
|
const SDLoc &SL, SDValue Chain,
|
|
|
|
unsigned Offset) const {
|
2015-07-09 10:09:52 +08:00
|
|
|
const DataLayout &DL = DAG.getDataLayout();
|
2014-09-22 23:35:29 +08:00
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIRegisterInfo *TRI = getSubtarget()->getRegisterInfo();
|
2015-12-01 05:15:57 +08:00
|
|
|
unsigned InputPtrReg = TRI->getPreloadedValue(MF, SIRegisterInfo::KERNARG_SEGMENT_PTR);
|
2014-07-29 01:31:39 +08:00
|
|
|
|
2013-06-04 01:40:18 +08:00
|
|
|
MachineRegisterInfo &MRI = DAG.getMachineFunction().getRegInfo();
|
2015-07-09 10:09:52 +08:00
|
|
|
MVT PtrVT = getPointerTy(DL, AMDGPUAS::CONSTANT_ADDRESS);
|
2015-06-02 05:58:24 +08:00
|
|
|
SDValue BasePtr = DAG.getCopyFromReg(Chain, SL,
|
|
|
|
MRI.getLiveInVirtReg(InputPtrReg), PtrVT);
|
2016-06-22 04:46:20 +08:00
|
|
|
return DAG.getNode(ISD::ADD, SL, PtrVT, BasePtr,
|
|
|
|
DAG.getConstant(Offset, SL, PtrVT));
|
|
|
|
}
|
|
|
|
SDValue SITargetLowering::LowerParameter(SelectionDAG &DAG, EVT VT, EVT MemVT,
|
|
|
|
const SDLoc &SL, SDValue Chain,
|
|
|
|
unsigned Offset, bool Signed) const {
|
|
|
|
const DataLayout &DL = DAG.getDataLayout();
|
|
|
|
Type *Ty = VT.getTypeForEVT(*DAG.getContext());
|
|
|
|
MVT PtrVT = getPointerTy(DL, AMDGPUAS::CONSTANT_ADDRESS);
|
|
|
|
PointerType *PtrTy = PointerType::get(Ty, AMDGPUAS::CONSTANT_ADDRESS);
|
2015-07-09 10:09:04 +08:00
|
|
|
SDValue PtrOffset = DAG.getUNDEF(PtrVT);
|
2014-07-29 01:31:39 +08:00
|
|
|
MachinePointerInfo PtrInfo(UndefValue::get(PtrTy));
|
|
|
|
|
2015-07-09 10:09:52 +08:00
|
|
|
unsigned Align = DL.getABITypeAlignment(Ty);
|
2015-06-05 00:00:27 +08:00
|
|
|
|
|
|
|
ISD::LoadExtType ExtTy = Signed ? ISD::SEXTLOAD : ISD::ZEXTLOAD;
|
2015-09-09 09:12:27 +08:00
|
|
|
if (MemVT.isFloatingPoint())
|
|
|
|
ExtTy = ISD::EXTLOAD;
|
|
|
|
|
2016-06-22 04:46:20 +08:00
|
|
|
SDValue Ptr = LowerParameterPtr(DAG, SL, Chain, Offset);
|
2015-06-05 00:00:27 +08:00
|
|
|
return DAG.getLoad(ISD::UNINDEXED, ExtTy,
|
2014-07-29 01:31:39 +08:00
|
|
|
VT, SL, Chain, Ptr, PtrOffset, PtrInfo, MemVT,
|
|
|
|
false, // isVolatile
|
|
|
|
true, // isNonTemporal
|
|
|
|
true, // isInvariant
|
2015-06-05 00:00:27 +08:00
|
|
|
Align); // Alignment
|
2013-06-04 01:40:18 +08:00
|
|
|
}
|
|
|
|
|
2013-03-07 17:03:52 +08:00
|
|
|
SDValue SITargetLowering::LowerFormalArguments(
|
2015-01-31 07:24:40 +08:00
|
|
|
SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
|
2016-06-12 23:39:02 +08:00
|
|
|
const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &DL,
|
|
|
|
SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIRegisterInfo *TRI = getSubtarget()->getRegisterInfo();
|
2013-03-07 17:03:52 +08:00
|
|
|
|
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
FunctionType *FType = MF.getFunction()->getFunctionType();
|
2013-03-07 17:04:14 +08:00
|
|
|
SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
|
2016-06-24 14:30:11 +08:00
|
|
|
const SISubtarget &ST = MF.getSubtarget<SISubtarget>();
|
2013-03-07 17:03:52 +08:00
|
|
|
|
2016-04-07 03:40:20 +08:00
|
|
|
if (Subtarget->isAmdHsaOS() && AMDGPU::isShader(CallConv)) {
|
2015-11-03 07:23:02 +08:00
|
|
|
const Function *Fn = MF.getFunction();
|
2016-02-02 21:52:43 +08:00
|
|
|
DiagnosticInfoUnsupported NoGraphicsHSA(
|
|
|
|
*Fn, "unsupported non-compute shaders with HSA", DL.getDebugLoc());
|
2015-11-03 07:23:02 +08:00
|
|
|
DAG.getContext()->diagnose(NoGraphicsHSA);
|
2016-05-26 23:24:55 +08:00
|
|
|
return DAG.getEntryNode();
|
2015-11-03 07:23:02 +08:00
|
|
|
}
|
|
|
|
|
2016-06-25 11:11:28 +08:00
|
|
|
// Create stack objects that are used for emitting debugger prologue if
|
|
|
|
// "amdgpu-debugger-emit-prologue" attribute was specified.
|
|
|
|
if (ST.debuggerEmitPrologue())
|
|
|
|
createDebuggerPrologueStackObjects(MF);
|
|
|
|
|
2013-03-07 17:03:52 +08:00
|
|
|
SmallVector<ISD::InputArg, 16> Splits;
|
2014-08-28 03:36:53 +08:00
|
|
|
BitVector Skipped(Ins.size());
|
2013-03-07 17:04:14 +08:00
|
|
|
|
|
|
|
for (unsigned i = 0, e = Ins.size(), PSInputNum = 0; i != e; ++i) {
|
2013-03-07 17:03:52 +08:00
|
|
|
const ISD::InputArg &Arg = Ins[i];
|
2013-05-18 08:21:46 +08:00
|
|
|
|
|
|
|
// First check if it's a PS input addr
|
2016-04-07 03:40:20 +08:00
|
|
|
if (CallConv == CallingConv::AMDGPU_PS && !Arg.Flags.isInReg() &&
|
2016-01-13 19:46:10 +08:00
|
|
|
!Arg.Flags.isByVal() && PSInputNum <= 15) {
|
2013-03-07 17:04:14 +08:00
|
|
|
|
2016-01-13 19:45:36 +08:00
|
|
|
if (!Arg.Used && !Info->isPSInputAllocated(PSInputNum)) {
|
2015-08-09 02:27:36 +08:00
|
|
|
// We can safely skip PS inputs
|
2014-08-28 03:36:53 +08:00
|
|
|
Skipped.set(i);
|
2013-03-07 17:04:14 +08:00
|
|
|
++PSInputNum;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2016-01-13 19:45:36 +08:00
|
|
|
Info->markPSInputAllocated(PSInputNum);
|
|
|
|
if (Arg.Used)
|
|
|
|
Info->PSInputEna |= 1 << PSInputNum;
|
|
|
|
|
|
|
|
++PSInputNum;
|
2013-03-07 17:04:14 +08:00
|
|
|
}
|
|
|
|
|
2016-05-06 04:27:02 +08:00
|
|
|
if (AMDGPU::isShader(CallConv)) {
|
|
|
|
// Second split vertices into their elements
|
|
|
|
if (Arg.VT.isVector()) {
|
|
|
|
ISD::InputArg NewArg = Arg;
|
|
|
|
NewArg.Flags.setSplit();
|
|
|
|
NewArg.VT = Arg.VT.getVectorElementType();
|
|
|
|
|
|
|
|
// We REALLY want the ORIGINAL number of vertex elements here, e.g. a
|
|
|
|
// three or five element vertex only needs three or five registers,
|
|
|
|
// NOT four or eight.
|
|
|
|
Type *ParamType = FType->getParamType(Arg.getOrigArgIndex());
|
|
|
|
unsigned NumElements = ParamType->getVectorNumElements();
|
|
|
|
|
|
|
|
for (unsigned j = 0; j != NumElements; ++j) {
|
|
|
|
Splits.push_back(NewArg);
|
|
|
|
NewArg.PartOffset += NewArg.VT.getStoreSize();
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
Splits.push_back(Arg);
|
2013-03-07 17:03:52 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
SmallVector<CCValAssign, 16> ArgLocs;
|
2014-08-07 02:45:26 +08:00
|
|
|
CCState CCInfo(CallConv, isVarArg, DAG.getMachineFunction(), ArgLocs,
|
|
|
|
*DAG.getContext());
|
2013-03-07 17:03:52 +08:00
|
|
|
|
2013-03-07 17:04:14 +08:00
|
|
|
// At least one interpolation mode must be enabled or else the GPU will hang.
|
2016-01-13 19:45:36 +08:00
|
|
|
//
|
|
|
|
// Check PSInputAddr instead of PSInputEna. The idea is that if the user set
|
|
|
|
// PSInputAddr, the user wants to enable some bits after the compilation
|
|
|
|
// based on run-time states. Since we can't know what the final PSInputEna
|
|
|
|
// will look like, so we shouldn't do anything here and the user should take
|
|
|
|
// responsibility for the correct programming.
|
2016-01-14 01:23:20 +08:00
|
|
|
//
|
|
|
|
// Otherwise, the following restrictions apply:
|
|
|
|
// - At least one of PERSP_* (0xF) or LINEAR_* (0x70) must be enabled.
|
|
|
|
// - If POS_W_FLOAT (11) is enabled, at least one of PERSP_* must be
|
|
|
|
// enabled too.
|
2016-04-07 03:40:20 +08:00
|
|
|
if (CallConv == CallingConv::AMDGPU_PS &&
|
2016-01-14 01:23:20 +08:00
|
|
|
((Info->getPSInputAddr() & 0x7F) == 0 ||
|
2016-06-20 08:37:41 +08:00
|
|
|
((Info->getPSInputAddr() & 0xF) == 0 && Info->isPSInputAllocated(11)))) {
|
2013-03-07 17:04:14 +08:00
|
|
|
CCInfo.AllocateReg(AMDGPU::VGPR0);
|
|
|
|
CCInfo.AllocateReg(AMDGPU::VGPR1);
|
2016-01-13 19:45:36 +08:00
|
|
|
Info->markPSInputAllocated(0);
|
|
|
|
Info->PSInputEna |= 1;
|
2013-03-07 17:04:14 +08:00
|
|
|
}
|
|
|
|
|
2016-04-07 03:40:20 +08:00
|
|
|
if (!AMDGPU::isShader(CallConv)) {
|
2015-12-01 05:16:03 +08:00
|
|
|
getOriginalFunctionArgs(DAG, DAG.getMachineFunction().getFunction(), Ins,
|
|
|
|
Splits);
|
2016-04-15 00:27:03 +08:00
|
|
|
|
|
|
|
assert(Info->hasWorkGroupIDX() && Info->hasWorkItemIDX());
|
|
|
|
} else {
|
|
|
|
assert(!Info->hasPrivateSegmentBuffer() && !Info->hasDispatchPtr() &&
|
|
|
|
!Info->hasKernargSegmentPtr() && !Info->hasFlatScratchInit() &&
|
|
|
|
!Info->hasWorkGroupIDX() && !Info->hasWorkGroupIDY() &&
|
|
|
|
!Info->hasWorkGroupIDZ() && !Info->hasWorkGroupInfo() &&
|
|
|
|
!Info->hasWorkItemIDX() && !Info->hasWorkItemIDY() &&
|
|
|
|
!Info->hasWorkItemIDZ());
|
2015-12-01 05:16:03 +08:00
|
|
|
}
|
2015-11-30 23:46:47 +08:00
|
|
|
|
2015-12-01 05:16:03 +08:00
|
|
|
// FIXME: How should these inputs interact with inreg / custom SGPR inputs?
|
|
|
|
if (Info->hasPrivateSegmentBuffer()) {
|
|
|
|
unsigned PrivateSegmentBufferReg = Info->addPrivateSegmentBuffer(*TRI);
|
|
|
|
MF.addLiveIn(PrivateSegmentBufferReg, &AMDGPU::SReg_128RegClass);
|
|
|
|
CCInfo.AllocateReg(PrivateSegmentBufferReg);
|
|
|
|
}
|
2015-11-30 23:46:47 +08:00
|
|
|
|
2015-12-01 05:16:03 +08:00
|
|
|
if (Info->hasDispatchPtr()) {
|
|
|
|
unsigned DispatchPtrReg = Info->addDispatchPtr(*TRI);
|
|
|
|
MF.addLiveIn(DispatchPtrReg, &AMDGPU::SReg_64RegClass);
|
|
|
|
CCInfo.AllocateReg(DispatchPtrReg);
|
2013-06-04 01:40:11 +08:00
|
|
|
}
|
|
|
|
|
2016-04-26 03:27:18 +08:00
|
|
|
if (Info->hasQueuePtr()) {
|
|
|
|
unsigned QueuePtrReg = Info->addQueuePtr(*TRI);
|
|
|
|
MF.addLiveIn(QueuePtrReg, &AMDGPU::SReg_64RegClass);
|
|
|
|
CCInfo.AllocateReg(QueuePtrReg);
|
|
|
|
}
|
|
|
|
|
2015-12-01 05:16:03 +08:00
|
|
|
if (Info->hasKernargSegmentPtr()) {
|
|
|
|
unsigned InputPtrReg = Info->addKernargSegmentPtr(*TRI);
|
|
|
|
MF.addLiveIn(InputPtrReg, &AMDGPU::SReg_64RegClass);
|
|
|
|
CCInfo.AllocateReg(InputPtrReg);
|
2013-10-23 08:44:32 +08:00
|
|
|
}
|
|
|
|
|
2016-02-12 14:31:30 +08:00
|
|
|
if (Info->hasFlatScratchInit()) {
|
|
|
|
unsigned FlatScratchInitReg = Info->addFlatScratchInit(*TRI);
|
|
|
|
MF.addLiveIn(FlatScratchInitReg, &AMDGPU::SReg_64RegClass);
|
|
|
|
CCInfo.AllocateReg(FlatScratchInitReg);
|
|
|
|
}
|
|
|
|
|
2013-03-07 17:03:52 +08:00
|
|
|
AnalyzeFormalArguments(CCInfo, Splits);
|
|
|
|
|
2015-07-11 06:51:36 +08:00
|
|
|
SmallVector<SDValue, 16> Chains;
|
|
|
|
|
2013-03-07 17:03:52 +08:00
|
|
|
for (unsigned i = 0, e = Ins.size(), ArgIdx = 0; i != e; ++i) {
|
|
|
|
|
2013-05-17 17:46:48 +08:00
|
|
|
const ISD::InputArg &Arg = Ins[i];
|
2014-08-28 03:36:53 +08:00
|
|
|
if (Skipped[i]) {
|
2013-05-17 17:46:48 +08:00
|
|
|
InVals.push_back(DAG.getUNDEF(Arg.VT));
|
2013-03-07 17:04:14 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2013-03-07 17:03:52 +08:00
|
|
|
CCValAssign &VA = ArgLocs[ArgIdx++];
|
2014-11-17 05:17:18 +08:00
|
|
|
MVT VT = VA.getLocVT();
|
2013-06-04 01:40:11 +08:00
|
|
|
|
|
|
|
if (VA.isMemLoc()) {
|
2013-10-23 08:44:32 +08:00
|
|
|
VT = Ins[i].VT;
|
|
|
|
EVT MemVT = Splits[i].VT;
|
2015-06-27 05:15:03 +08:00
|
|
|
const unsigned Offset = Subtarget->getExplicitKernelArgOffset() +
|
|
|
|
VA.getLocMemOffset();
|
2013-06-04 01:40:18 +08:00
|
|
|
// The first 36 bytes of the input buffer contains information about
|
|
|
|
// thread group and global sizes.
|
2015-07-11 06:28:41 +08:00
|
|
|
SDValue Arg = LowerParameter(DAG, VT, MemVT, DL, Chain,
|
2014-10-15 04:05:26 +08:00
|
|
|
Offset, Ins[i].Flags.isSExt());
|
2015-07-11 06:51:36 +08:00
|
|
|
Chains.push_back(Arg.getValue(1));
|
2014-08-23 02:49:31 +08:00
|
|
|
|
2015-08-02 06:20:21 +08:00
|
|
|
auto *ParamTy =
|
2015-02-17 02:10:47 +08:00
|
|
|
dyn_cast<PointerType>(FType->getParamType(Ins[i].getOrigArgIndex()));
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() == SISubtarget::SOUTHERN_ISLANDS &&
|
2014-08-23 02:49:31 +08:00
|
|
|
ParamTy && ParamTy->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS) {
|
|
|
|
// On SI local pointers are just offsets into LDS, so they are always
|
|
|
|
// less than 16-bits. On CI and newer they could potentially be
|
|
|
|
// real pointers, so we can't guarantee their size.
|
|
|
|
Arg = DAG.getNode(ISD::AssertZext, DL, Arg.getValueType(), Arg,
|
|
|
|
DAG.getValueType(MVT::i16));
|
|
|
|
}
|
|
|
|
|
2013-06-04 01:40:11 +08:00
|
|
|
InVals.push_back(Arg);
|
2014-10-15 04:05:26 +08:00
|
|
|
Info->ABIArgOffset = Offset + MemVT.getStoreSize();
|
2013-06-04 01:40:11 +08:00
|
|
|
continue;
|
|
|
|
}
|
2013-03-07 17:03:52 +08:00
|
|
|
assert(VA.isRegLoc() && "Parameter must be in a register!");
|
|
|
|
|
|
|
|
unsigned Reg = VA.getLocReg();
|
|
|
|
|
|
|
|
if (VT == MVT::i64) {
|
|
|
|
// For now assume it is a pointer
|
|
|
|
Reg = TRI->getMatchingSuperReg(Reg, AMDGPU::sub0,
|
|
|
|
&AMDGPU::SReg_64RegClass);
|
|
|
|
Reg = MF.addLiveIn(Reg, &AMDGPU::SReg_64RegClass);
|
2015-07-11 06:51:36 +08:00
|
|
|
SDValue Copy = DAG.getCopyFromReg(Chain, DL, Reg, VT);
|
|
|
|
InVals.push_back(Copy);
|
2013-03-07 17:03:52 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
const TargetRegisterClass *RC = TRI->getMinimalPhysRegClass(Reg, VT);
|
|
|
|
|
|
|
|
Reg = MF.addLiveIn(Reg, RC);
|
|
|
|
SDValue Val = DAG.getCopyFromReg(Chain, DL, Reg, VT);
|
|
|
|
|
|
|
|
if (Arg.VT.isVector()) {
|
|
|
|
|
|
|
|
// Build a vector from the registers
|
2015-02-17 02:10:47 +08:00
|
|
|
Type *ParamType = FType->getParamType(Arg.getOrigArgIndex());
|
2013-03-07 17:03:52 +08:00
|
|
|
unsigned NumElements = ParamType->getVectorNumElements();
|
|
|
|
|
|
|
|
SmallVector<SDValue, 4> Regs;
|
|
|
|
Regs.push_back(Val);
|
|
|
|
for (unsigned j = 1; j != NumElements; ++j) {
|
|
|
|
Reg = ArgLocs[ArgIdx++].getLocReg();
|
|
|
|
Reg = MF.addLiveIn(Reg, RC);
|
2015-07-11 06:51:36 +08:00
|
|
|
|
|
|
|
SDValue Copy = DAG.getCopyFromReg(Chain, DL, Reg, VT);
|
|
|
|
Regs.push_back(Copy);
|
2013-03-07 17:03:52 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Fill up the missing vector elements
|
|
|
|
NumElements = Arg.VT.getVectorNumElements() - NumElements;
|
2015-02-17 23:29:18 +08:00
|
|
|
Regs.append(NumElements, DAG.getUNDEF(VT));
|
2013-05-18 08:21:46 +08:00
|
|
|
|
2016-04-27 05:15:30 +08:00
|
|
|
InVals.push_back(DAG.getBuildVector(Arg.VT, DL, Regs));
|
2013-03-07 17:03:52 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
InVals.push_back(Val);
|
|
|
|
}
|
2015-01-21 03:33:04 +08:00
|
|
|
|
2015-12-01 05:16:03 +08:00
|
|
|
// TODO: Add GridWorkGroupCount user SGPRs when used. For now with HSA we read
|
|
|
|
// these from the dispatch pointer.
|
|
|
|
|
|
|
|
// Start adding system SGPRs.
|
|
|
|
if (Info->hasWorkGroupIDX()) {
|
|
|
|
unsigned Reg = Info->addWorkGroupIDX();
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::SReg_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
2016-04-15 00:27:03 +08:00
|
|
|
}
|
2015-12-01 05:16:03 +08:00
|
|
|
|
|
|
|
if (Info->hasWorkGroupIDY()) {
|
|
|
|
unsigned Reg = Info->addWorkGroupIDY();
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::SReg_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Info->hasWorkGroupIDZ()) {
|
|
|
|
unsigned Reg = Info->addWorkGroupIDZ();
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::SReg_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Info->hasWorkGroupInfo()) {
|
|
|
|
unsigned Reg = Info->addWorkGroupInfo();
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::SReg_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
2015-01-21 03:33:04 +08:00
|
|
|
}
|
2015-07-11 06:51:36 +08:00
|
|
|
|
2015-12-01 05:16:03 +08:00
|
|
|
if (Info->hasPrivateSegmentWaveByteOffset()) {
|
|
|
|
// Scratch wave offset passed in system SGPR.
|
2016-04-15 00:27:03 +08:00
|
|
|
unsigned PrivateSegmentWaveByteOffsetReg;
|
|
|
|
|
|
|
|
if (AMDGPU::isShader(CallConv)) {
|
|
|
|
PrivateSegmentWaveByteOffsetReg = findFirstFreeSGPR(CCInfo);
|
|
|
|
Info->setPrivateSegmentWaveByteOffset(PrivateSegmentWaveByteOffsetReg);
|
|
|
|
} else
|
|
|
|
PrivateSegmentWaveByteOffsetReg = Info->addPrivateSegmentWaveByteOffset();
|
2015-12-01 05:16:03 +08:00
|
|
|
|
|
|
|
MF.addLiveIn(PrivateSegmentWaveByteOffsetReg, &AMDGPU::SGPR_32RegClass);
|
|
|
|
CCInfo.AllocateReg(PrivateSegmentWaveByteOffsetReg);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Now that we've figured out where the scratch register inputs are, see if
|
|
|
|
// should reserve the arguments and use them directly.
|
|
|
|
bool HasStackObjects = MF.getFrameInfo()->hasStackObjects();
|
2016-02-12 14:31:30 +08:00
|
|
|
// Record that we know we have non-spill stack objects so we don't need to
|
|
|
|
// check all stack objects later.
|
|
|
|
if (HasStackObjects)
|
|
|
|
Info->setHasNonSpillStackObjects(true);
|
2015-12-01 05:16:03 +08:00
|
|
|
|
|
|
|
if (ST.isAmdHsaOS()) {
|
|
|
|
// TODO: Assume we will spill without optimizations.
|
|
|
|
if (HasStackObjects) {
|
|
|
|
// If we have stack objects, we unquestionably need the private buffer
|
|
|
|
// resource. For the HSA ABI, this will be the first 4 user SGPR
|
|
|
|
// inputs. We can reserve those and use them directly.
|
|
|
|
|
|
|
|
unsigned PrivateSegmentBufferReg = TRI->getPreloadedValue(
|
|
|
|
MF, SIRegisterInfo::PRIVATE_SEGMENT_BUFFER);
|
|
|
|
Info->setScratchRSrcReg(PrivateSegmentBufferReg);
|
|
|
|
|
|
|
|
unsigned PrivateSegmentWaveByteOffsetReg = TRI->getPreloadedValue(
|
|
|
|
MF, SIRegisterInfo::PRIVATE_SEGMENT_WAVE_BYTE_OFFSET);
|
|
|
|
Info->setScratchWaveOffsetReg(PrivateSegmentWaveByteOffsetReg);
|
|
|
|
} else {
|
|
|
|
unsigned ReservedBufferReg
|
|
|
|
= TRI->reservedPrivateSegmentBufferReg(MF);
|
|
|
|
unsigned ReservedOffsetReg
|
|
|
|
= TRI->reservedPrivateSegmentWaveByteOffsetReg(MF);
|
|
|
|
|
|
|
|
// We tentatively reserve the last registers (skipping the last two
|
|
|
|
// which may contain VCC). After register allocation, we'll replace
|
|
|
|
// these with the ones immediately after those which were really
|
|
|
|
// allocated. In the prologue copies will be inserted from the argument
|
|
|
|
// to these reserved registers.
|
|
|
|
Info->setScratchRSrcReg(ReservedBufferReg);
|
|
|
|
Info->setScratchWaveOffsetReg(ReservedOffsetReg);
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
unsigned ReservedBufferReg = TRI->reservedPrivateSegmentBufferReg(MF);
|
|
|
|
|
|
|
|
// Without HSA, relocations are used for the scratch pointer and the
|
|
|
|
// buffer resource setup is always inserted in the prologue. Scratch wave
|
|
|
|
// offset is still in an input SGPR.
|
|
|
|
Info->setScratchRSrcReg(ReservedBufferReg);
|
|
|
|
|
|
|
|
if (HasStackObjects) {
|
|
|
|
unsigned ScratchWaveOffsetReg = TRI->getPreloadedValue(
|
|
|
|
MF, SIRegisterInfo::PRIVATE_SEGMENT_WAVE_BYTE_OFFSET);
|
|
|
|
Info->setScratchWaveOffsetReg(ScratchWaveOffsetReg);
|
|
|
|
} else {
|
|
|
|
unsigned ReservedOffsetReg
|
|
|
|
= TRI->reservedPrivateSegmentWaveByteOffsetReg(MF);
|
|
|
|
Info->setScratchWaveOffsetReg(ReservedOffsetReg);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Info->hasWorkItemIDX()) {
|
|
|
|
unsigned Reg = TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_X);
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::VGPR_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
2016-04-15 00:27:03 +08:00
|
|
|
}
|
2015-12-01 05:16:03 +08:00
|
|
|
|
|
|
|
if (Info->hasWorkItemIDY()) {
|
|
|
|
unsigned Reg = TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_Y);
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::VGPR_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Info->hasWorkItemIDZ()) {
|
|
|
|
unsigned Reg = TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_Z);
|
|
|
|
MF.addLiveIn(Reg, &AMDGPU::VGPR_32RegClass);
|
|
|
|
CCInfo.AllocateReg(Reg);
|
|
|
|
}
|
2015-12-01 05:15:53 +08:00
|
|
|
|
2015-07-11 06:51:36 +08:00
|
|
|
if (Chains.empty())
|
|
|
|
return Chain;
|
|
|
|
|
|
|
|
return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chains);
|
2013-03-07 17:03:52 +08:00
|
|
|
}
|
|
|
|
|
2016-06-12 23:39:02 +08:00
|
|
|
SDValue
|
|
|
|
SITargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
|
|
|
|
bool isVarArg,
|
|
|
|
const SmallVectorImpl<ISD::OutputArg> &Outs,
|
|
|
|
const SmallVectorImpl<SDValue> &OutVals,
|
|
|
|
const SDLoc &DL, SelectionDAG &DAG) const {
|
2016-01-14 01:23:04 +08:00
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
|
|
|
|
|
2016-04-07 03:40:20 +08:00
|
|
|
if (!AMDGPU::isShader(CallConv))
|
2016-01-14 01:23:04 +08:00
|
|
|
return AMDGPUTargetLowering::LowerReturn(Chain, CallConv, isVarArg, Outs,
|
|
|
|
OutVals, DL, DAG);
|
|
|
|
|
2016-01-14 01:23:09 +08:00
|
|
|
Info->setIfReturnsVoid(Outs.size() == 0);
|
|
|
|
|
2016-01-14 01:23:04 +08:00
|
|
|
SmallVector<ISD::OutputArg, 48> Splits;
|
|
|
|
SmallVector<SDValue, 48> SplitVals;
|
|
|
|
|
|
|
|
// Split vectors into their elements.
|
|
|
|
for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
|
|
|
|
const ISD::OutputArg &Out = Outs[i];
|
|
|
|
|
|
|
|
if (Out.VT.isVector()) {
|
|
|
|
MVT VT = Out.VT.getVectorElementType();
|
|
|
|
ISD::OutputArg NewOut = Out;
|
|
|
|
NewOut.Flags.setSplit();
|
|
|
|
NewOut.VT = VT;
|
|
|
|
|
|
|
|
// We want the original number of vector elements here, e.g.
|
|
|
|
// three or five, not four or eight.
|
|
|
|
unsigned NumElements = Out.ArgVT.getVectorNumElements();
|
|
|
|
|
|
|
|
for (unsigned j = 0; j != NumElements; ++j) {
|
|
|
|
SDValue Elem = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, VT, OutVals[i],
|
|
|
|
DAG.getConstant(j, DL, MVT::i32));
|
|
|
|
SplitVals.push_back(Elem);
|
|
|
|
Splits.push_back(NewOut);
|
|
|
|
NewOut.PartOffset += NewOut.VT.getStoreSize();
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
SplitVals.push_back(OutVals[i]);
|
|
|
|
Splits.push_back(Out);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// CCValAssign - represent the assignment of the return value to a location.
|
|
|
|
SmallVector<CCValAssign, 48> RVLocs;
|
|
|
|
|
|
|
|
// CCState - Info about the registers and stack slots.
|
|
|
|
CCState CCInfo(CallConv, isVarArg, DAG.getMachineFunction(), RVLocs,
|
|
|
|
*DAG.getContext());
|
|
|
|
|
|
|
|
// Analyze outgoing return values.
|
|
|
|
AnalyzeReturn(CCInfo, Splits);
|
|
|
|
|
|
|
|
SDValue Flag;
|
|
|
|
SmallVector<SDValue, 48> RetOps;
|
|
|
|
RetOps.push_back(Chain); // Operand #0 = Chain (updated below)
|
|
|
|
|
|
|
|
// Copy the result values into the output registers.
|
|
|
|
for (unsigned i = 0, realRVLocIdx = 0;
|
|
|
|
i != RVLocs.size();
|
|
|
|
++i, ++realRVLocIdx) {
|
|
|
|
CCValAssign &VA = RVLocs[i];
|
|
|
|
assert(VA.isRegLoc() && "Can only return in registers!");
|
|
|
|
|
|
|
|
SDValue Arg = SplitVals[realRVLocIdx];
|
|
|
|
|
|
|
|
// Copied from other backends.
|
|
|
|
switch (VA.getLocInfo()) {
|
|
|
|
default: llvm_unreachable("Unknown loc info!");
|
|
|
|
case CCValAssign::Full:
|
|
|
|
break;
|
|
|
|
case CCValAssign::BCvt:
|
|
|
|
Arg = DAG.getNode(ISD::BITCAST, DL, VA.getLocVT(), Arg);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
Chain = DAG.getCopyToReg(Chain, DL, VA.getLocReg(), Arg, Flag);
|
|
|
|
Flag = Chain.getValue(1);
|
|
|
|
RetOps.push_back(DAG.getRegister(VA.getLocReg(), VA.getLocVT()));
|
|
|
|
}
|
|
|
|
|
|
|
|
// Update chain and glue.
|
|
|
|
RetOps[0] = Chain;
|
|
|
|
if (Flag.getNode())
|
|
|
|
RetOps.push_back(Flag);
|
|
|
|
|
2016-06-23 04:15:28 +08:00
|
|
|
unsigned Opc = Info->returnsVoid() ? AMDGPUISD::ENDPGM : AMDGPUISD::RETURN;
|
|
|
|
return DAG.getNode(Opc, DL, MVT::Other, RetOps);
|
2016-01-14 01:23:04 +08:00
|
|
|
}
|
|
|
|
|
2016-01-26 12:29:24 +08:00
|
|
|
unsigned SITargetLowering::getRegisterByName(const char* RegName, EVT VT,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
unsigned Reg = StringSwitch<unsigned>(RegName)
|
|
|
|
.Case("m0", AMDGPU::M0)
|
|
|
|
.Case("exec", AMDGPU::EXEC)
|
|
|
|
.Case("exec_lo", AMDGPU::EXEC_LO)
|
|
|
|
.Case("exec_hi", AMDGPU::EXEC_HI)
|
|
|
|
.Case("flat_scratch", AMDGPU::FLAT_SCR)
|
|
|
|
.Case("flat_scratch_lo", AMDGPU::FLAT_SCR_LO)
|
|
|
|
.Case("flat_scratch_hi", AMDGPU::FLAT_SCR_HI)
|
|
|
|
.Default(AMDGPU::NoRegister);
|
|
|
|
|
|
|
|
if (Reg == AMDGPU::NoRegister) {
|
|
|
|
report_fatal_error(Twine("invalid register name \""
|
|
|
|
+ StringRef(RegName) + "\"."));
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() == SISubtarget::SOUTHERN_ISLANDS &&
|
2016-01-26 12:29:24 +08:00
|
|
|
Subtarget->getRegisterInfo()->regsOverlap(Reg, AMDGPU::FLAT_SCR)) {
|
|
|
|
report_fatal_error(Twine("invalid register \""
|
|
|
|
+ StringRef(RegName) + "\" for subtarget."));
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (Reg) {
|
|
|
|
case AMDGPU::M0:
|
|
|
|
case AMDGPU::EXEC_LO:
|
|
|
|
case AMDGPU::EXEC_HI:
|
|
|
|
case AMDGPU::FLAT_SCR_LO:
|
|
|
|
case AMDGPU::FLAT_SCR_HI:
|
|
|
|
if (VT.getSizeInBits() == 32)
|
|
|
|
return Reg;
|
|
|
|
break;
|
|
|
|
case AMDGPU::EXEC:
|
|
|
|
case AMDGPU::FLAT_SCR:
|
|
|
|
if (VT.getSizeInBits() == 64)
|
|
|
|
return Reg;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
llvm_unreachable("missing register type checking");
|
|
|
|
}
|
|
|
|
|
|
|
|
report_fatal_error(Twine("invalid type for register \""
|
|
|
|
+ StringRef(RegName) + "\"."));
|
|
|
|
}
|
|
|
|
|
2016-07-01 06:52:52 +08:00
|
|
|
MachineBasicBlock *
|
|
|
|
SITargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
|
|
|
|
MachineBasicBlock *BB) const {
|
|
|
|
switch (MI.getOpcode()) {
|
2016-04-15 05:58:15 +08:00
|
|
|
case AMDGPU::SI_INIT_M0: {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2016-07-01 06:52:52 +08:00
|
|
|
BuildMI(*BB, MI.getIterator(), MI.getDebugLoc(),
|
2016-04-15 05:58:15 +08:00
|
|
|
TII->get(AMDGPU::S_MOV_B32), AMDGPU::M0)
|
2016-07-01 06:52:52 +08:00
|
|
|
.addOperand(MI.getOperand(0));
|
|
|
|
MI.eraseFromParent();
|
2016-04-15 05:58:15 +08:00
|
|
|
break;
|
|
|
|
}
|
2015-02-21 06:10:45 +08:00
|
|
|
case AMDGPU::BRANCH:
|
|
|
|
return BB;
|
2016-03-16 01:28:44 +08:00
|
|
|
case AMDGPU::GET_GROUPSTATICSIZE: {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
|
|
|
|
2016-03-16 01:28:44 +08:00
|
|
|
MachineFunction *MF = BB->getParent();
|
|
|
|
SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
|
2016-07-01 06:52:52 +08:00
|
|
|
DebugLoc DL = MI.getDebugLoc();
|
|
|
|
BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOVK_I32))
|
|
|
|
.addOperand(MI.getOperand(0))
|
|
|
|
.addImm(MFI->LDSSize);
|
|
|
|
MI.eraseFromParent();
|
2016-03-16 01:28:44 +08:00
|
|
|
return BB;
|
|
|
|
}
|
|
|
|
default:
|
|
|
|
return AMDGPUTargetLowering::EmitInstrWithCustomInserter(MI, BB);
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
|
|
|
return BB;
|
|
|
|
}
|
|
|
|
|
2015-01-30 03:34:32 +08:00
|
|
|
bool SITargetLowering::enableAggressiveFMAFusion(EVT VT) const {
|
|
|
|
// This currently forces unfolding various combinations of fsub into fma with
|
|
|
|
// free fneg'd operands. As long as we have fast FMA (controlled by
|
|
|
|
// isFMAFasterThanFMulAndFAdd), we should perform these.
|
|
|
|
|
|
|
|
// When fma is quarter rate, for f64 where add / sub are at best half rate,
|
|
|
|
// most of these combines appear to be cycle neutral but save on instruction
|
|
|
|
// count / code size.
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2015-07-09 10:09:04 +08:00
|
|
|
EVT SITargetLowering::getSetCCResultType(const DataLayout &DL, LLVMContext &Ctx,
|
|
|
|
EVT VT) const {
|
2013-07-19 05:43:53 +08:00
|
|
|
if (!VT.isVector()) {
|
|
|
|
return MVT::i1;
|
|
|
|
}
|
2014-11-29 06:51:38 +08:00
|
|
|
return EVT::getVectorVT(Ctx, MVT::i1, VT.getVectorNumElements());
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
|
|
|
|
2015-07-09 23:12:23 +08:00
|
|
|
MVT SITargetLowering::getScalarShiftAmountTy(const DataLayout &, EVT) const {
|
2013-03-18 19:34:05 +08:00
|
|
|
return MVT::i32;
|
|
|
|
}
|
|
|
|
|
2015-01-30 03:34:32 +08:00
|
|
|
// Answering this is somewhat tricky and depends on the specific device which
|
|
|
|
// have different rates for fma or all f64 operations.
|
|
|
|
//
|
|
|
|
// v_fma_f64 and v_mul_f64 always take the same number of cycles as each other
|
|
|
|
// regardless of which device (although the number of cycles differs between
|
|
|
|
// devices), so it is always profitable for f64.
|
|
|
|
//
|
|
|
|
// v_fma_f32 takes 4 or 16 cycles depending on the device, so it is profitable
|
|
|
|
// only on full rate devices. Normally, we should prefer selecting v_mad_f32
|
|
|
|
// which we can always do even without fused FP ops since it returns the same
|
|
|
|
// result as the separate operations and since it is always full
|
|
|
|
// rate. Therefore, we lie and report that it is not faster for f32. v_mad_f32
|
|
|
|
// however does not support denormals, so we do report fma as faster if we have
|
|
|
|
// a fast fma device and require denormals.
|
|
|
|
//
|
2013-08-10 18:38:54 +08:00
|
|
|
bool SITargetLowering::isFMAFasterThanFMulAndFAdd(EVT VT) const {
|
|
|
|
VT = VT.getScalarType();
|
|
|
|
|
|
|
|
if (!VT.isSimple())
|
|
|
|
return false;
|
|
|
|
|
|
|
|
switch (VT.getSimpleVT().SimpleTy) {
|
|
|
|
case MVT::f32:
|
2015-01-30 03:34:32 +08:00
|
|
|
// This is as fast on some subtargets. However, we always have full rate f32
|
|
|
|
// mad available which returns the same result as the separate operations
|
2015-02-21 06:10:41 +08:00
|
|
|
// which we should prefer over fma. We can't use this if we want to support
|
|
|
|
// denormals, so only report this in these cases.
|
|
|
|
return Subtarget->hasFP32Denormals() && Subtarget->hasFastFMAF32();
|
2013-08-10 18:38:54 +08:00
|
|
|
case MVT::f64:
|
|
|
|
return true;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2012-12-12 05:25:42 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Custom DAG Lowering Operations
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
SDValue SITargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
switch (Op.getOpcode()) {
|
|
|
|
default: return AMDGPUTargetLowering::LowerOperation(Op, DAG);
|
2014-07-21 23:45:01 +08:00
|
|
|
case ISD::FrameIndex: return LowerFrameIndex(Op, DAG);
|
2012-12-20 06:10:31 +08:00
|
|
|
case ISD::BRCOND: return LowerBRCOND(Op, DAG);
|
2013-08-26 23:06:04 +08:00
|
|
|
case ISD::LOAD: {
|
2014-07-21 23:45:06 +08:00
|
|
|
SDValue Result = LowerLOAD(Op, DAG);
|
|
|
|
assert((!Result.getNode() ||
|
|
|
|
Result.getNode()->getNumValues() == 2) &&
|
|
|
|
"Load should return a value and a chain");
|
|
|
|
return Result;
|
2013-08-26 23:06:04 +08:00
|
|
|
}
|
2013-10-23 08:44:32 +08:00
|
|
|
|
2014-07-20 02:44:39 +08:00
|
|
|
case ISD::FSIN:
|
|
|
|
case ISD::FCOS:
|
|
|
|
return LowerTrig(Op, DAG);
|
2014-02-05 01:18:40 +08:00
|
|
|
case ISD::SELECT: return LowerSELECT(Op, DAG);
|
2014-07-16 04:18:31 +08:00
|
|
|
case ISD::FDIV: return LowerFDIV(Op, DAG);
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
case ISD::ATOMIC_CMP_SWAP: return LowerATOMIC_CMP_SWAP(Op, DAG);
|
2013-11-14 07:36:50 +08:00
|
|
|
case ISD::STORE: return LowerSTORE(Op, DAG);
|
2014-07-26 14:23:37 +08:00
|
|
|
case ISD::GlobalAddress: {
|
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
|
|
|
|
return LowerGlobalAddress(MFI, Op, DAG);
|
2013-06-04 01:40:18 +08:00
|
|
|
}
|
2014-07-26 14:23:37 +08:00
|
|
|
case ISD::INTRINSIC_WO_CHAIN: return LowerINTRINSIC_WO_CHAIN(Op, DAG);
|
2016-04-12 22:05:04 +08:00
|
|
|
case ISD::INTRINSIC_W_CHAIN: return LowerINTRINSIC_W_CHAIN(Op, DAG);
|
2014-07-26 14:23:37 +08:00
|
|
|
case ISD::INTRINSIC_VOID: return LowerINTRINSIC_VOID(Op, DAG);
|
2016-04-26 03:27:24 +08:00
|
|
|
case ISD::ADDRSPACECAST: return lowerADDRSPACECAST(Op, DAG);
|
2016-06-18 06:27:03 +08:00
|
|
|
case ISD::TRAP: return lowerTRAP(Op, DAG);
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2012-12-20 06:10:31 +08:00
|
|
|
/// \brief Helper function for LowerBRCOND
|
|
|
|
static SDNode *findUser(SDValue Value, unsigned Opcode) {
|
|
|
|
|
|
|
|
SDNode *Parent = Value.getNode();
|
|
|
|
for (SDNode::use_iterator I = Parent->use_begin(), E = Parent->use_end();
|
|
|
|
I != E; ++I) {
|
|
|
|
|
|
|
|
if (I.getUse().get() != Value)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (I->getOpcode() == Opcode)
|
|
|
|
return *I;
|
|
|
|
}
|
2014-04-25 13:30:21 +08:00
|
|
|
return nullptr;
|
2012-12-20 06:10:31 +08:00
|
|
|
}
|
|
|
|
|
2014-07-21 23:45:01 +08:00
|
|
|
SDValue SITargetLowering::LowerFrameIndex(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
|
2015-07-17 03:40:07 +08:00
|
|
|
SDLoc SL(Op);
|
2014-07-21 23:45:01 +08:00
|
|
|
FrameIndexSDNode *FINode = cast<FrameIndexSDNode>(Op);
|
|
|
|
unsigned FrameIndex = FINode->getIndex();
|
|
|
|
|
2016-02-28 04:26:57 +08:00
|
|
|
// A FrameIndex node represents a 32-bit offset into scratch memory. If the
|
|
|
|
// high bit of a frame index offset were to be set, this would mean that it
|
|
|
|
// represented an offset of ~2GB * 64 = ~128GB from the start of the scratch
|
|
|
|
// buffer, with 64 being the number of threads per wave.
|
2015-07-17 03:40:07 +08:00
|
|
|
//
|
2016-02-28 04:26:57 +08:00
|
|
|
// The maximum private allocation for the entire GPU is 4G, and we are
|
|
|
|
// concerned with the largest the index could ever be for an individual
|
|
|
|
// workitem. This will occur with the minmum dispatch size. If a program
|
|
|
|
// requires more, the dispatch size will be reduced.
|
|
|
|
//
|
|
|
|
// With this limit, we can mark the high bit of the FrameIndex node as known
|
|
|
|
// zero, which is important, because it means in most situations we can prove
|
|
|
|
// that values derived from FrameIndex nodes are non-negative. This enables us
|
|
|
|
// to take advantage of more addressing modes when accessing scratch buffers,
|
|
|
|
// since for scratch reads/writes, the register offset must always be
|
|
|
|
// positive.
|
2015-07-17 03:40:07 +08:00
|
|
|
|
2016-02-28 04:26:57 +08:00
|
|
|
uint64_t MaxGPUAlloc = UINT64_C(4) * 1024 * 1024 * 1024;
|
|
|
|
|
|
|
|
// XXX - It is unclear if partial dispatch works. Assume it works at half wave
|
|
|
|
// granularity. It is probably a full wave.
|
|
|
|
uint64_t MinGranularity = 32;
|
2015-07-17 03:40:07 +08:00
|
|
|
|
2016-02-28 04:26:57 +08:00
|
|
|
unsigned KnownBits = Log2_64(MaxGPUAlloc / MinGranularity);
|
|
|
|
EVT ExtVT = EVT::getIntegerVT(*DAG.getContext(), KnownBits);
|
|
|
|
|
|
|
|
SDValue TFI = DAG.getTargetFrameIndex(FrameIndex, MVT::i32);
|
2015-07-17 03:40:07 +08:00
|
|
|
return DAG.getNode(ISD::AssertZext, SL, MVT::i32, TFI,
|
2016-02-28 04:26:57 +08:00
|
|
|
DAG.getValueType(ExtVT));
|
2014-07-21 23:45:01 +08:00
|
|
|
}
|
|
|
|
|
2016-02-13 07:45:29 +08:00
|
|
|
bool SITargetLowering::isCFIntrinsic(const SDNode *Intr) const {
|
2016-02-13 08:36:10 +08:00
|
|
|
if (Intr->getOpcode() != ISD::INTRINSIC_W_CHAIN)
|
2016-02-13 07:45:29 +08:00
|
|
|
return false;
|
|
|
|
|
|
|
|
switch (cast<ConstantSDNode>(Intr->getOperand(1))->getZExtValue()) {
|
|
|
|
default: return false;
|
|
|
|
case AMDGPUIntrinsic::amdgcn_if:
|
|
|
|
case AMDGPUIntrinsic::amdgcn_else:
|
|
|
|
case AMDGPUIntrinsic::amdgcn_if_break:
|
|
|
|
case AMDGPUIntrinsic::amdgcn_else_break:
|
|
|
|
case AMDGPUIntrinsic::amdgcn_loop:
|
|
|
|
case AMDGPUIntrinsic::amdgcn_end_cf:
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-25 11:11:28 +08:00
|
|
|
void SITargetLowering::createDebuggerPrologueStackObjects(
|
|
|
|
MachineFunction &MF) const {
|
|
|
|
// Create stack objects that are used for emitting debugger prologue.
|
|
|
|
//
|
|
|
|
// Debugger prologue writes work group IDs and work item IDs to scratch memory
|
|
|
|
// at fixed location in the following format:
|
|
|
|
// offset 0: work group ID x
|
|
|
|
// offset 4: work group ID y
|
|
|
|
// offset 8: work group ID z
|
|
|
|
// offset 16: work item ID x
|
|
|
|
// offset 20: work item ID y
|
|
|
|
// offset 24: work item ID z
|
|
|
|
SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
|
|
|
|
int ObjectIdx = 0;
|
|
|
|
|
|
|
|
// For each dimension:
|
|
|
|
for (unsigned i = 0; i < 3; ++i) {
|
|
|
|
// Create fixed stack object for work group ID.
|
|
|
|
ObjectIdx = MF.getFrameInfo()->CreateFixedObject(4, i * 4, true);
|
|
|
|
Info->setDebuggerWorkGroupIDStackObjectIndex(i, ObjectIdx);
|
|
|
|
// Create fixed stack object for work item ID.
|
|
|
|
ObjectIdx = MF.getFrameInfo()->CreateFixedObject(4, i * 4 + 16, true);
|
|
|
|
Info->setDebuggerWorkItemIDStackObjectIndex(i, ObjectIdx);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-12-20 06:10:31 +08:00
|
|
|
/// This transforms the control flow intrinsics to get the branch destination as
|
|
|
|
/// last parameter, also switches branch target with BR if the need arise
|
|
|
|
SDValue SITargetLowering::LowerBRCOND(SDValue BRCOND,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
|
2013-05-25 10:42:55 +08:00
|
|
|
SDLoc DL(BRCOND);
|
2012-12-20 06:10:31 +08:00
|
|
|
|
|
|
|
SDNode *Intr = BRCOND.getOperand(1).getNode();
|
|
|
|
SDValue Target = BRCOND.getOperand(2);
|
2014-04-25 13:30:21 +08:00
|
|
|
SDNode *BR = nullptr;
|
2016-02-13 07:45:29 +08:00
|
|
|
SDNode *SetCC = nullptr;
|
2012-12-20 06:10:31 +08:00
|
|
|
|
|
|
|
if (Intr->getOpcode() == ISD::SETCC) {
|
|
|
|
// As long as we negate the condition everything is fine
|
2016-02-13 07:45:29 +08:00
|
|
|
SetCC = Intr;
|
2012-12-20 06:10:31 +08:00
|
|
|
Intr = SetCC->getOperand(0).getNode();
|
|
|
|
|
|
|
|
} else {
|
|
|
|
// Get the target from BR if we don't negate the condition
|
|
|
|
BR = findUser(BRCOND, ISD::BR);
|
|
|
|
Target = BR->getOperand(1);
|
|
|
|
}
|
|
|
|
|
2016-05-06 01:36:36 +08:00
|
|
|
if (!isCFIntrinsic(Intr)) {
|
2016-02-13 07:45:29 +08:00
|
|
|
// This is a uniform branch so we don't need to legalize.
|
|
|
|
return BRCOND;
|
|
|
|
}
|
|
|
|
|
|
|
|
assert(!SetCC ||
|
|
|
|
(SetCC->getConstantOperandVal(1) == 1 &&
|
|
|
|
cast<CondCodeSDNode>(SetCC->getOperand(2).getNode())->get() ==
|
|
|
|
ISD::SETNE));
|
2012-12-20 06:10:31 +08:00
|
|
|
|
|
|
|
// Build the result and
|
2015-02-17 23:29:18 +08:00
|
|
|
ArrayRef<EVT> Res(Intr->value_begin() + 1, Intr->value_end());
|
2012-12-20 06:10:31 +08:00
|
|
|
|
|
|
|
// operands of the new intrinsic call
|
|
|
|
SmallVector<SDValue, 4> Ops;
|
|
|
|
Ops.push_back(BRCOND.getOperand(0));
|
2015-02-17 23:29:18 +08:00
|
|
|
Ops.append(Intr->op_begin() + 1, Intr->op_end());
|
2012-12-20 06:10:31 +08:00
|
|
|
Ops.push_back(Target);
|
|
|
|
|
|
|
|
// build the new intrinsic call
|
|
|
|
SDNode *Result = DAG.getNode(
|
|
|
|
Res.size() > 1 ? ISD::INTRINSIC_W_CHAIN : ISD::INTRINSIC_VOID, DL,
|
2014-04-27 02:35:24 +08:00
|
|
|
DAG.getVTList(Res), Ops).getNode();
|
2012-12-20 06:10:31 +08:00
|
|
|
|
|
|
|
if (BR) {
|
|
|
|
// Give the branch instruction our target
|
|
|
|
SDValue Ops[] = {
|
|
|
|
BR->getOperand(0),
|
|
|
|
BRCOND.getOperand(2)
|
|
|
|
};
|
2014-08-02 06:09:43 +08:00
|
|
|
SDValue NewBR = DAG.getNode(ISD::BR, DL, BR->getVTList(), Ops);
|
|
|
|
DAG.ReplaceAllUsesWith(BR, NewBR.getNode());
|
|
|
|
BR = NewBR.getNode();
|
2012-12-20 06:10:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
SDValue Chain = SDValue(Result, Result->getNumValues() - 1);
|
|
|
|
|
|
|
|
// Copy the intrinsic results to registers
|
|
|
|
for (unsigned i = 1, e = Intr->getNumValues() - 1; i != e; ++i) {
|
|
|
|
SDNode *CopyToReg = findUser(SDValue(Intr, i), ISD::CopyToReg);
|
|
|
|
if (!CopyToReg)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
Chain = DAG.getCopyToReg(
|
|
|
|
Chain, DL,
|
|
|
|
CopyToReg->getOperand(1),
|
|
|
|
SDValue(Result, i - 1),
|
|
|
|
SDValue());
|
|
|
|
|
|
|
|
DAG.ReplaceAllUsesWith(SDValue(CopyToReg, 0), CopyToReg->getOperand(0));
|
|
|
|
}
|
|
|
|
|
|
|
|
// Remove the old intrinsic from the chain
|
|
|
|
DAG.ReplaceAllUsesOfValueWith(
|
|
|
|
SDValue(Intr, Intr->getNumValues() - 1),
|
|
|
|
Intr->getOperand(0));
|
|
|
|
|
|
|
|
return Chain;
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
|
|
|
|
2016-04-26 03:27:24 +08:00
|
|
|
SDValue SITargetLowering::getSegmentAperture(unsigned AS,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
SDLoc SL;
|
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
|
2016-06-07 04:03:31 +08:00
|
|
|
unsigned UserSGPR = Info->getQueuePtrUserSGPR();
|
|
|
|
assert(UserSGPR != AMDGPU::NoRegister);
|
|
|
|
|
2016-04-26 03:27:24 +08:00
|
|
|
SDValue QueuePtr = CreateLiveInRegister(
|
2016-06-07 04:03:31 +08:00
|
|
|
DAG, &AMDGPU::SReg_64RegClass, UserSGPR, MVT::i64);
|
2016-04-26 03:27:24 +08:00
|
|
|
|
|
|
|
// Offset into amd_queue_t for group_segment_aperture_base_hi /
|
|
|
|
// private_segment_aperture_base_hi.
|
|
|
|
uint32_t StructOffset = (AS == AMDGPUAS::LOCAL_ADDRESS) ? 0x40 : 0x44;
|
|
|
|
|
|
|
|
SDValue Ptr = DAG.getNode(ISD::ADD, SL, MVT::i64, QueuePtr,
|
|
|
|
DAG.getConstant(StructOffset, SL, MVT::i64));
|
|
|
|
|
|
|
|
// TODO: Use custom target PseudoSourceValue.
|
|
|
|
// TODO: We should use the value from the IR intrinsic call, but it might not
|
|
|
|
// be available and how do we get it?
|
|
|
|
Value *V = UndefValue::get(PointerType::get(Type::getInt8Ty(*DAG.getContext()),
|
|
|
|
AMDGPUAS::CONSTANT_ADDRESS));
|
|
|
|
|
|
|
|
MachinePointerInfo PtrInfo(V, StructOffset);
|
|
|
|
return DAG.getLoad(MVT::i32, SL, QueuePtr.getValue(1), Ptr,
|
|
|
|
PtrInfo, false,
|
|
|
|
false, true,
|
|
|
|
MinAlign(64, StructOffset));
|
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::lowerADDRSPACECAST(SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
SDLoc SL(Op);
|
|
|
|
const AddrSpaceCastSDNode *ASC = cast<AddrSpaceCastSDNode>(Op);
|
|
|
|
|
|
|
|
SDValue Src = ASC->getOperand(0);
|
|
|
|
|
|
|
|
// FIXME: Really support non-0 null pointers.
|
|
|
|
SDValue SegmentNullPtr = DAG.getConstant(-1, SL, MVT::i32);
|
|
|
|
SDValue FlatNullPtr = DAG.getConstant(0, SL, MVT::i64);
|
|
|
|
|
|
|
|
// flat -> local/private
|
|
|
|
if (ASC->getSrcAddressSpace() == AMDGPUAS::FLAT_ADDRESS) {
|
|
|
|
if (ASC->getDestAddressSpace() == AMDGPUAS::LOCAL_ADDRESS ||
|
|
|
|
ASC->getDestAddressSpace() == AMDGPUAS::PRIVATE_ADDRESS) {
|
|
|
|
SDValue NonNull = DAG.getSetCC(SL, MVT::i1, Src, FlatNullPtr, ISD::SETNE);
|
|
|
|
SDValue Ptr = DAG.getNode(ISD::TRUNCATE, SL, MVT::i32, Src);
|
|
|
|
|
|
|
|
return DAG.getNode(ISD::SELECT, SL, MVT::i32,
|
|
|
|
NonNull, Ptr, SegmentNullPtr);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// local/private -> flat
|
|
|
|
if (ASC->getDestAddressSpace() == AMDGPUAS::FLAT_ADDRESS) {
|
|
|
|
if (ASC->getSrcAddressSpace() == AMDGPUAS::LOCAL_ADDRESS ||
|
|
|
|
ASC->getSrcAddressSpace() == AMDGPUAS::PRIVATE_ADDRESS) {
|
|
|
|
SDValue NonNull
|
|
|
|
= DAG.getSetCC(SL, MVT::i1, Src, SegmentNullPtr, ISD::SETNE);
|
|
|
|
|
|
|
|
SDValue Aperture = getSegmentAperture(ASC->getSrcAddressSpace(), DAG);
|
|
|
|
SDValue CvtPtr
|
|
|
|
= DAG.getNode(ISD::BUILD_VECTOR, SL, MVT::v2i32, Src, Aperture);
|
|
|
|
|
|
|
|
return DAG.getNode(ISD::SELECT, SL, MVT::i64, NonNull,
|
|
|
|
DAG.getNode(ISD::BITCAST, SL, MVT::i64, CvtPtr),
|
|
|
|
FlatNullPtr);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// global <-> flat are no-ops and never emitted.
|
|
|
|
|
|
|
|
const MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
DiagnosticInfoUnsupported InvalidAddrSpaceCast(
|
|
|
|
*MF.getFunction(), "invalid addrspacecast", SL.getDebugLoc());
|
|
|
|
DAG.getContext()->diagnose(InvalidAddrSpaceCast);
|
|
|
|
|
|
|
|
return DAG.getUNDEF(ASC->getValueType(0));
|
|
|
|
}
|
|
|
|
|
2016-06-25 09:59:16 +08:00
|
|
|
bool
|
|
|
|
SITargetLowering::isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const {
|
|
|
|
if (GA->getAddressSpace() != AMDGPUAS::GLOBAL_ADDRESS)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return TargetLowering::isOffsetFoldingLegal(GA);
|
|
|
|
}
|
|
|
|
|
2016-06-15 04:29:59 +08:00
|
|
|
SDValue SITargetLowering::LowerGlobalAddress(AMDGPUMachineFunction *MFI,
|
|
|
|
SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
GlobalAddressSDNode *GSD = cast<GlobalAddressSDNode>(Op);
|
|
|
|
|
2016-06-21 01:33:43 +08:00
|
|
|
if (GSD->getAddressSpace() != AMDGPUAS::CONSTANT_ADDRESS &&
|
|
|
|
GSD->getAddressSpace() != AMDGPUAS::GLOBAL_ADDRESS)
|
2016-06-15 04:29:59 +08:00
|
|
|
return AMDGPUTargetLowering::LowerGlobalAddress(MFI, Op, DAG);
|
|
|
|
|
|
|
|
SDLoc DL(GSD);
|
|
|
|
const GlobalValue *GV = GSD->getGlobal();
|
2016-06-18 06:22:09 +08:00
|
|
|
EVT PtrVT = Op.getValueType();
|
2016-06-15 04:29:59 +08:00
|
|
|
|
|
|
|
// In order to support pc-relative addressing, the PC_ADD_REL_OFFSET SDNode is
|
|
|
|
// lowered to the following code sequence:
|
|
|
|
// s_getpc_b64 s[0:1]
|
|
|
|
// s_add_u32 s0, s0, $symbol
|
|
|
|
// s_addc_u32 s1, s1, 0
|
|
|
|
//
|
|
|
|
// s_getpc_b64 returns the address of the s_add_u32 instruction and then
|
|
|
|
// a fixup or relocation is emitted to replace $symbol with a literal
|
|
|
|
// constant, which is a pc-relative offset from the encoding of the $symbol
|
|
|
|
// operand to the global variable.
|
|
|
|
//
|
|
|
|
// What we want here is an offset from the value returned by s_getpc
|
|
|
|
// (which is the address of the s_add_u32 instruction) to the global
|
|
|
|
// variable, but since the encoding of $symbol starts 4 bytes after the start
|
|
|
|
// of the s_add_u32 instruction, we end up with an offset that is 4 bytes too
|
|
|
|
// small. This requires us to add 4 to the global variable offset in order to
|
|
|
|
// compute the correct address.
|
|
|
|
SDValue GA = DAG.getTargetGlobalAddress(GV, DL, MVT::i32,
|
|
|
|
GSD->getOffset() + 4);
|
|
|
|
return DAG.getNode(AMDGPUISD::PC_ADD_REL_OFFSET, DL, PtrVT, GA);
|
|
|
|
}
|
|
|
|
|
2016-06-18 06:27:03 +08:00
|
|
|
SDValue SITargetLowering::lowerTRAP(SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
const MachineFunction &MF = DAG.getMachineFunction();
|
|
|
|
DiagnosticInfoUnsupported NoTrap(*MF.getFunction(),
|
|
|
|
"trap handler not supported",
|
|
|
|
Op.getDebugLoc(),
|
|
|
|
DS_Warning);
|
|
|
|
DAG.getContext()->diagnose(NoTrap);
|
|
|
|
|
|
|
|
// Emit s_endpgm.
|
|
|
|
|
|
|
|
// FIXME: This should really be selected to s_trap, but that requires
|
|
|
|
// setting up the trap handler for it o do anything.
|
2016-06-23 04:15:28 +08:00
|
|
|
return DAG.getNode(AMDGPUISD::ENDPGM, SDLoc(Op), MVT::Other,
|
|
|
|
Op.getOperand(0));
|
2016-06-18 06:27:03 +08:00
|
|
|
}
|
|
|
|
|
2016-06-12 23:39:02 +08:00
|
|
|
SDValue SITargetLowering::copyToM0(SelectionDAG &DAG, SDValue Chain,
|
|
|
|
const SDLoc &DL, SDValue V) const {
|
2016-04-15 05:58:15 +08:00
|
|
|
// We can't use S_MOV_B32 directly, because there is no way to specify m0 as
|
|
|
|
// the destination register.
|
|
|
|
//
|
2015-05-12 22:18:14 +08:00
|
|
|
// We can't use CopyToReg, because MachineCSE won't combine COPY instructions,
|
|
|
|
// so we will end up with redundant moves to m0.
|
|
|
|
//
|
2016-04-15 05:58:15 +08:00
|
|
|
// We use a pseudo to ensure we emit s_mov_b32 with m0 as the direct result.
|
|
|
|
|
|
|
|
// A Null SDValue creates a glue result.
|
|
|
|
SDNode *M0 = DAG.getMachineNode(AMDGPU::SI_INIT_M0, DL, MVT::Other, MVT::Glue,
|
|
|
|
V, Chain);
|
|
|
|
return SDValue(M0, 0);
|
2015-05-12 22:18:14 +08:00
|
|
|
}
|
|
|
|
|
2015-12-01 05:15:45 +08:00
|
|
|
SDValue SITargetLowering::lowerImplicitZextParam(SelectionDAG &DAG,
|
|
|
|
SDValue Op,
|
|
|
|
MVT VT,
|
|
|
|
unsigned Offset) const {
|
|
|
|
SDLoc SL(Op);
|
|
|
|
SDValue Param = LowerParameter(DAG, MVT::i32, MVT::i32, SL,
|
|
|
|
DAG.getEntryNode(), Offset, false);
|
|
|
|
// The local size values will have the hi 16-bits as zero.
|
|
|
|
return DAG.getNode(ISD::AssertZext, SL, MVT::i32, Param,
|
|
|
|
DAG.getValueType(VT));
|
|
|
|
}
|
|
|
|
|
2016-06-21 02:33:56 +08:00
|
|
|
static SDValue emitNonHSAIntrinsicError(SelectionDAG& DAG, SDLoc DL, EVT VT) {
|
2016-01-30 13:19:45 +08:00
|
|
|
DiagnosticInfoUnsupported BadIntrin(*DAG.getMachineFunction().getFunction(),
|
2016-06-21 02:33:56 +08:00
|
|
|
"non-hsa intrinsic with hsa target",
|
|
|
|
DL.getDebugLoc());
|
|
|
|
DAG.getContext()->diagnose(BadIntrin);
|
|
|
|
return DAG.getUNDEF(VT);
|
|
|
|
}
|
|
|
|
|
|
|
|
static SDValue emitRemovedIntrinsicError(SelectionDAG& DAG, SDLoc DL, EVT VT) {
|
|
|
|
DiagnosticInfoUnsupported BadIntrin(*DAG.getMachineFunction().getFunction(),
|
|
|
|
"intrinsic not supported on subtarget",
|
|
|
|
DL.getDebugLoc());
|
2016-01-30 13:19:45 +08:00
|
|
|
DAG.getContext()->diagnose(BadIntrin);
|
|
|
|
return DAG.getUNDEF(VT);
|
|
|
|
}
|
|
|
|
|
2014-07-26 14:23:37 +08:00
|
|
|
SDValue SITargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
2015-07-10 05:20:37 +08:00
|
|
|
auto MFI = MF.getInfo<SIMachineFunctionInfo>();
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIRegisterInfo *TRI = getSubtarget()->getRegisterInfo();
|
2014-07-26 14:23:37 +08:00
|
|
|
|
|
|
|
EVT VT = Op.getValueType();
|
|
|
|
SDLoc DL(Op);
|
|
|
|
unsigned IntrinsicID = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
|
|
|
|
|
2015-09-17 00:31:21 +08:00
|
|
|
// TODO: Should this propagate fast-math-flags?
|
|
|
|
|
2014-07-26 14:23:37 +08:00
|
|
|
switch (IntrinsicID) {
|
2015-11-26 08:43:29 +08:00
|
|
|
case Intrinsic::amdgcn_dispatch_ptr:
|
2016-04-26 03:27:18 +08:00
|
|
|
case Intrinsic::amdgcn_queue_ptr: {
|
2016-01-12 05:18:33 +08:00
|
|
|
if (!Subtarget->isAmdHsaOS()) {
|
2016-02-02 21:52:43 +08:00
|
|
|
DiagnosticInfoUnsupported BadIntrin(
|
|
|
|
*MF.getFunction(), "unsupported hsa intrinsic without hsa target",
|
|
|
|
DL.getDebugLoc());
|
2016-01-12 05:18:33 +08:00
|
|
|
DAG.getContext()->diagnose(BadIntrin);
|
|
|
|
return DAG.getUNDEF(VT);
|
|
|
|
}
|
|
|
|
|
2016-04-26 03:27:18 +08:00
|
|
|
auto Reg = IntrinsicID == Intrinsic::amdgcn_dispatch_ptr ?
|
|
|
|
SIRegisterInfo::DISPATCH_PTR : SIRegisterInfo::QUEUE_PTR;
|
2015-11-26 08:43:29 +08:00
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::SReg_64RegClass,
|
2016-04-26 03:27:18 +08:00
|
|
|
TRI->getPreloadedValue(MF, Reg), VT);
|
|
|
|
}
|
2016-06-22 04:46:20 +08:00
|
|
|
case Intrinsic::amdgcn_implicitarg_ptr: {
|
|
|
|
unsigned offset = getImplicitParameterOffset(MFI, FIRST_IMPLICIT);
|
|
|
|
return LowerParameterPtr(DAG, DL, DAG.getEntryNode(), offset);
|
|
|
|
}
|
2016-04-30 05:16:52 +08:00
|
|
|
case Intrinsic::amdgcn_kernarg_segment_ptr: {
|
|
|
|
unsigned Reg
|
|
|
|
= TRI->getPreloadedValue(MF, SIRegisterInfo::KERNARG_SEGMENT_PTR);
|
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::SReg_64RegClass, Reg, VT);
|
|
|
|
}
|
2016-01-23 13:32:20 +08:00
|
|
|
case Intrinsic::amdgcn_rcp:
|
|
|
|
return DAG.getNode(AMDGPUISD::RCP, DL, VT, Op.getOperand(1));
|
|
|
|
case Intrinsic::amdgcn_rsq:
|
2016-01-26 12:14:16 +08:00
|
|
|
case AMDGPUIntrinsic::AMDGPU_rsq: // Legacy name
|
2016-01-23 13:32:20 +08:00
|
|
|
return DAG.getNode(AMDGPUISD::RSQ, DL, VT, Op.getOperand(1));
|
2016-06-21 02:33:56 +08:00
|
|
|
case Intrinsic::amdgcn_rsq_legacy: {
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() >= SISubtarget::VOLCANIC_ISLANDS)
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitRemovedIntrinsicError(DAG, DL, VT);
|
|
|
|
|
|
|
|
return DAG.getNode(AMDGPUISD::RSQ_LEGACY, DL, VT, Op.getOperand(1));
|
|
|
|
}
|
2016-02-13 09:03:00 +08:00
|
|
|
case Intrinsic::amdgcn_rsq_clamp:
|
2016-01-26 12:14:16 +08:00
|
|
|
case AMDGPUIntrinsic::AMDGPU_rsq_clamped: { // Legacy name
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() < SISubtarget::VOLCANIC_ISLANDS)
|
2016-02-13 09:03:00 +08:00
|
|
|
return DAG.getNode(AMDGPUISD::RSQ_CLAMP, DL, VT, Op.getOperand(1));
|
2016-01-23 13:32:20 +08:00
|
|
|
|
|
|
|
Type *Type = VT.getTypeForEVT(*DAG.getContext());
|
|
|
|
APFloat Max = APFloat::getLargest(Type->getFltSemantics());
|
|
|
|
APFloat Min = APFloat::getLargest(Type->getFltSemantics(), true);
|
|
|
|
|
|
|
|
SDValue Rsq = DAG.getNode(AMDGPUISD::RSQ, DL, VT, Op.getOperand(1));
|
|
|
|
SDValue Tmp = DAG.getNode(ISD::FMINNUM, DL, VT, Rsq,
|
|
|
|
DAG.getConstantFP(Max, DL, VT));
|
|
|
|
return DAG.getNode(ISD::FMAXNUM, DL, VT, Tmp,
|
|
|
|
DAG.getConstantFP(Min, DL, VT));
|
|
|
|
}
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_ngroups_x:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::NGROUPS_X, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_ngroups_y:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::NGROUPS_Y, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_ngroups_z:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::NGROUPS_Z, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_global_size_x:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::GLOBAL_SIZE_X, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_global_size_y:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::GLOBAL_SIZE_Y, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_global_size_z:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2014-09-22 23:35:29 +08:00
|
|
|
return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
|
|
|
|
SI::KernelInputOffsets::GLOBAL_SIZE_Z, false);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_local_size_x:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2015-12-01 05:15:45 +08:00
|
|
|
return lowerImplicitZextParam(DAG, Op, MVT::i16,
|
|
|
|
SI::KernelInputOffsets::LOCAL_SIZE_X);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_local_size_y:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2015-12-01 05:15:45 +08:00
|
|
|
return lowerImplicitZextParam(DAG, Op, MVT::i16,
|
|
|
|
SI::KernelInputOffsets::LOCAL_SIZE_Y);
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_local_size_z:
|
2016-01-30 13:19:45 +08:00
|
|
|
if (Subtarget->isAmdHsaOS())
|
2016-06-21 02:33:56 +08:00
|
|
|
return emitNonHSAIntrinsicError(DAG, DL, VT);
|
2016-01-30 13:19:45 +08:00
|
|
|
|
2015-12-01 05:15:45 +08:00
|
|
|
return lowerImplicitZextParam(DAG, Op, MVT::i16,
|
|
|
|
SI::KernelInputOffsets::LOCAL_SIZE_Z);
|
2016-01-23 05:30:34 +08:00
|
|
|
case Intrinsic::amdgcn_read_workdim:
|
|
|
|
case AMDGPUIntrinsic::AMDGPU_read_workdim: // Legacy name.
|
2015-12-01 05:15:45 +08:00
|
|
|
// Really only 2 bits.
|
|
|
|
return lowerImplicitZextParam(DAG, Op, MVT::i8,
|
|
|
|
getImplicitParameterOffset(MFI, GRID_DIM));
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workgroup_id_x:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tgid_x:
|
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::SReg_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKGROUP_ID_X), VT);
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workgroup_id_y:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tgid_y:
|
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::SReg_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKGROUP_ID_Y), VT);
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workgroup_id_z:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tgid_z:
|
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::SReg_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKGROUP_ID_Z), VT);
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workitem_id_x:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tidig_x:
|
2015-01-08 04:59:25 +08:00
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::VGPR_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_X), VT);
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workitem_id_y:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tidig_y:
|
2015-01-08 04:59:25 +08:00
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::VGPR_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_Y), VT);
|
2016-01-30 12:25:19 +08:00
|
|
|
case Intrinsic::amdgcn_workitem_id_z:
|
2014-07-26 14:23:37 +08:00
|
|
|
case Intrinsic::r600_read_tidig_z:
|
2015-01-08 04:59:25 +08:00
|
|
|
return CreateLiveInRegister(DAG, &AMDGPU::VGPR_32RegClass,
|
2015-12-01 05:15:57 +08:00
|
|
|
TRI->getPreloadedValue(MF, SIRegisterInfo::WORKITEM_ID_Z), VT);
|
2014-07-26 14:23:37 +08:00
|
|
|
case AMDGPUIntrinsic::SI_load_const: {
|
|
|
|
SDValue Ops[] = {
|
|
|
|
Op.getOperand(1),
|
|
|
|
Op.getOperand(2)
|
|
|
|
};
|
|
|
|
|
|
|
|
MachineMemOperand *MMO = MF.getMachineMemOperand(
|
|
|
|
MachinePointerInfo(),
|
|
|
|
MachineMemOperand::MOLoad | MachineMemOperand::MOInvariant,
|
|
|
|
VT.getStoreSize(), 4);
|
|
|
|
return DAG.getMemIntrinsicNode(AMDGPUISD::LOAD_CONSTANT, DL,
|
|
|
|
Op->getVTList(), Ops, VT, MMO);
|
|
|
|
}
|
|
|
|
case AMDGPUIntrinsic::SI_vs_load_input:
|
|
|
|
return DAG.getNode(AMDGPUISD::LOAD_INPUT, DL, VT,
|
|
|
|
Op.getOperand(1),
|
|
|
|
Op.getOperand(2),
|
|
|
|
Op.getOperand(3));
|
2015-03-24 21:40:08 +08:00
|
|
|
|
2015-05-12 23:00:46 +08:00
|
|
|
case AMDGPUIntrinsic::SI_fs_constant: {
|
|
|
|
SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(3));
|
|
|
|
SDValue Glue = M0.getValue(1);
|
|
|
|
return DAG.getNode(AMDGPUISD::INTERP_MOV, DL, MVT::f32,
|
|
|
|
DAG.getConstant(2, DL, MVT::i32), // P0
|
|
|
|
Op.getOperand(1), Op.getOperand(2), Glue);
|
|
|
|
}
|
2015-10-29 23:29:09 +08:00
|
|
|
case AMDGPUIntrinsic::SI_packf16:
|
|
|
|
if (Op.getOperand(1).isUndef() && Op.getOperand(2).isUndef())
|
|
|
|
return DAG.getUNDEF(MVT::i32);
|
|
|
|
return Op;
|
2015-05-12 23:00:46 +08:00
|
|
|
case AMDGPUIntrinsic::SI_fs_interp: {
|
|
|
|
SDValue IJ = Op.getOperand(4);
|
|
|
|
SDValue I = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, IJ,
|
|
|
|
DAG.getConstant(0, DL, MVT::i32));
|
|
|
|
SDValue J = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, IJ,
|
|
|
|
DAG.getConstant(1, DL, MVT::i32));
|
|
|
|
SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(3));
|
|
|
|
SDValue Glue = M0.getValue(1);
|
|
|
|
SDValue P1 = DAG.getNode(AMDGPUISD::INTERP_P1, DL,
|
|
|
|
DAG.getVTList(MVT::f32, MVT::Glue),
|
|
|
|
I, Op.getOperand(1), Op.getOperand(2), Glue);
|
|
|
|
Glue = SDValue(P1.getNode(), 1);
|
|
|
|
return DAG.getNode(AMDGPUISD::INTERP_P2, DL, MVT::f32, P1, J,
|
|
|
|
Op.getOperand(1), Op.getOperand(2), Glue);
|
|
|
|
}
|
2015-12-16 01:02:49 +08:00
|
|
|
case Intrinsic::amdgcn_interp_p1: {
|
|
|
|
SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(4));
|
|
|
|
SDValue Glue = M0.getValue(1);
|
|
|
|
return DAG.getNode(AMDGPUISD::INTERP_P1, DL, MVT::f32, Op.getOperand(1),
|
|
|
|
Op.getOperand(2), Op.getOperand(3), Glue);
|
|
|
|
}
|
|
|
|
case Intrinsic::amdgcn_interp_p2: {
|
|
|
|
SDValue M0 = copyToM0(DAG, DAG.getEntryNode(), DL, Op.getOperand(5));
|
|
|
|
SDValue Glue = SDValue(M0.getNode(), 1);
|
|
|
|
return DAG.getNode(AMDGPUISD::INTERP_P2, DL, MVT::f32, Op.getOperand(1),
|
|
|
|
Op.getOperand(2), Op.getOperand(3), Op.getOperand(4),
|
|
|
|
Glue);
|
|
|
|
}
|
2016-02-13 09:19:56 +08:00
|
|
|
case Intrinsic::amdgcn_sin:
|
|
|
|
return DAG.getNode(AMDGPUISD::SIN_HW, DL, VT, Op.getOperand(1));
|
|
|
|
|
|
|
|
case Intrinsic::amdgcn_cos:
|
|
|
|
return DAG.getNode(AMDGPUISD::COS_HW, DL, VT, Op.getOperand(1));
|
|
|
|
|
|
|
|
case Intrinsic::amdgcn_log_clamp: {
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() < SISubtarget::VOLCANIC_ISLANDS)
|
2016-02-13 09:19:56 +08:00
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
DiagnosticInfoUnsupported BadIntrin(
|
|
|
|
*MF.getFunction(), "intrinsic not supported on subtarget",
|
|
|
|
DL.getDebugLoc());
|
|
|
|
DAG.getContext()->diagnose(BadIntrin);
|
|
|
|
return DAG.getUNDEF(VT);
|
|
|
|
}
|
2016-01-23 13:32:20 +08:00
|
|
|
case Intrinsic::amdgcn_ldexp:
|
|
|
|
return DAG.getNode(AMDGPUISD::LDEXP, DL, VT,
|
|
|
|
Op.getOperand(1), Op.getOperand(2));
|
2016-05-28 08:19:52 +08:00
|
|
|
|
|
|
|
case Intrinsic::amdgcn_fract:
|
|
|
|
return DAG.getNode(AMDGPUISD::FRACT, DL, VT, Op.getOperand(1));
|
|
|
|
|
2016-01-23 13:32:20 +08:00
|
|
|
case Intrinsic::amdgcn_class:
|
|
|
|
return DAG.getNode(AMDGPUISD::FP_CLASS, DL, VT,
|
|
|
|
Op.getOperand(1), Op.getOperand(2));
|
|
|
|
case Intrinsic::amdgcn_div_fmas:
|
|
|
|
return DAG.getNode(AMDGPUISD::DIV_FMAS, DL, VT,
|
|
|
|
Op.getOperand(1), Op.getOperand(2), Op.getOperand(3),
|
|
|
|
Op.getOperand(4));
|
|
|
|
|
|
|
|
case Intrinsic::amdgcn_div_fixup:
|
|
|
|
return DAG.getNode(AMDGPUISD::DIV_FIXUP, DL, VT,
|
|
|
|
Op.getOperand(1), Op.getOperand(2), Op.getOperand(3));
|
|
|
|
|
|
|
|
case Intrinsic::amdgcn_trig_preop:
|
|
|
|
return DAG.getNode(AMDGPUISD::TRIG_PREOP, DL, VT,
|
|
|
|
Op.getOperand(1), Op.getOperand(2));
|
|
|
|
case Intrinsic::amdgcn_div_scale: {
|
|
|
|
// 3rd parameter required to be a constant.
|
|
|
|
const ConstantSDNode *Param = dyn_cast<ConstantSDNode>(Op.getOperand(3));
|
|
|
|
if (!Param)
|
|
|
|
return DAG.getUNDEF(VT);
|
|
|
|
|
|
|
|
// Translate to the operands expected by the machine instruction. The
|
|
|
|
// first parameter must be the same as the first instruction.
|
|
|
|
SDValue Numerator = Op.getOperand(1);
|
|
|
|
SDValue Denominator = Op.getOperand(2);
|
|
|
|
|
|
|
|
// Note this order is opposite of the machine instruction's operations,
|
|
|
|
// which is s0.f = Quotient, s1.f = Denominator, s2.f = Numerator. The
|
|
|
|
// intrinsic has the numerator as the first operand to match a normal
|
|
|
|
// division operation.
|
|
|
|
|
|
|
|
SDValue Src0 = Param->isAllOnesValue() ? Numerator : Denominator;
|
|
|
|
|
|
|
|
return DAG.getNode(AMDGPUISD::DIV_SCALE, DL, Op->getVTList(), Src0,
|
|
|
|
Denominator, Numerator);
|
|
|
|
}
|
|
|
|
case AMDGPUIntrinsic::AMDGPU_cvt_f32_ubyte0:
|
|
|
|
return DAG.getNode(AMDGPUISD::CVT_F32_UBYTE0, DL, VT, Op.getOperand(1));
|
|
|
|
case AMDGPUIntrinsic::AMDGPU_cvt_f32_ubyte1:
|
|
|
|
return DAG.getNode(AMDGPUISD::CVT_F32_UBYTE1, DL, VT, Op.getOperand(1));
|
|
|
|
case AMDGPUIntrinsic::AMDGPU_cvt_f32_ubyte2:
|
|
|
|
return DAG.getNode(AMDGPUISD::CVT_F32_UBYTE2, DL, VT, Op.getOperand(1));
|
|
|
|
case AMDGPUIntrinsic::AMDGPU_cvt_f32_ubyte3:
|
|
|
|
return DAG.getNode(AMDGPUISD::CVT_F32_UBYTE3, DL, VT, Op.getOperand(1));
|
2014-07-26 14:23:37 +08:00
|
|
|
default:
|
|
|
|
return AMDGPUTargetLowering::LowerOperation(Op, DAG);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-04-12 22:05:04 +08:00
|
|
|
SDValue SITargetLowering::LowerINTRINSIC_W_CHAIN(SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
unsigned IntrID = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue();
|
|
|
|
switch (IntrID) {
|
|
|
|
case Intrinsic::amdgcn_atomic_inc:
|
|
|
|
case Intrinsic::amdgcn_atomic_dec: {
|
|
|
|
MemSDNode *M = cast<MemSDNode>(Op);
|
|
|
|
unsigned Opc = (IntrID == Intrinsic::amdgcn_atomic_inc) ?
|
|
|
|
AMDGPUISD::ATOMIC_INC : AMDGPUISD::ATOMIC_DEC;
|
|
|
|
SDValue Ops[] = {
|
|
|
|
M->getOperand(0), // Chain
|
|
|
|
M->getOperand(2), // Ptr
|
|
|
|
M->getOperand(3) // Value
|
|
|
|
};
|
|
|
|
|
|
|
|
return DAG.getMemIntrinsicNode(Opc, SDLoc(Op), M->getVTList(), Ops,
|
|
|
|
M->getMemoryVT(), M->getMemOperand());
|
|
|
|
}
|
|
|
|
default:
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-07-26 14:23:37 +08:00
|
|
|
SDValue SITargetLowering::LowerINTRINSIC_VOID(SDValue Op,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
MachineFunction &MF = DAG.getMachineFunction();
|
2015-05-12 22:18:14 +08:00
|
|
|
SDLoc DL(Op);
|
2014-07-26 14:23:37 +08:00
|
|
|
SDValue Chain = Op.getOperand(0);
|
|
|
|
unsigned IntrinsicID = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue();
|
|
|
|
|
|
|
|
switch (IntrinsicID) {
|
2015-05-12 22:18:14 +08:00
|
|
|
case AMDGPUIntrinsic::SI_sendmsg: {
|
|
|
|
Chain = copyToM0(DAG, Chain, DL, Op.getOperand(3));
|
|
|
|
SDValue Glue = Chain.getValue(1);
|
|
|
|
return DAG.getNode(AMDGPUISD::SENDMSG, DL, MVT::Other, Chain,
|
|
|
|
Op.getOperand(2), Glue);
|
|
|
|
}
|
2014-07-26 14:23:37 +08:00
|
|
|
case AMDGPUIntrinsic::SI_tbuffer_store: {
|
|
|
|
SDValue Ops[] = {
|
|
|
|
Chain,
|
|
|
|
Op.getOperand(2),
|
|
|
|
Op.getOperand(3),
|
|
|
|
Op.getOperand(4),
|
|
|
|
Op.getOperand(5),
|
|
|
|
Op.getOperand(6),
|
|
|
|
Op.getOperand(7),
|
|
|
|
Op.getOperand(8),
|
|
|
|
Op.getOperand(9),
|
|
|
|
Op.getOperand(10),
|
|
|
|
Op.getOperand(11),
|
|
|
|
Op.getOperand(12),
|
|
|
|
Op.getOperand(13),
|
|
|
|
Op.getOperand(14)
|
|
|
|
};
|
|
|
|
|
|
|
|
EVT VT = Op.getOperand(3).getValueType();
|
|
|
|
|
|
|
|
MachineMemOperand *MMO = MF.getMachineMemOperand(
|
|
|
|
MachinePointerInfo(),
|
|
|
|
MachineMemOperand::MOStore,
|
|
|
|
VT.getStoreSize(), 4);
|
|
|
|
return DAG.getMemIntrinsicNode(AMDGPUISD::TBUFFER_STORE_FORMAT, DL,
|
|
|
|
Op->getVTList(), Ops, VT, MMO);
|
|
|
|
}
|
|
|
|
default:
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-11-14 07:36:50 +08:00
|
|
|
SDValue SITargetLowering::LowerLOAD(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
SDLoc DL(Op);
|
|
|
|
LoadSDNode *Load = cast<LoadSDNode>(Op);
|
2016-02-11 02:21:39 +08:00
|
|
|
ISD::LoadExtType ExtType = Load->getExtensionType();
|
2016-02-11 02:21:45 +08:00
|
|
|
EVT MemVT = Load->getMemoryVT();
|
2016-02-11 02:21:39 +08:00
|
|
|
|
2016-02-11 02:21:45 +08:00
|
|
|
if (ExtType == ISD::NON_EXTLOAD && MemVT.getSizeInBits() < 32) {
|
|
|
|
assert(MemVT == MVT::i1 && "Only i1 non-extloads expected");
|
2016-02-11 02:21:39 +08:00
|
|
|
// FIXME: Copied from PPC
|
|
|
|
// First, load into 32 bits, then truncate to 1 bit.
|
|
|
|
|
|
|
|
SDValue Chain = Load->getChain();
|
|
|
|
SDValue BasePtr = Load->getBasePtr();
|
|
|
|
MachineMemOperand *MMO = Load->getMemOperand();
|
|
|
|
|
|
|
|
SDValue NewLD = DAG.getExtLoad(ISD::EXTLOAD, DL, MVT::i32, Chain,
|
|
|
|
BasePtr, MVT::i8, MMO);
|
|
|
|
|
|
|
|
SDValue Ops[] = {
|
2016-02-11 02:21:45 +08:00
|
|
|
DAG.getNode(ISD::TRUNCATE, DL, MemVT, NewLD),
|
2016-02-11 02:21:39 +08:00
|
|
|
NewLD.getValue(1)
|
|
|
|
};
|
|
|
|
|
|
|
|
return DAG.getMergeValues(Ops, DL);
|
|
|
|
}
|
2014-07-08 02:34:45 +08:00
|
|
|
|
2016-02-11 02:21:45 +08:00
|
|
|
if (!MemVT.isVector())
|
|
|
|
return SDValue();
|
2015-11-24 20:05:03 +08:00
|
|
|
|
2016-02-11 02:21:45 +08:00
|
|
|
assert(Op.getValueType().getVectorElementType() == MVT::i32 &&
|
|
|
|
"Custom lowering for non-i32 vectors hasn't been implemented.");
|
|
|
|
|
2016-05-03 04:13:51 +08:00
|
|
|
unsigned AS = Load->getAddressSpace();
|
|
|
|
if (!allowsMemoryAccess(*DAG.getContext(), DAG.getDataLayout(), MemVT,
|
|
|
|
AS, Load->getAlignment())) {
|
|
|
|
SDValue Ops[2];
|
|
|
|
std::tie(Ops[0], Ops[1]) = expandUnalignedLoad(Load, DAG);
|
|
|
|
return DAG.getMergeValues(Ops, DL);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned NumElements = MemVT.getVectorNumElements();
|
|
|
|
switch (AS) {
|
2016-02-11 02:21:45 +08:00
|
|
|
case AMDGPUAS::CONSTANT_ADDRESS:
|
|
|
|
if (isMemOpUniform(Load))
|
|
|
|
return SDValue();
|
|
|
|
// Non-uniform loads will be selected to MUBUF instructions, so they
|
|
|
|
// have the same legalization requires ments as global and private
|
|
|
|
// loads.
|
|
|
|
//
|
|
|
|
// Fall-through
|
|
|
|
case AMDGPUAS::GLOBAL_ADDRESS:
|
2016-02-13 12:18:53 +08:00
|
|
|
case AMDGPUAS::FLAT_ADDRESS:
|
|
|
|
if (NumElements > 4)
|
2016-02-11 02:21:45 +08:00
|
|
|
return SplitVectorLoad(Op, DAG);
|
|
|
|
// v4 loads are supported for private and global memory.
|
|
|
|
return SDValue();
|
2016-02-13 12:18:53 +08:00
|
|
|
case AMDGPUAS::PRIVATE_ADDRESS: {
|
|
|
|
// Depending on the setting of the private_element_size field in the
|
|
|
|
// resource descriptor, we can only make private accesses up to a certain
|
|
|
|
// size.
|
|
|
|
switch (Subtarget->getMaxPrivateElementSize()) {
|
|
|
|
case 4:
|
2016-04-15 07:31:26 +08:00
|
|
|
return scalarizeVectorLoad(Load, DAG);
|
2016-02-13 12:18:53 +08:00
|
|
|
case 8:
|
|
|
|
if (NumElements > 2)
|
|
|
|
return SplitVectorLoad(Op, DAG);
|
|
|
|
return SDValue();
|
|
|
|
case 16:
|
|
|
|
// Same as global/flat
|
|
|
|
if (NumElements > 4)
|
|
|
|
return SplitVectorLoad(Op, DAG);
|
|
|
|
return SDValue();
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unsupported private_element_size");
|
|
|
|
}
|
|
|
|
}
|
2016-05-03 04:13:51 +08:00
|
|
|
case AMDGPUAS::LOCAL_ADDRESS: {
|
|
|
|
if (NumElements > 2)
|
|
|
|
return SplitVectorLoad(Op, DAG);
|
|
|
|
|
|
|
|
if (NumElements == 2)
|
|
|
|
return SDValue();
|
|
|
|
|
2016-02-11 02:21:45 +08:00
|
|
|
// If properly aligned, if we split we might be able to use ds_read_b64.
|
|
|
|
return SplitVectorLoad(Op, DAG);
|
2016-05-03 04:13:51 +08:00
|
|
|
}
|
2016-02-11 02:21:45 +08:00
|
|
|
default:
|
|
|
|
return SDValue();
|
2014-03-25 01:50:46 +08:00
|
|
|
}
|
2013-11-14 07:36:50 +08:00
|
|
|
}
|
|
|
|
|
2014-02-05 01:18:40 +08:00
|
|
|
SDValue SITargetLowering::LowerSELECT(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
if (Op.getValueType() != MVT::i64)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
SDLoc DL(Op);
|
|
|
|
SDValue Cond = Op.getOperand(0);
|
|
|
|
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue Zero = DAG.getConstant(0, DL, MVT::i32);
|
|
|
|
SDValue One = DAG.getConstant(1, DL, MVT::i32);
|
2014-02-05 01:18:40 +08:00
|
|
|
|
2014-03-31 22:01:55 +08:00
|
|
|
SDValue LHS = DAG.getNode(ISD::BITCAST, DL, MVT::v2i32, Op.getOperand(1));
|
|
|
|
SDValue RHS = DAG.getNode(ISD::BITCAST, DL, MVT::v2i32, Op.getOperand(2));
|
|
|
|
|
|
|
|
SDValue Lo0 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, LHS, Zero);
|
|
|
|
SDValue Lo1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, RHS, Zero);
|
2014-02-05 01:18:40 +08:00
|
|
|
|
|
|
|
SDValue Lo = DAG.getSelect(DL, MVT::i32, Cond, Lo0, Lo1);
|
|
|
|
|
2014-03-31 22:01:55 +08:00
|
|
|
SDValue Hi0 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, LHS, One);
|
|
|
|
SDValue Hi1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, MVT::i32, RHS, One);
|
2014-02-05 01:18:40 +08:00
|
|
|
|
|
|
|
SDValue Hi = DAG.getSelect(DL, MVT::i32, Cond, Hi0, Hi1);
|
|
|
|
|
2016-04-27 05:15:30 +08:00
|
|
|
SDValue Res = DAG.getBuildVector(MVT::v2i32, DL, {Lo, Hi});
|
2014-03-31 22:01:55 +08:00
|
|
|
return DAG.getNode(ISD::BITCAST, DL, MVT::i64, Res);
|
2014-02-05 01:18:40 +08:00
|
|
|
}
|
|
|
|
|
2014-07-16 07:50:10 +08:00
|
|
|
// Catch division cases where we can use shortcuts with rcp and rsq
|
|
|
|
// instructions.
|
|
|
|
SDValue SITargetLowering::LowerFastFDIV(SDValue Op, SelectionDAG &DAG) const {
|
2014-07-16 04:18:31 +08:00
|
|
|
SDLoc SL(Op);
|
|
|
|
SDValue LHS = Op.getOperand(0);
|
|
|
|
SDValue RHS = Op.getOperand(1);
|
|
|
|
EVT VT = Op.getValueType();
|
2014-07-16 07:50:10 +08:00
|
|
|
bool Unsafe = DAG.getTarget().Options.UnsafeFPMath;
|
2014-07-16 04:18:31 +08:00
|
|
|
|
|
|
|
if (const ConstantFPSDNode *CLHS = dyn_cast<ConstantFPSDNode>(LHS)) {
|
2014-07-16 07:50:10 +08:00
|
|
|
if ((Unsafe || (VT == MVT::f32 && !Subtarget->hasFP32Denormals())) &&
|
|
|
|
CLHS->isExactlyValue(1.0)) {
|
|
|
|
// v_rcp_f32 and v_rsq_f32 do not support denormals, and according to
|
|
|
|
// the CI documentation has a worst case error of 1 ulp.
|
|
|
|
// OpenCL requires <= 2.5 ulp for 1.0 / x, so it should always be OK to
|
|
|
|
// use it as long as we aren't trying to use denormals.
|
2014-07-16 04:18:31 +08:00
|
|
|
|
|
|
|
// 1.0 / sqrt(x) -> rsq(x)
|
2014-07-16 07:50:10 +08:00
|
|
|
//
|
|
|
|
// XXX - Is UnsafeFPMath sufficient to do this for f64? The maximum ULP
|
|
|
|
// error seems really high at 2^29 ULP.
|
2014-07-16 04:18:31 +08:00
|
|
|
if (RHS.getOpcode() == ISD::FSQRT)
|
|
|
|
return DAG.getNode(AMDGPUISD::RSQ, SL, VT, RHS.getOperand(0));
|
|
|
|
|
|
|
|
// 1.0 / x -> rcp(x)
|
|
|
|
return DAG.getNode(AMDGPUISD::RCP, SL, VT, RHS);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
const SDNodeFlags *Flags = Op->getFlags();
|
|
|
|
|
|
|
|
if (Unsafe || Flags->hasAllowReciprocal()) {
|
2014-07-16 07:50:10 +08:00
|
|
|
// Turn into multiply by the reciprocal.
|
|
|
|
// x / y -> x * (1.0 / y)
|
2015-09-17 00:31:21 +08:00
|
|
|
SDNodeFlags Flags;
|
|
|
|
Flags.setUnsafeAlgebra(true);
|
2014-07-16 07:50:10 +08:00
|
|
|
SDValue Recip = DAG.getNode(AMDGPUISD::RCP, SL, VT, RHS);
|
2015-09-17 00:31:21 +08:00
|
|
|
return DAG.getNode(ISD::FMUL, SL, VT, LHS, Recip, &Flags);
|
2014-07-16 07:50:10 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue();
|
2014-07-16 04:18:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::LowerFDIV32(SDValue Op, SelectionDAG &DAG) const {
|
2016-06-08 04:27:12 +08:00
|
|
|
if (SDValue FastLowered = LowerFastFDIV(Op, DAG))
|
|
|
|
return FastLowered;
|
2014-07-16 07:50:10 +08:00
|
|
|
|
|
|
|
// This uses v_rcp_f32 which does not handle denormals. Let this hit a
|
|
|
|
// selection error for now rather than do something incorrect.
|
|
|
|
if (Subtarget->hasFP32Denormals())
|
|
|
|
return SDValue();
|
2014-07-16 04:18:31 +08:00
|
|
|
|
|
|
|
SDLoc SL(Op);
|
|
|
|
SDValue LHS = Op.getOperand(0);
|
|
|
|
SDValue RHS = Op.getOperand(1);
|
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
// faster 2.5 ulp fdiv when using -amdgpu-fast-fdiv flag
|
|
|
|
if (EnableAMDGPUFastFDIV) {
|
|
|
|
SDValue r1 = DAG.getNode(ISD::FABS, SL, MVT::f32, RHS);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
const APFloat K0Val(BitsToFloat(0x6f800000));
|
|
|
|
const SDValue K0 = DAG.getConstantFP(K0Val, SL, MVT::f32);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
const APFloat K1Val(BitsToFloat(0x2f800000));
|
|
|
|
const SDValue K1 = DAG.getConstantFP(K1Val, SL, MVT::f32);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
const SDValue One = DAG.getConstantFP(1.0, SL, MVT::f32);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
EVT SetCCVT =
|
|
|
|
getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), MVT::f32);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue r2 = DAG.getSetCC(SL, SetCCVT, r1, K0, ISD::SETOGT);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue r3 = DAG.getNode(ISD::SELECT, SL, MVT::f32, r2, K1, One);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
// TODO: Should this propagate fast-math-flags?
|
2015-09-17 00:31:21 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
r1 = DAG.getNode(ISD::FMUL, SL, MVT::f32, RHS, r3);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue r0 = DAG.getNode(AMDGPUISD::RCP, SL, MVT::f32, r1);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue Mul = DAG.getNode(ISD::FMUL, SL, MVT::f32, LHS, r0);
|
2014-07-16 04:18:31 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
return DAG.getNode(ISD::FMUL, SL, MVT::f32, r3, Mul);
|
2016-06-10 10:18:02 +08:00
|
|
|
}
|
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
// Generates more precise fpdiv32.
|
|
|
|
const SDValue One = DAG.getConstantFP(1.0, SL, MVT::f32);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDVTList ScaleVT = DAG.getVTList(MVT::f32, MVT::i1);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue DenominatorScaled = DAG.getNode(AMDGPUISD::DIV_SCALE, SL, ScaleVT, RHS, RHS, LHS);
|
|
|
|
SDValue NumeratorScaled = DAG.getNode(AMDGPUISD::DIV_SCALE, SL, ScaleVT, LHS, RHS, LHS);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue ApproxRcp = DAG.getNode(AMDGPUISD::RCP, SL, MVT::f32, DenominatorScaled);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue NegDivScale0 = DAG.getNode(ISD::FNEG, SL, MVT::f32, DenominatorScaled);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue Fma0 = DAG.getNode(ISD::FMA, SL, MVT::f32, NegDivScale0, ApproxRcp, One);
|
|
|
|
SDValue Fma1 = DAG.getNode(ISD::FMA, SL, MVT::f32, Fma0, ApproxRcp, ApproxRcp);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue Mul = DAG.getNode(ISD::FMUL, SL, MVT::f32, NumeratorScaled, Fma1);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue Fma2 = DAG.getNode(ISD::FMA, SL, MVT::f32, NegDivScale0, Mul, NumeratorScaled);
|
|
|
|
SDValue Fma3 = DAG.getNode(ISD::FMA, SL, MVT::f32, Fma2, Fma1, Mul);
|
|
|
|
SDValue Fma4 = DAG.getNode(ISD::FMA, SL, MVT::f32, NegDivScale0, Fma3, NumeratorScaled);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
SDValue Scale = NumeratorScaled.getValue(1);
|
|
|
|
SDValue Fmas = DAG.getNode(AMDGPUISD::DIV_FMAS, SL, MVT::f32, Fma4, Fma1, Fma3, Scale);
|
2016-06-10 10:18:02 +08:00
|
|
|
|
2016-06-10 03:17:15 +08:00
|
|
|
return DAG.getNode(AMDGPUISD::DIV_FIXUP, SL, MVT::f32, Fmas, RHS, LHS);
|
2014-07-16 04:18:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::LowerFDIV64(SDValue Op, SelectionDAG &DAG) const {
|
2015-02-14 12:30:08 +08:00
|
|
|
if (DAG.getTarget().Options.UnsafeFPMath)
|
|
|
|
return LowerFastFDIV(Op, DAG);
|
|
|
|
|
|
|
|
SDLoc SL(Op);
|
|
|
|
SDValue X = Op.getOperand(0);
|
|
|
|
SDValue Y = Op.getOperand(1);
|
|
|
|
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue One = DAG.getConstantFP(1.0, SL, MVT::f64);
|
2015-02-14 12:30:08 +08:00
|
|
|
|
|
|
|
SDVTList ScaleVT = DAG.getVTList(MVT::f64, MVT::i1);
|
|
|
|
|
|
|
|
SDValue DivScale0 = DAG.getNode(AMDGPUISD::DIV_SCALE, SL, ScaleVT, Y, Y, X);
|
|
|
|
|
|
|
|
SDValue NegDivScale0 = DAG.getNode(ISD::FNEG, SL, MVT::f64, DivScale0);
|
|
|
|
|
|
|
|
SDValue Rcp = DAG.getNode(AMDGPUISD::RCP, SL, MVT::f64, DivScale0);
|
|
|
|
|
|
|
|
SDValue Fma0 = DAG.getNode(ISD::FMA, SL, MVT::f64, NegDivScale0, Rcp, One);
|
|
|
|
|
|
|
|
SDValue Fma1 = DAG.getNode(ISD::FMA, SL, MVT::f64, Rcp, Fma0, Rcp);
|
|
|
|
|
|
|
|
SDValue Fma2 = DAG.getNode(ISD::FMA, SL, MVT::f64, NegDivScale0, Fma1, One);
|
|
|
|
|
|
|
|
SDValue DivScale1 = DAG.getNode(AMDGPUISD::DIV_SCALE, SL, ScaleVT, X, Y, X);
|
|
|
|
|
|
|
|
SDValue Fma3 = DAG.getNode(ISD::FMA, SL, MVT::f64, Fma1, Fma2, Fma1);
|
|
|
|
SDValue Mul = DAG.getNode(ISD::FMUL, SL, MVT::f64, DivScale1, Fma3);
|
|
|
|
|
|
|
|
SDValue Fma4 = DAG.getNode(ISD::FMA, SL, MVT::f64,
|
|
|
|
NegDivScale0, Mul, DivScale1);
|
|
|
|
|
|
|
|
SDValue Scale;
|
|
|
|
|
2016-06-24 14:30:11 +08:00
|
|
|
if (Subtarget->getGeneration() == SISubtarget::SOUTHERN_ISLANDS) {
|
2015-02-14 12:30:08 +08:00
|
|
|
// Workaround a hardware bug on SI where the condition output from div_scale
|
|
|
|
// is not usable.
|
|
|
|
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue Hi = DAG.getConstant(1, SL, MVT::i32);
|
2015-02-14 12:30:08 +08:00
|
|
|
|
|
|
|
// Figure out if the scale to use for div_fmas.
|
|
|
|
SDValue NumBC = DAG.getNode(ISD::BITCAST, SL, MVT::v2i32, X);
|
|
|
|
SDValue DenBC = DAG.getNode(ISD::BITCAST, SL, MVT::v2i32, Y);
|
|
|
|
SDValue Scale0BC = DAG.getNode(ISD::BITCAST, SL, MVT::v2i32, DivScale0);
|
|
|
|
SDValue Scale1BC = DAG.getNode(ISD::BITCAST, SL, MVT::v2i32, DivScale1);
|
|
|
|
|
|
|
|
SDValue NumHi = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, SL, MVT::i32, NumBC, Hi);
|
|
|
|
SDValue DenHi = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, SL, MVT::i32, DenBC, Hi);
|
|
|
|
|
|
|
|
SDValue Scale0Hi
|
|
|
|
= DAG.getNode(ISD::EXTRACT_VECTOR_ELT, SL, MVT::i32, Scale0BC, Hi);
|
|
|
|
SDValue Scale1Hi
|
|
|
|
= DAG.getNode(ISD::EXTRACT_VECTOR_ELT, SL, MVT::i32, Scale1BC, Hi);
|
|
|
|
|
|
|
|
SDValue CmpDen = DAG.getSetCC(SL, MVT::i1, DenHi, Scale0Hi, ISD::SETEQ);
|
|
|
|
SDValue CmpNum = DAG.getSetCC(SL, MVT::i1, NumHi, Scale1Hi, ISD::SETEQ);
|
|
|
|
Scale = DAG.getNode(ISD::XOR, SL, MVT::i1, CmpNum, CmpDen);
|
|
|
|
} else {
|
|
|
|
Scale = DivScale1.getValue(1);
|
|
|
|
}
|
|
|
|
|
|
|
|
SDValue Fmas = DAG.getNode(AMDGPUISD::DIV_FMAS, SL, MVT::f64,
|
|
|
|
Fma4, Fma3, Mul, Scale);
|
|
|
|
|
|
|
|
return DAG.getNode(AMDGPUISD::DIV_FIXUP, SL, MVT::f64, Fmas, Y, X);
|
2014-07-16 04:18:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::LowerFDIV(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
EVT VT = Op.getValueType();
|
|
|
|
|
|
|
|
if (VT == MVT::f32)
|
|
|
|
return LowerFDIV32(Op, DAG);
|
|
|
|
|
|
|
|
if (VT == MVT::f64)
|
|
|
|
return LowerFDIV64(Op, DAG);
|
|
|
|
|
|
|
|
llvm_unreachable("Unexpected type for fdiv");
|
|
|
|
}
|
|
|
|
|
2013-11-14 07:36:50 +08:00
|
|
|
SDValue SITargetLowering::LowerSTORE(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
SDLoc DL(Op);
|
|
|
|
StoreSDNode *Store = cast<StoreSDNode>(Op);
|
|
|
|
EVT VT = Store->getMemoryVT();
|
|
|
|
|
2016-02-11 13:32:46 +08:00
|
|
|
if (VT == MVT::i1) {
|
|
|
|
return DAG.getTruncStore(Store->getChain(), DL,
|
|
|
|
DAG.getSExtOrTrunc(Store->getValue(), DL, MVT::i32),
|
|
|
|
Store->getBasePtr(), MVT::i1, Store->getMemOperand());
|
2014-07-21 23:45:01 +08:00
|
|
|
}
|
|
|
|
|
2016-05-03 04:13:51 +08:00
|
|
|
assert(VT.isVector() &&
|
|
|
|
Store->getValue().getValueType().getScalarType() == MVT::i32);
|
|
|
|
|
|
|
|
unsigned AS = Store->getAddressSpace();
|
|
|
|
if (!allowsMemoryAccess(*DAG.getContext(), DAG.getDataLayout(), VT,
|
|
|
|
AS, Store->getAlignment())) {
|
|
|
|
return expandUnalignedStore(Store, DAG);
|
|
|
|
}
|
2013-11-14 07:36:50 +08:00
|
|
|
|
2016-02-13 12:18:53 +08:00
|
|
|
unsigned NumElements = VT.getVectorNumElements();
|
2016-05-03 04:13:51 +08:00
|
|
|
switch (AS) {
|
2016-02-13 12:18:53 +08:00
|
|
|
case AMDGPUAS::GLOBAL_ADDRESS:
|
|
|
|
case AMDGPUAS::FLAT_ADDRESS:
|
|
|
|
if (NumElements > 4)
|
|
|
|
return SplitVectorStore(Op, DAG);
|
|
|
|
return SDValue();
|
|
|
|
case AMDGPUAS::PRIVATE_ADDRESS: {
|
|
|
|
switch (Subtarget->getMaxPrivateElementSize()) {
|
|
|
|
case 4:
|
2016-04-15 07:31:26 +08:00
|
|
|
return scalarizeVectorStore(Store, DAG);
|
2016-02-13 12:18:53 +08:00
|
|
|
case 8:
|
|
|
|
if (NumElements > 2)
|
|
|
|
return SplitVectorStore(Op, DAG);
|
|
|
|
return SDValue();
|
|
|
|
case 16:
|
|
|
|
if (NumElements > 4)
|
|
|
|
return SplitVectorStore(Op, DAG);
|
|
|
|
return SDValue();
|
|
|
|
default:
|
|
|
|
llvm_unreachable("unsupported private_element_size");
|
|
|
|
}
|
|
|
|
}
|
2016-05-03 04:13:51 +08:00
|
|
|
case AMDGPUAS::LOCAL_ADDRESS: {
|
|
|
|
if (NumElements > 2)
|
|
|
|
return SplitVectorStore(Op, DAG);
|
|
|
|
|
|
|
|
if (NumElements == 2)
|
|
|
|
return Op;
|
|
|
|
|
2016-02-11 13:32:46 +08:00
|
|
|
// If properly aligned, if we split we might be able to use ds_write_b64.
|
|
|
|
return SplitVectorStore(Op, DAG);
|
2016-05-03 04:13:51 +08:00
|
|
|
}
|
2016-02-13 12:18:53 +08:00
|
|
|
default:
|
|
|
|
llvm_unreachable("unhandled address space");
|
2016-02-11 13:32:46 +08:00
|
|
|
}
|
2013-11-14 07:36:50 +08:00
|
|
|
}
|
|
|
|
|
2014-07-20 02:44:39 +08:00
|
|
|
SDValue SITargetLowering::LowerTrig(SDValue Op, SelectionDAG &DAG) const {
|
2015-04-28 22:05:47 +08:00
|
|
|
SDLoc DL(Op);
|
2014-07-20 02:44:39 +08:00
|
|
|
EVT VT = Op.getValueType();
|
|
|
|
SDValue Arg = Op.getOperand(0);
|
2015-09-17 00:31:21 +08:00
|
|
|
// TODO: Should this propagate fast-math-flags?
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue FractPart = DAG.getNode(AMDGPUISD::FRACT, DL, VT,
|
|
|
|
DAG.getNode(ISD::FMUL, DL, VT, Arg,
|
|
|
|
DAG.getConstantFP(0.5/M_PI, DL,
|
|
|
|
VT)));
|
2014-07-20 02:44:39 +08:00
|
|
|
|
|
|
|
switch (Op.getOpcode()) {
|
|
|
|
case ISD::FCOS:
|
|
|
|
return DAG.getNode(AMDGPUISD::COS_HW, SDLoc(Op), VT, FractPart);
|
|
|
|
case ISD::FSIN:
|
|
|
|
return DAG.getNode(AMDGPUISD::SIN_HW, SDLoc(Op), VT, FractPart);
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Wrong trig opcode");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
SDValue SITargetLowering::LowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const {
|
|
|
|
AtomicSDNode *AtomicNode = cast<AtomicSDNode>(Op);
|
|
|
|
assert(AtomicNode->isCompareAndSwap());
|
|
|
|
unsigned AS = AtomicNode->getAddressSpace();
|
|
|
|
|
|
|
|
// No custom lowering required for local address space
|
|
|
|
if (!isFlatGlobalAddrSpace(AS))
|
|
|
|
return Op;
|
|
|
|
|
|
|
|
// Non-local address space requires custom lowering for atomic compare
|
|
|
|
// and swap; cmp and swap should be in a v2i32 or v2i64 in case of _X2
|
|
|
|
SDLoc DL(Op);
|
|
|
|
SDValue ChainIn = Op.getOperand(0);
|
|
|
|
SDValue Addr = Op.getOperand(1);
|
|
|
|
SDValue Old = Op.getOperand(2);
|
|
|
|
SDValue New = Op.getOperand(3);
|
|
|
|
EVT VT = Op.getValueType();
|
|
|
|
MVT SimpleVT = VT.getSimpleVT();
|
|
|
|
MVT VecType = MVT::getVectorVT(SimpleVT, 2);
|
|
|
|
|
2016-04-27 05:15:30 +08:00
|
|
|
SDValue NewOld = DAG.getBuildVector(VecType, DL, {New, Old});
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
SDValue Ops[] = { ChainIn, Addr, NewOld };
|
2016-06-10 07:42:48 +08:00
|
|
|
|
|
|
|
return DAG.getMemIntrinsicNode(AMDGPUISD::ATOMIC_CMP_SWAP, DL, Op->getVTList(),
|
|
|
|
Ops, VT, AtomicNode->getMemOperand());
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
}
|
|
|
|
|
2012-12-12 05:25:42 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Custom DAG optimizations
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2014-06-12 01:50:44 +08:00
|
|
|
SDValue SITargetLowering::performUCharToFloatCombine(SDNode *N,
|
2015-01-14 09:35:22 +08:00
|
|
|
DAGCombinerInfo &DCI) const {
|
2014-06-12 01:50:44 +08:00
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
EVT ScalarVT = VT.getScalarType();
|
|
|
|
if (ScalarVT != MVT::f32)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
SDLoc DL(N);
|
|
|
|
|
|
|
|
SDValue Src = N->getOperand(0);
|
|
|
|
EVT SrcVT = Src.getValueType();
|
|
|
|
|
|
|
|
// TODO: We could try to match extracting the higher bytes, which would be
|
|
|
|
// easier if i8 vectors weren't promoted to i32 vectors, particularly after
|
|
|
|
// types are legalized. v4i8 -> v4f32 is probably the only case to worry
|
|
|
|
// about in practice.
|
|
|
|
if (DCI.isAfterLegalizeVectorOps() && SrcVT == MVT::i32) {
|
|
|
|
if (DAG.MaskedValueIsZero(Src, APInt::getHighBitsSet(32, 24))) {
|
|
|
|
SDValue Cvt = DAG.getNode(AMDGPUISD::CVT_F32_UBYTE0, DL, VT, Src);
|
|
|
|
DCI.AddToWorklist(Cvt.getNode());
|
|
|
|
return Cvt;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2015-03-12 02:43:21 +08:00
|
|
|
/// \brief Return true if the given offset Size in bytes can be folded into
|
|
|
|
/// the immediate offsets of a memory instruction for the given address space.
|
|
|
|
static bool canFoldOffset(unsigned OffsetSize, unsigned AS,
|
2016-06-24 14:30:11 +08:00
|
|
|
const SISubtarget &STI) {
|
2015-03-12 02:43:21 +08:00
|
|
|
switch (AS) {
|
|
|
|
case AMDGPUAS::GLOBAL_ADDRESS: {
|
|
|
|
// MUBUF instructions a 12-bit offset in bytes.
|
|
|
|
return isUInt<12>(OffsetSize);
|
|
|
|
}
|
|
|
|
case AMDGPUAS::CONSTANT_ADDRESS: {
|
|
|
|
// SMRD instructions have an 8-bit offset in dwords on SI and
|
|
|
|
// a 20-bit offset in bytes on VI.
|
2016-06-24 14:30:11 +08:00
|
|
|
if (STI.getGeneration() >= SISubtarget::VOLCANIC_ISLANDS)
|
2015-03-12 02:43:21 +08:00
|
|
|
return isUInt<20>(OffsetSize);
|
|
|
|
else
|
|
|
|
return (OffsetSize % 4 == 0) && isUInt<8>(OffsetSize / 4);
|
|
|
|
}
|
|
|
|
case AMDGPUAS::LOCAL_ADDRESS:
|
|
|
|
case AMDGPUAS::REGION_ADDRESS: {
|
|
|
|
// The single offset versions have a 16-bit offset in bytes.
|
|
|
|
return isUInt<16>(OffsetSize);
|
|
|
|
}
|
|
|
|
case AMDGPUAS::PRIVATE_ADDRESS:
|
|
|
|
// Indirect register addressing does not use any offsets.
|
|
|
|
default:
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-08-16 01:49:05 +08:00
|
|
|
// (shl (add x, c1), c2) -> add (shl x, c2), (shl c1, c2)
|
|
|
|
|
|
|
|
// This is a variant of
|
|
|
|
// (mul (add x, c1), c2) -> add (mul x, c2), (mul c1, c2),
|
|
|
|
//
|
|
|
|
// The normal DAG combiner will do this, but only if the add has one use since
|
|
|
|
// that would increase the number of instructions.
|
|
|
|
//
|
|
|
|
// This prevents us from seeing a constant offset that can be folded into a
|
|
|
|
// memory instruction's addressing mode. If we know the resulting add offset of
|
|
|
|
// a pointer can be folded into an addressing offset, we can replace the pointer
|
|
|
|
// operand with the add of new constant offset. This eliminates one of the uses,
|
|
|
|
// and may allow the remaining use to also be simplified.
|
|
|
|
//
|
|
|
|
SDValue SITargetLowering::performSHLPtrCombine(SDNode *N,
|
|
|
|
unsigned AddrSpace,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
SDValue N0 = N->getOperand(0);
|
|
|
|
SDValue N1 = N->getOperand(1);
|
|
|
|
|
|
|
|
if (N0.getOpcode() != ISD::ADD)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
const ConstantSDNode *CN1 = dyn_cast<ConstantSDNode>(N1);
|
|
|
|
if (!CN1)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
const ConstantSDNode *CAdd = dyn_cast<ConstantSDNode>(N0.getOperand(1));
|
|
|
|
if (!CAdd)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
// If the resulting offset is too large, we can't fold it into the addressing
|
|
|
|
// mode offset.
|
|
|
|
APInt Offset = CAdd->getAPIntValue() << CN1->getAPIntValue();
|
2016-06-24 14:30:11 +08:00
|
|
|
if (!canFoldOffset(Offset.getZExtValue(), AddrSpace, *getSubtarget()))
|
2014-08-16 01:49:05 +08:00
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
SDLoc SL(N);
|
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
|
|
|
|
SDValue ShlX = DAG.getNode(ISD::SHL, SL, VT, N0.getOperand(0), N1);
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue COffset = DAG.getConstant(Offset, SL, MVT::i32);
|
2014-08-16 01:49:05 +08:00
|
|
|
|
|
|
|
return DAG.getNode(ISD::ADD, SL, VT, ShlX, COffset);
|
|
|
|
}
|
|
|
|
|
2015-01-07 07:00:46 +08:00
|
|
|
SDValue SITargetLowering::performAndCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
if (DCI.isBeforeLegalize())
|
|
|
|
return SDValue();
|
|
|
|
|
2016-01-19 06:01:13 +08:00
|
|
|
if (SDValue Base = AMDGPUTargetLowering::performAndCombine(N, DCI))
|
|
|
|
return Base;
|
|
|
|
|
2015-01-07 07:00:46 +08:00
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
|
|
|
|
// (and (fcmp ord x, x), (fcmp une (fabs x), inf)) ->
|
|
|
|
// fp_class x, ~(s_nan | q_nan | n_infinity | p_infinity)
|
|
|
|
SDValue LHS = N->getOperand(0);
|
|
|
|
SDValue RHS = N->getOperand(1);
|
|
|
|
|
|
|
|
if (LHS.getOpcode() == ISD::SETCC &&
|
|
|
|
RHS.getOpcode() == ISD::SETCC) {
|
|
|
|
ISD::CondCode LCC = cast<CondCodeSDNode>(LHS.getOperand(2))->get();
|
|
|
|
ISD::CondCode RCC = cast<CondCodeSDNode>(RHS.getOperand(2))->get();
|
|
|
|
|
|
|
|
SDValue X = LHS.getOperand(0);
|
|
|
|
SDValue Y = RHS.getOperand(0);
|
|
|
|
if (Y.getOpcode() != ISD::FABS || Y.getOperand(0) != X)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
if (LCC == ISD::SETO) {
|
|
|
|
if (X != LHS.getOperand(1))
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
if (RCC == ISD::SETUNE) {
|
|
|
|
const ConstantFPSDNode *C1 = dyn_cast<ConstantFPSDNode>(RHS.getOperand(1));
|
|
|
|
if (!C1 || !C1->isInfinity() || C1->isNegative())
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
const uint32_t Mask = SIInstrFlags::N_NORMAL |
|
|
|
|
SIInstrFlags::N_SUBNORMAL |
|
|
|
|
SIInstrFlags::N_ZERO |
|
|
|
|
SIInstrFlags::P_ZERO |
|
|
|
|
SIInstrFlags::P_SUBNORMAL |
|
|
|
|
SIInstrFlags::P_NORMAL;
|
|
|
|
|
|
|
|
static_assert(((~(SIInstrFlags::S_NAN |
|
|
|
|
SIInstrFlags::Q_NAN |
|
|
|
|
SIInstrFlags::N_INFINITY |
|
|
|
|
SIInstrFlags::P_INFINITY)) & 0x3ff) == Mask,
|
|
|
|
"mask not equal");
|
|
|
|
|
2015-04-28 22:05:47 +08:00
|
|
|
SDLoc DL(N);
|
|
|
|
return DAG.getNode(AMDGPUISD::FP_CLASS, DL, MVT::i1,
|
|
|
|
X, DAG.getConstant(Mask, DL, MVT::i32));
|
2015-01-07 07:00:46 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2015-01-07 07:00:39 +08:00
|
|
|
SDValue SITargetLowering::performOrCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
SDValue LHS = N->getOperand(0);
|
|
|
|
SDValue RHS = N->getOperand(1);
|
|
|
|
|
2016-04-13 02:24:38 +08:00
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
if (VT == MVT::i64) {
|
|
|
|
// TODO: This could be a generic combine with a predicate for extracting the
|
|
|
|
// high half of an integer being free.
|
|
|
|
|
|
|
|
// (or i64:x, (zero_extend i32:y)) ->
|
|
|
|
// i64 (bitcast (v2i32 build_vector (or i32:y, lo_32(x)), hi_32(x)))
|
|
|
|
if (LHS.getOpcode() == ISD::ZERO_EXTEND &&
|
|
|
|
RHS.getOpcode() != ISD::ZERO_EXTEND)
|
|
|
|
std::swap(LHS, RHS);
|
|
|
|
|
|
|
|
if (RHS.getOpcode() == ISD::ZERO_EXTEND) {
|
|
|
|
SDValue ExtSrc = RHS.getOperand(0);
|
|
|
|
EVT SrcVT = ExtSrc.getValueType();
|
|
|
|
if (SrcVT == MVT::i32) {
|
|
|
|
SDLoc SL(N);
|
|
|
|
SDValue LowLHS, HiBits;
|
|
|
|
std::tie(LowLHS, HiBits) = split64BitValue(LHS, DAG);
|
|
|
|
SDValue LowOr = DAG.getNode(ISD::OR, SL, MVT::i32, LowLHS, ExtSrc);
|
|
|
|
|
|
|
|
DCI.AddToWorklist(LowOr.getNode());
|
|
|
|
DCI.AddToWorklist(HiBits.getNode());
|
|
|
|
|
|
|
|
SDValue Vec = DAG.getNode(ISD::BUILD_VECTOR, SL, MVT::v2i32,
|
|
|
|
LowOr, HiBits);
|
|
|
|
return DAG.getNode(ISD::BITCAST, SL, MVT::i64, Vec);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-01-07 07:00:39 +08:00
|
|
|
// or (fp_class x, c1), (fp_class x, c2) -> fp_class x, (c1 | c2)
|
|
|
|
if (LHS.getOpcode() == AMDGPUISD::FP_CLASS &&
|
|
|
|
RHS.getOpcode() == AMDGPUISD::FP_CLASS) {
|
|
|
|
SDValue Src = LHS.getOperand(0);
|
|
|
|
if (Src != RHS.getOperand(0))
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
const ConstantSDNode *CLHS = dyn_cast<ConstantSDNode>(LHS.getOperand(1));
|
|
|
|
const ConstantSDNode *CRHS = dyn_cast<ConstantSDNode>(RHS.getOperand(1));
|
|
|
|
if (!CLHS || !CRHS)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
// Only 10 bits are used.
|
|
|
|
static const uint32_t MaxMask = 0x3ff;
|
|
|
|
|
|
|
|
uint32_t NewMask = (CLHS->getZExtValue() | CRHS->getZExtValue()) & MaxMask;
|
2015-04-28 22:05:47 +08:00
|
|
|
SDLoc DL(N);
|
|
|
|
return DAG.getNode(AMDGPUISD::FP_CLASS, DL, MVT::i1,
|
|
|
|
Src, DAG.getConstant(NewMask, DL, MVT::i32));
|
2015-01-07 07:00:39 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::performClassCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
SDValue Mask = N->getOperand(1);
|
|
|
|
|
|
|
|
// fp_class x, 0 -> false
|
|
|
|
if (const ConstantSDNode *CMask = dyn_cast<ConstantSDNode>(Mask)) {
|
|
|
|
if (CMask->isNullValue())
|
2015-04-28 22:05:47 +08:00
|
|
|
return DAG.getConstant(0, SDLoc(N), MVT::i1);
|
2015-01-07 07:00:39 +08:00
|
|
|
}
|
|
|
|
|
2016-06-21 02:33:56 +08:00
|
|
|
if (N->getOperand(0).isUndef())
|
|
|
|
return DAG.getUNDEF(MVT::i1);
|
|
|
|
|
2015-01-07 07:00:39 +08:00
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2016-04-14 09:42:16 +08:00
|
|
|
// Constant fold canonicalize.
|
|
|
|
SDValue SITargetLowering::performFCanonicalizeCombine(
|
|
|
|
SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
ConstantFPSDNode *CFP = dyn_cast<ConstantFPSDNode>(N->getOperand(0));
|
|
|
|
if (!CFP)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
const APFloat &C = CFP->getValueAPF();
|
|
|
|
|
|
|
|
// Flush denormals to 0 if not enabled.
|
|
|
|
if (C.isDenormal()) {
|
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
if (VT == MVT::f32 && !Subtarget->hasFP32Denormals())
|
|
|
|
return DAG.getConstantFP(0.0, SDLoc(N), VT);
|
|
|
|
|
|
|
|
if (VT == MVT::f64 && !Subtarget->hasFP64Denormals())
|
|
|
|
return DAG.getConstantFP(0.0, SDLoc(N), VT);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (C.isNaN()) {
|
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
APFloat CanonicalQNaN = APFloat::getQNaN(C.getSemantics());
|
|
|
|
if (C.isSignaling()) {
|
|
|
|
// Quiet a signaling NaN.
|
|
|
|
return DAG.getConstantFP(CanonicalQNaN, SDLoc(N), VT);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Make sure it is the canonical NaN bitpattern.
|
|
|
|
//
|
|
|
|
// TODO: Can we use -1 as the canonical NaN value since it's an inline
|
|
|
|
// immediate?
|
|
|
|
if (C.bitcastToAPInt() != CanonicalQNaN.bitcastToAPInt())
|
|
|
|
return DAG.getConstantFP(CanonicalQNaN, SDLoc(N), VT);
|
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue(CFP, 0);
|
|
|
|
}
|
|
|
|
|
2014-11-15 04:08:52 +08:00
|
|
|
static unsigned minMaxOpcToMin3Max3Opc(unsigned Opc) {
|
|
|
|
switch (Opc) {
|
|
|
|
case ISD::FMAXNUM:
|
|
|
|
return AMDGPUISD::FMAX3;
|
2015-06-09 08:52:37 +08:00
|
|
|
case ISD::SMAX:
|
2014-11-15 04:08:52 +08:00
|
|
|
return AMDGPUISD::SMAX3;
|
2015-06-09 08:52:37 +08:00
|
|
|
case ISD::UMAX:
|
2014-11-15 04:08:52 +08:00
|
|
|
return AMDGPUISD::UMAX3;
|
|
|
|
case ISD::FMINNUM:
|
|
|
|
return AMDGPUISD::FMIN3;
|
2015-06-09 08:52:37 +08:00
|
|
|
case ISD::SMIN:
|
2014-11-15 04:08:52 +08:00
|
|
|
return AMDGPUISD::SMIN3;
|
2015-06-09 08:52:37 +08:00
|
|
|
case ISD::UMIN:
|
2014-11-15 04:08:52 +08:00
|
|
|
return AMDGPUISD::UMIN3;
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Not a min/max opcode");
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-12 23:39:02 +08:00
|
|
|
static SDValue performIntMed3ImmCombine(SelectionDAG &DAG, const SDLoc &SL,
|
|
|
|
SDValue Op0, SDValue Op1, bool Signed) {
|
2016-01-29 04:53:42 +08:00
|
|
|
ConstantSDNode *K1 = dyn_cast<ConstantSDNode>(Op1);
|
|
|
|
if (!K1)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
ConstantSDNode *K0 = dyn_cast<ConstantSDNode>(Op0.getOperand(1));
|
|
|
|
if (!K0)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
if (Signed) {
|
|
|
|
if (K0->getAPIntValue().sge(K1->getAPIntValue()))
|
|
|
|
return SDValue();
|
|
|
|
} else {
|
|
|
|
if (K0->getAPIntValue().uge(K1->getAPIntValue()))
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
|
|
|
EVT VT = K0->getValueType(0);
|
|
|
|
return DAG.getNode(Signed ? AMDGPUISD::SMED3 : AMDGPUISD::UMED3, SL, VT,
|
|
|
|
Op0.getOperand(0), SDValue(K0, 0), SDValue(K1, 0));
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool isKnownNeverSNan(SelectionDAG &DAG, SDValue Op) {
|
|
|
|
if (!DAG.getTargetLoweringInfo().hasFloatingPointExceptions())
|
|
|
|
return true;
|
|
|
|
|
|
|
|
return DAG.isKnownNeverNaN(Op);
|
|
|
|
}
|
|
|
|
|
2016-06-12 23:39:02 +08:00
|
|
|
static SDValue performFPMed3ImmCombine(SelectionDAG &DAG, const SDLoc &SL,
|
|
|
|
SDValue Op0, SDValue Op1) {
|
2016-01-29 04:53:42 +08:00
|
|
|
ConstantFPSDNode *K1 = dyn_cast<ConstantFPSDNode>(Op1);
|
|
|
|
if (!K1)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
ConstantFPSDNode *K0 = dyn_cast<ConstantFPSDNode>(Op0.getOperand(1));
|
|
|
|
if (!K0)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
// Ordered >= (although NaN inputs should have folded away by now).
|
|
|
|
APFloat::cmpResult Cmp = K0->getValueAPF().compare(K1->getValueAPF());
|
|
|
|
if (Cmp == APFloat::cmpGreaterThan)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
// This isn't safe with signaling NaNs because in IEEE mode, min/max on a
|
|
|
|
// signaling NaN gives a quiet NaN. The quiet NaN input to the min would then
|
|
|
|
// give the other result, which is different from med3 with a NaN input.
|
|
|
|
SDValue Var = Op0.getOperand(0);
|
|
|
|
if (!isKnownNeverSNan(DAG, Var))
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
return DAG.getNode(AMDGPUISD::FMED3, SL, K0->getValueType(0),
|
|
|
|
Var, SDValue(K0, 0), SDValue(K1, 0));
|
|
|
|
}
|
|
|
|
|
|
|
|
SDValue SITargetLowering::performMinMaxCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
2014-11-15 04:08:52 +08:00
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
|
|
|
|
unsigned Opc = N->getOpcode();
|
|
|
|
SDValue Op0 = N->getOperand(0);
|
|
|
|
SDValue Op1 = N->getOperand(1);
|
|
|
|
|
|
|
|
// Only do this if the inner op has one use since this will just increases
|
|
|
|
// register pressure for no benefit.
|
|
|
|
|
2016-01-29 04:53:48 +08:00
|
|
|
if (Opc != AMDGPUISD::FMIN_LEGACY && Opc != AMDGPUISD::FMAX_LEGACY) {
|
|
|
|
// max(max(a, b), c) -> max3(a, b, c)
|
|
|
|
// min(min(a, b), c) -> min3(a, b, c)
|
|
|
|
if (Op0.getOpcode() == Opc && Op0.hasOneUse()) {
|
|
|
|
SDLoc DL(N);
|
|
|
|
return DAG.getNode(minMaxOpcToMin3Max3Opc(Opc),
|
|
|
|
DL,
|
|
|
|
N->getValueType(0),
|
|
|
|
Op0.getOperand(0),
|
|
|
|
Op0.getOperand(1),
|
|
|
|
Op1);
|
|
|
|
}
|
|
|
|
|
|
|
|
// Try commuted.
|
|
|
|
// max(a, max(b, c)) -> max3(a, b, c)
|
|
|
|
// min(a, min(b, c)) -> min3(a, b, c)
|
|
|
|
if (Op1.getOpcode() == Opc && Op1.hasOneUse()) {
|
|
|
|
SDLoc DL(N);
|
|
|
|
return DAG.getNode(minMaxOpcToMin3Max3Opc(Opc),
|
|
|
|
DL,
|
|
|
|
N->getValueType(0),
|
|
|
|
Op0,
|
|
|
|
Op1.getOperand(0),
|
|
|
|
Op1.getOperand(1));
|
|
|
|
}
|
2014-11-15 04:08:52 +08:00
|
|
|
}
|
|
|
|
|
2016-01-29 04:53:42 +08:00
|
|
|
// min(max(x, K0), K1), K0 < K1 -> med3(x, K0, K1)
|
|
|
|
if (Opc == ISD::SMIN && Op0.getOpcode() == ISD::SMAX && Op0.hasOneUse()) {
|
|
|
|
if (SDValue Med3 = performIntMed3ImmCombine(DAG, SDLoc(N), Op0, Op1, true))
|
|
|
|
return Med3;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Opc == ISD::UMIN && Op0.getOpcode() == ISD::UMAX && Op0.hasOneUse()) {
|
|
|
|
if (SDValue Med3 = performIntMed3ImmCombine(DAG, SDLoc(N), Op0, Op1, false))
|
|
|
|
return Med3;
|
|
|
|
}
|
|
|
|
|
|
|
|
// fminnum(fmaxnum(x, K0), K1), K0 < K1 && !is_snan(x) -> fmed3(x, K0, K1)
|
2016-01-29 04:53:48 +08:00
|
|
|
if (((Opc == ISD::FMINNUM && Op0.getOpcode() == ISD::FMAXNUM) ||
|
|
|
|
(Opc == AMDGPUISD::FMIN_LEGACY &&
|
|
|
|
Op0.getOpcode() == AMDGPUISD::FMAX_LEGACY)) &&
|
2016-01-29 04:53:42 +08:00
|
|
|
N->getValueType(0) == MVT::f32 && Op0.hasOneUse()) {
|
|
|
|
if (SDValue Res = performFPMed3ImmCombine(DAG, SDLoc(N), Op0, Op1))
|
|
|
|
return Res;
|
|
|
|
}
|
|
|
|
|
2014-11-15 04:08:52 +08:00
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2015-01-07 07:00:41 +08:00
|
|
|
SDValue SITargetLowering::performSetCCCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
|
|
|
SDLoc SL(N);
|
|
|
|
|
|
|
|
SDValue LHS = N->getOperand(0);
|
|
|
|
SDValue RHS = N->getOperand(1);
|
|
|
|
EVT VT = LHS.getValueType();
|
|
|
|
|
|
|
|
if (VT != MVT::f32 && VT != MVT::f64)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
// Match isinf pattern
|
|
|
|
// (fcmp oeq (fabs x), inf) -> (fp_class x, (p_infinity | n_infinity))
|
|
|
|
ISD::CondCode CC = cast<CondCodeSDNode>(N->getOperand(2))->get();
|
|
|
|
if (CC == ISD::SETOEQ && LHS.getOpcode() == ISD::FABS) {
|
|
|
|
const ConstantFPSDNode *CRHS = dyn_cast<ConstantFPSDNode>(RHS);
|
|
|
|
if (!CRHS)
|
|
|
|
return SDValue();
|
|
|
|
|
|
|
|
const APFloat &APF = CRHS->getValueAPF();
|
|
|
|
if (APF.isInfinity() && !APF.isNegative()) {
|
|
|
|
unsigned Mask = SIInstrFlags::P_INFINITY | SIInstrFlags::N_INFINITY;
|
2015-04-28 22:05:47 +08:00
|
|
|
return DAG.getNode(AMDGPUISD::FP_CLASS, SL, MVT::i1, LHS.getOperand(0),
|
|
|
|
DAG.getConstant(Mask, SL, MVT::i32));
|
2015-01-07 07:00:41 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return SDValue();
|
|
|
|
}
|
|
|
|
|
2012-12-12 05:25:42 +08:00
|
|
|
SDValue SITargetLowering::PerformDAGCombine(SDNode *N,
|
|
|
|
DAGCombinerInfo &DCI) const {
|
|
|
|
SelectionDAG &DAG = DCI.DAG;
|
2013-05-25 10:42:55 +08:00
|
|
|
SDLoc DL(N);
|
2012-12-12 05:25:42 +08:00
|
|
|
|
|
|
|
switch (N->getOpcode()) {
|
2014-12-22 00:48:42 +08:00
|
|
|
default:
|
|
|
|
return AMDGPUTargetLowering::PerformDAGCombine(N, DCI);
|
2015-01-07 07:00:41 +08:00
|
|
|
case ISD::SETCC:
|
|
|
|
return performSetCCCombine(N, DCI);
|
2016-01-29 04:53:48 +08:00
|
|
|
case ISD::FMAXNUM:
|
2014-11-15 04:08:52 +08:00
|
|
|
case ISD::FMINNUM:
|
2015-06-09 08:52:37 +08:00
|
|
|
case ISD::SMAX:
|
|
|
|
case ISD::SMIN:
|
|
|
|
case ISD::UMAX:
|
2016-01-29 04:53:48 +08:00
|
|
|
case ISD::UMIN:
|
|
|
|
case AMDGPUISD::FMIN_LEGACY:
|
|
|
|
case AMDGPUISD::FMAX_LEGACY: {
|
2014-11-15 04:08:52 +08:00
|
|
|
if (DCI.getDAGCombineLevel() >= AfterLegalizeDAG &&
|
2015-03-16 23:53:55 +08:00
|
|
|
N->getValueType(0) != MVT::f64 &&
|
2014-11-15 04:08:52 +08:00
|
|
|
getTargetMachine().getOptLevel() > CodeGenOpt::None)
|
2016-01-29 04:53:42 +08:00
|
|
|
return performMinMaxCombine(N, DCI);
|
2014-11-15 04:08:52 +08:00
|
|
|
break;
|
|
|
|
}
|
2014-06-12 01:50:44 +08:00
|
|
|
|
|
|
|
case AMDGPUISD::CVT_F32_UBYTE0:
|
|
|
|
case AMDGPUISD::CVT_F32_UBYTE1:
|
|
|
|
case AMDGPUISD::CVT_F32_UBYTE2:
|
|
|
|
case AMDGPUISD::CVT_F32_UBYTE3: {
|
|
|
|
unsigned Offset = N->getOpcode() - AMDGPUISD::CVT_F32_UBYTE0;
|
|
|
|
SDValue Src = N->getOperand(0);
|
2016-05-10 00:29:50 +08:00
|
|
|
|
2016-07-02 06:47:50 +08:00
|
|
|
// TODO: Handle (or x, (srl y, 8)) pattern when known bits are zero.
|
2016-05-10 00:29:50 +08:00
|
|
|
if (Src.getOpcode() == ISD::SRL) {
|
|
|
|
// cvt_f32_ubyte0 (srl x, 16) -> cvt_f32_ubyte2 x
|
|
|
|
// cvt_f32_ubyte1 (srl x, 16) -> cvt_f32_ubyte3 x
|
|
|
|
// cvt_f32_ubyte0 (srl x, 8) -> cvt_f32_ubyte1 x
|
|
|
|
|
|
|
|
if (const ConstantSDNode *C = dyn_cast<ConstantSDNode>(Src.getOperand(1))) {
|
|
|
|
unsigned SrcOffset = C->getZExtValue() + 8 * Offset;
|
|
|
|
if (SrcOffset < 32 && SrcOffset % 8 == 0) {
|
|
|
|
return DAG.getNode(AMDGPUISD::CVT_F32_UBYTE0 + SrcOffset / 8, DL,
|
|
|
|
MVT::f32, Src.getOperand(0));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-06-12 01:50:44 +08:00
|
|
|
APInt Demanded = APInt::getBitsSet(32, 8 * Offset, 8 * Offset + 8);
|
|
|
|
|
|
|
|
APInt KnownZero, KnownOne;
|
|
|
|
TargetLowering::TargetLoweringOpt TLO(DAG, !DCI.isBeforeLegalize(),
|
|
|
|
!DCI.isBeforeLegalizeOps());
|
|
|
|
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
|
|
|
|
if (TLO.ShrinkDemandedConstant(Src, Demanded) ||
|
|
|
|
TLI.SimplifyDemandedBits(Src, Demanded, KnownZero, KnownOne, TLO)) {
|
|
|
|
DCI.CommitTargetLoweringOpt(TLO);
|
|
|
|
}
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
case ISD::UINT_TO_FP: {
|
|
|
|
return performUCharToFloatCombine(N, DCI);
|
2016-01-12 01:02:00 +08:00
|
|
|
}
|
2014-09-29 22:59:34 +08:00
|
|
|
case ISD::FADD: {
|
|
|
|
if (DCI.getDAGCombineLevel() < AfterLegalizeDAG)
|
|
|
|
break;
|
|
|
|
|
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
if (VT != MVT::f32)
|
|
|
|
break;
|
|
|
|
|
2015-02-21 06:10:41 +08:00
|
|
|
// Only do this if we are not trying to support denormals. v_mad_f32 does
|
|
|
|
// not support denormals ever.
|
|
|
|
if (Subtarget->hasFP32Denormals())
|
|
|
|
break;
|
|
|
|
|
2014-09-29 22:59:34 +08:00
|
|
|
SDValue LHS = N->getOperand(0);
|
|
|
|
SDValue RHS = N->getOperand(1);
|
|
|
|
|
|
|
|
// These should really be instruction patterns, but writing patterns with
|
|
|
|
// source modiifiers is a pain.
|
|
|
|
|
|
|
|
// fadd (fadd (a, a), b) -> mad 2.0, a, b
|
|
|
|
if (LHS.getOpcode() == ISD::FADD) {
|
|
|
|
SDValue A = LHS.getOperand(0);
|
|
|
|
if (A == LHS.getOperand(1)) {
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue Two = DAG.getConstantFP(2.0, DL, MVT::f32);
|
2015-02-21 06:10:41 +08:00
|
|
|
return DAG.getNode(ISD::FMAD, DL, VT, Two, A, RHS);
|
2014-09-29 22:59:34 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// fadd (b, fadd (a, a)) -> mad 2.0, a, b
|
|
|
|
if (RHS.getOpcode() == ISD::FADD) {
|
|
|
|
SDValue A = RHS.getOperand(0);
|
|
|
|
if (A == RHS.getOperand(1)) {
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue Two = DAG.getConstantFP(2.0, DL, MVT::f32);
|
2015-02-21 06:10:41 +08:00
|
|
|
return DAG.getNode(ISD::FMAD, DL, VT, Two, A, LHS);
|
2014-09-29 22:59:34 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-02-21 06:10:41 +08:00
|
|
|
return SDValue();
|
2014-09-29 22:59:34 +08:00
|
|
|
}
|
2014-08-30 00:01:14 +08:00
|
|
|
case ISD::FSUB: {
|
|
|
|
if (DCI.getDAGCombineLevel() < AfterLegalizeDAG)
|
|
|
|
break;
|
|
|
|
|
|
|
|
EVT VT = N->getValueType(0);
|
|
|
|
|
|
|
|
// Try to get the fneg to fold into the source modifier. This undoes generic
|
|
|
|
// DAG combines and folds them into the mad.
|
2015-02-21 06:10:41 +08:00
|
|
|
//
|
|
|
|
// Only do this if we are not trying to support denormals. v_mad_f32 does
|
|
|
|
// not support denormals ever.
|
|
|
|
if (VT == MVT::f32 &&
|
|
|
|
!Subtarget->hasFP32Denormals()) {
|
2014-08-30 00:01:14 +08:00
|
|
|
SDValue LHS = N->getOperand(0);
|
|
|
|
SDValue RHS = N->getOperand(1);
|
2014-09-29 22:59:38 +08:00
|
|
|
if (LHS.getOpcode() == ISD::FADD) {
|
|
|
|
// (fsub (fadd a, a), c) -> mad 2.0, a, (fneg c)
|
|
|
|
|
|
|
|
SDValue A = LHS.getOperand(0);
|
|
|
|
if (A == LHS.getOperand(1)) {
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue Two = DAG.getConstantFP(2.0, DL, MVT::f32);
|
2014-09-29 22:59:38 +08:00
|
|
|
SDValue NegRHS = DAG.getNode(ISD::FNEG, DL, VT, RHS);
|
|
|
|
|
2015-02-21 06:10:41 +08:00
|
|
|
return DAG.getNode(ISD::FMAD, DL, VT, Two, A, NegRHS);
|
2014-09-29 22:59:38 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (RHS.getOpcode() == ISD::FADD) {
|
|
|
|
// (fsub c, (fadd a, a)) -> mad -2.0, a, c
|
|
|
|
|
|
|
|
SDValue A = RHS.getOperand(0);
|
|
|
|
if (A == RHS.getOperand(1)) {
|
2015-04-28 22:05:47 +08:00
|
|
|
const SDValue NegTwo = DAG.getConstantFP(-2.0, DL, MVT::f32);
|
2015-02-21 06:10:41 +08:00
|
|
|
return DAG.getNode(ISD::FMAD, DL, VT, NegTwo, A, LHS);
|
2014-09-29 22:59:38 +08:00
|
|
|
}
|
|
|
|
}
|
2015-02-21 06:10:41 +08:00
|
|
|
|
|
|
|
return SDValue();
|
2014-08-30 00:01:14 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
break;
|
|
|
|
}
|
2014-08-16 01:49:05 +08:00
|
|
|
case ISD::LOAD:
|
|
|
|
case ISD::STORE:
|
|
|
|
case ISD::ATOMIC_LOAD:
|
|
|
|
case ISD::ATOMIC_STORE:
|
|
|
|
case ISD::ATOMIC_CMP_SWAP:
|
|
|
|
case ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS:
|
|
|
|
case ISD::ATOMIC_SWAP:
|
|
|
|
case ISD::ATOMIC_LOAD_ADD:
|
|
|
|
case ISD::ATOMIC_LOAD_SUB:
|
|
|
|
case ISD::ATOMIC_LOAD_AND:
|
|
|
|
case ISD::ATOMIC_LOAD_OR:
|
|
|
|
case ISD::ATOMIC_LOAD_XOR:
|
|
|
|
case ISD::ATOMIC_LOAD_NAND:
|
|
|
|
case ISD::ATOMIC_LOAD_MIN:
|
|
|
|
case ISD::ATOMIC_LOAD_MAX:
|
|
|
|
case ISD::ATOMIC_LOAD_UMIN:
|
2016-04-12 22:05:04 +08:00
|
|
|
case ISD::ATOMIC_LOAD_UMAX:
|
|
|
|
case AMDGPUISD::ATOMIC_INC:
|
|
|
|
case AMDGPUISD::ATOMIC_DEC: { // TODO: Target mem intrinsics.
|
2014-08-16 01:49:05 +08:00
|
|
|
if (DCI.isBeforeLegalize())
|
|
|
|
break;
|
|
|
|
|
|
|
|
MemSDNode *MemNode = cast<MemSDNode>(N);
|
|
|
|
SDValue Ptr = MemNode->getBasePtr();
|
2014-05-23 02:09:07 +08:00
|
|
|
|
2014-08-16 01:49:05 +08:00
|
|
|
// TODO: We could also do this for multiplies.
|
|
|
|
unsigned AS = MemNode->getAddressSpace();
|
|
|
|
if (Ptr.getOpcode() == ISD::SHL && AS != AMDGPUAS::PRIVATE_ADDRESS) {
|
|
|
|
SDValue NewPtr = performSHLPtrCombine(Ptr.getNode(), AS, DCI);
|
|
|
|
if (NewPtr) {
|
2015-02-17 23:29:18 +08:00
|
|
|
SmallVector<SDValue, 8> NewOps(MemNode->op_begin(), MemNode->op_end());
|
2014-08-16 01:49:05 +08:00
|
|
|
|
|
|
|
NewOps[N->getOpcode() == ISD::STORE ? 2 : 1] = NewPtr;
|
|
|
|
return SDValue(DAG.UpdateNodeOperands(MemNode, NewOps), 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
2015-01-07 07:00:46 +08:00
|
|
|
case ISD::AND:
|
|
|
|
return performAndCombine(N, DCI);
|
2015-01-07 07:00:39 +08:00
|
|
|
case ISD::OR:
|
|
|
|
return performOrCombine(N, DCI);
|
|
|
|
case AMDGPUISD::FP_CLASS:
|
|
|
|
return performClassCombine(N, DCI);
|
2016-04-14 09:42:16 +08:00
|
|
|
case ISD::FCANONICALIZE:
|
|
|
|
return performFCanonicalizeCombine(N, DCI);
|
2016-06-21 02:33:56 +08:00
|
|
|
case AMDGPUISD::FRACT:
|
|
|
|
case AMDGPUISD::RCP:
|
|
|
|
case AMDGPUISD::RSQ:
|
|
|
|
case AMDGPUISD::RSQ_LEGACY:
|
|
|
|
case AMDGPUISD::RSQ_CLAMP:
|
|
|
|
case AMDGPUISD::LDEXP: {
|
|
|
|
SDValue Src = N->getOperand(0);
|
|
|
|
if (Src.isUndef())
|
|
|
|
return Src;
|
|
|
|
break;
|
|
|
|
}
|
2014-08-16 01:49:05 +08:00
|
|
|
}
|
2014-05-23 02:09:07 +08:00
|
|
|
return AMDGPUTargetLowering::PerformDAGCombine(N, DCI);
|
2012-12-12 05:25:42 +08:00
|
|
|
}
|
2013-02-27 01:52:16 +08:00
|
|
|
|
2013-02-27 01:52:23 +08:00
|
|
|
/// \brief Analyze the possible immediate value Op
|
|
|
|
///
|
|
|
|
/// Returns -1 if it isn't an immediate, 0 if it's and inline immediate
|
|
|
|
/// and the immediate value if it's a literal immediate
|
|
|
|
int32_t SITargetLowering::analyzeImmediate(const SDNode *N) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2013-02-27 01:52:23 +08:00
|
|
|
|
2013-04-06 07:31:20 +08:00
|
|
|
if (const ConstantSDNode *Node = dyn_cast<ConstantSDNode>(N)) {
|
2014-12-18 05:04:08 +08:00
|
|
|
if (TII->isInlineConstant(Node->getAPIntValue()))
|
|
|
|
return 0;
|
|
|
|
|
2015-02-14 03:05:03 +08:00
|
|
|
uint64_t Val = Node->getZExtValue();
|
|
|
|
return isUInt<32>(Val) ? Val : -1;
|
2014-12-18 05:04:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (const ConstantFPSDNode *Node = dyn_cast<ConstantFPSDNode>(N)) {
|
|
|
|
if (TII->isInlineConstant(Node->getValueAPF().bitcastToAPInt()))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (Node->getValueType(0) == MVT::f32)
|
|
|
|
return FloatToBits(Node->getValueAPF().convertToFloat());
|
|
|
|
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -1;
|
2013-02-27 01:52:23 +08:00
|
|
|
}
|
|
|
|
|
2013-04-10 16:39:08 +08:00
|
|
|
/// \brief Helper function for adjustWritemask
|
2013-05-23 23:43:05 +08:00
|
|
|
static unsigned SubIdx2Lane(unsigned Idx) {
|
2013-04-10 16:39:08 +08:00
|
|
|
switch (Idx) {
|
|
|
|
default: return 0;
|
|
|
|
case AMDGPU::sub0: return 0;
|
|
|
|
case AMDGPU::sub1: return 1;
|
|
|
|
case AMDGPU::sub2: return 2;
|
|
|
|
case AMDGPU::sub3: return 3;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// \brief Adjust the writemask of MIMG instructions
|
|
|
|
void SITargetLowering::adjustWritemask(MachineSDNode *&Node,
|
|
|
|
SelectionDAG &DAG) const {
|
|
|
|
SDNode *Users[4] = { };
|
2013-10-23 10:53:47 +08:00
|
|
|
unsigned Lane = 0;
|
2016-02-26 17:51:05 +08:00
|
|
|
unsigned DmaskIdx = (Node->getNumOperands() - Node->getNumValues() == 9) ? 2 : 3;
|
|
|
|
unsigned OldDmask = Node->getConstantOperandVal(DmaskIdx);
|
2013-10-23 10:53:47 +08:00
|
|
|
unsigned NewDmask = 0;
|
2013-04-10 16:39:08 +08:00
|
|
|
|
|
|
|
// Try to figure out the used register components
|
|
|
|
for (SDNode::use_iterator I = Node->use_begin(), E = Node->use_end();
|
|
|
|
I != E; ++I) {
|
|
|
|
|
|
|
|
// Abort if we can't understand the usage
|
|
|
|
if (!I->isMachineOpcode() ||
|
|
|
|
I->getMachineOpcode() != TargetOpcode::EXTRACT_SUBREG)
|
|
|
|
return;
|
|
|
|
|
2013-10-23 10:53:47 +08:00
|
|
|
// Lane means which subreg of %VGPRa_VGPRb_VGPRc_VGPRd is used.
|
|
|
|
// Note that subregs are packed, i.e. Lane==0 is the first bit set
|
|
|
|
// in OldDmask, so it can be any of X,Y,Z,W; Lane==1 is the second bit
|
|
|
|
// set, etc.
|
2013-04-10 16:39:16 +08:00
|
|
|
Lane = SubIdx2Lane(I->getConstantOperandVal(1));
|
2013-04-10 16:39:08 +08:00
|
|
|
|
2013-10-23 10:53:47 +08:00
|
|
|
// Set which texture component corresponds to the lane.
|
|
|
|
unsigned Comp;
|
|
|
|
for (unsigned i = 0, Dmask = OldDmask; i <= Lane; i++) {
|
|
|
|
assert(Dmask);
|
2013-10-23 11:50:25 +08:00
|
|
|
Comp = countTrailingZeros(Dmask);
|
2013-10-23 10:53:47 +08:00
|
|
|
Dmask &= ~(1 << Comp);
|
|
|
|
}
|
|
|
|
|
2013-04-10 16:39:08 +08:00
|
|
|
// Abort if we have more than one user per component
|
|
|
|
if (Users[Lane])
|
|
|
|
return;
|
|
|
|
|
|
|
|
Users[Lane] = *I;
|
2013-10-23 10:53:47 +08:00
|
|
|
NewDmask |= 1 << Comp;
|
2013-04-10 16:39:08 +08:00
|
|
|
}
|
|
|
|
|
2013-10-23 10:53:47 +08:00
|
|
|
// Abort if there's no change
|
|
|
|
if (NewDmask == OldDmask)
|
2013-04-10 16:39:08 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
// Adjust the writemask in the node
|
|
|
|
std::vector<SDValue> Ops;
|
2016-02-26 17:51:05 +08:00
|
|
|
Ops.insert(Ops.end(), Node->op_begin(), Node->op_begin() + DmaskIdx);
|
2015-04-28 22:05:47 +08:00
|
|
|
Ops.push_back(DAG.getTargetConstant(NewDmask, SDLoc(Node), MVT::i32));
|
2016-02-26 17:51:05 +08:00
|
|
|
Ops.insert(Ops.end(), Node->op_begin() + DmaskIdx + 1, Node->op_end());
|
2014-04-28 13:57:50 +08:00
|
|
|
Node = (MachineSDNode*)DAG.UpdateNodeOperands(Node, Ops);
|
2013-04-10 16:39:08 +08:00
|
|
|
|
2013-04-10 16:39:16 +08:00
|
|
|
// If we only got one lane, replace it with a copy
|
2013-10-23 10:53:47 +08:00
|
|
|
// (if NewDmask has only one bit set...)
|
|
|
|
if (NewDmask && (NewDmask & (NewDmask-1)) == 0) {
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue RC = DAG.getTargetConstant(AMDGPU::VGPR_32RegClassID, SDLoc(),
|
|
|
|
MVT::i32);
|
2013-04-10 16:39:16 +08:00
|
|
|
SDNode *Copy = DAG.getMachineNode(TargetOpcode::COPY_TO_REGCLASS,
|
2013-05-25 10:42:55 +08:00
|
|
|
SDLoc(), Users[Lane]->getValueType(0),
|
2013-04-10 16:39:16 +08:00
|
|
|
SDValue(Node, 0), RC);
|
|
|
|
DAG.ReplaceAllUsesWith(Users[Lane], Copy);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2013-04-10 16:39:08 +08:00
|
|
|
// Update the users of the node with the new indices
|
|
|
|
for (unsigned i = 0, Idx = AMDGPU::sub0; i < 4; ++i) {
|
|
|
|
|
|
|
|
SDNode *User = Users[i];
|
|
|
|
if (!User)
|
|
|
|
continue;
|
|
|
|
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue Op = DAG.getTargetConstant(Idx, SDLoc(User), MVT::i32);
|
2013-04-10 16:39:08 +08:00
|
|
|
DAG.UpdateNodeOperands(User, User->getOperand(0), Op);
|
|
|
|
|
|
|
|
switch (Idx) {
|
|
|
|
default: break;
|
|
|
|
case AMDGPU::sub0: Idx = AMDGPU::sub1; break;
|
|
|
|
case AMDGPU::sub1: Idx = AMDGPU::sub2; break;
|
|
|
|
case AMDGPU::sub2: Idx = AMDGPU::sub3; break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-07-17 03:40:07 +08:00
|
|
|
static bool isFrameIndexOp(SDValue Op) {
|
|
|
|
if (Op.getOpcode() == ISD::AssertZext)
|
|
|
|
Op = Op.getOperand(0);
|
|
|
|
|
|
|
|
return isa<FrameIndexSDNode>(Op);
|
|
|
|
}
|
|
|
|
|
2014-10-10 03:06:00 +08:00
|
|
|
/// \brief Legalize target independent instructions (e.g. INSERT_SUBREG)
|
|
|
|
/// with frame index operands.
|
|
|
|
/// LLVM assumes that inputs are to these instructions are registers.
|
|
|
|
void SITargetLowering::legalizeTargetIndependentNode(SDNode *Node,
|
|
|
|
SelectionDAG &DAG) const {
|
2014-10-10 02:09:15 +08:00
|
|
|
|
|
|
|
SmallVector<SDValue, 8> Ops;
|
2014-10-10 03:06:00 +08:00
|
|
|
for (unsigned i = 0; i < Node->getNumOperands(); ++i) {
|
2015-07-17 03:40:07 +08:00
|
|
|
if (!isFrameIndexOp(Node->getOperand(i))) {
|
2014-10-10 03:06:00 +08:00
|
|
|
Ops.push_back(Node->getOperand(i));
|
2014-10-10 02:09:15 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2014-10-10 03:06:00 +08:00
|
|
|
SDLoc DL(Node);
|
2014-10-10 02:09:15 +08:00
|
|
|
Ops.push_back(SDValue(DAG.getMachineNode(AMDGPU::S_MOV_B32, DL,
|
2014-10-10 03:06:00 +08:00
|
|
|
Node->getOperand(i).getValueType(),
|
|
|
|
Node->getOperand(i)), 0));
|
2014-10-10 02:09:15 +08:00
|
|
|
}
|
|
|
|
|
2014-10-10 03:06:00 +08:00
|
|
|
DAG.UpdateNodeOperands(Node, Ops);
|
2014-10-10 02:09:15 +08:00
|
|
|
}
|
|
|
|
|
2014-06-04 07:06:13 +08:00
|
|
|
/// \brief Fold the instructions after selecting them.
|
2013-04-10 16:39:08 +08:00
|
|
|
SDNode *SITargetLowering::PostISelFolding(MachineSDNode *Node,
|
|
|
|
SelectionDAG &DAG) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2016-02-19 00:44:18 +08:00
|
|
|
unsigned Opcode = Node->getMachineOpcode();
|
2013-04-10 16:39:08 +08:00
|
|
|
|
2016-02-19 00:44:18 +08:00
|
|
|
if (TII->isMIMG(Opcode) && !TII->get(Opcode).mayStore())
|
2013-04-10 16:39:08 +08:00
|
|
|
adjustWritemask(Node, DAG);
|
|
|
|
|
2016-02-19 00:44:18 +08:00
|
|
|
if (Opcode == AMDGPU::INSERT_SUBREG ||
|
|
|
|
Opcode == AMDGPU::REG_SEQUENCE) {
|
2014-10-10 02:09:15 +08:00
|
|
|
legalizeTargetIndependentNode(Node, DAG);
|
|
|
|
return Node;
|
|
|
|
}
|
2015-01-08 23:08:17 +08:00
|
|
|
return Node;
|
2013-04-10 16:39:08 +08:00
|
|
|
}
|
2013-04-10 16:39:16 +08:00
|
|
|
|
|
|
|
/// \brief Assign the register class depending on the number of
|
|
|
|
/// bits set in the writemask
|
2016-07-01 06:52:52 +08:00
|
|
|
void SITargetLowering::AdjustInstrPostInstrSelection(MachineInstr &MI,
|
2013-04-10 16:39:16 +08:00
|
|
|
SDNode *Node) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2013-04-10 16:39:16 +08:00
|
|
|
|
2016-07-01 06:52:52 +08:00
|
|
|
MachineRegisterInfo &MRI = MI.getParent()->getParent()->getRegInfo();
|
2015-10-22 05:51:02 +08:00
|
|
|
|
2016-07-01 06:52:52 +08:00
|
|
|
if (TII->isVOP3(MI.getOpcode())) {
|
2015-10-22 05:51:02 +08:00
|
|
|
// Make sure constant bus requirements are respected.
|
2016-07-01 06:52:52 +08:00
|
|
|
TII->legalizeOperandsVOP3(MRI, MI);
|
2015-10-22 05:51:02 +08:00
|
|
|
return;
|
|
|
|
}
|
2014-09-27 01:54:59 +08:00
|
|
|
|
2016-07-01 06:52:52 +08:00
|
|
|
if (TII->isMIMG(MI)) {
|
|
|
|
unsigned VReg = MI.getOperand(0).getReg();
|
|
|
|
unsigned DmaskIdx = MI.getNumOperands() == 12 ? 3 : 4;
|
|
|
|
unsigned Writemask = MI.getOperand(DmaskIdx).getImm();
|
2014-09-08 23:07:31 +08:00
|
|
|
unsigned BitsSet = 0;
|
|
|
|
for (unsigned i = 0; i < 4; ++i)
|
|
|
|
BitsSet += Writemask & (1 << i) ? 1 : 0;
|
|
|
|
|
|
|
|
const TargetRegisterClass *RC;
|
|
|
|
switch (BitsSet) {
|
|
|
|
default: return;
|
2015-01-08 04:59:25 +08:00
|
|
|
case 1: RC = &AMDGPU::VGPR_32RegClass; break;
|
2014-09-08 23:07:31 +08:00
|
|
|
case 2: RC = &AMDGPU::VReg_64RegClass; break;
|
|
|
|
case 3: RC = &AMDGPU::VReg_96RegClass; break;
|
|
|
|
}
|
|
|
|
|
2016-07-01 06:52:52 +08:00
|
|
|
unsigned NewOpcode = TII->getMaskedMIMGOp(MI.getOpcode(), BitsSet);
|
|
|
|
MI.setDesc(TII->get(NewOpcode));
|
2014-09-08 23:07:31 +08:00
|
|
|
MRI.setRegClass(VReg, RC);
|
|
|
|
return;
|
2013-04-10 16:39:16 +08:00
|
|
|
}
|
|
|
|
|
2014-09-08 23:07:31 +08:00
|
|
|
// Replace unused atomics with the no return version.
|
2016-07-01 06:52:52 +08:00
|
|
|
int NoRetAtomicOp = AMDGPU::getAtomicNoRetOp(MI.getOpcode());
|
2014-09-08 23:07:31 +08:00
|
|
|
if (NoRetAtomicOp != -1) {
|
|
|
|
if (!Node->hasAnyUseOfValue(0)) {
|
2016-07-01 06:52:52 +08:00
|
|
|
MI.setDesc(TII->get(NoRetAtomicOp));
|
|
|
|
MI.RemoveOperand(0);
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
return;
|
2014-09-08 23:07:31 +08:00
|
|
|
}
|
|
|
|
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
// For mubuf_atomic_cmpswap, we need to have tablegen use an extract_subreg
|
|
|
|
// instruction, because the return type of these instructions is a vec2 of
|
|
|
|
// the memory type, so it can be tied to the input operand.
|
|
|
|
// This means these instructions always have a use, so we need to add a
|
|
|
|
// special case to check if the atomic has only one extract_subreg use,
|
|
|
|
// which itself has no uses.
|
|
|
|
if ((Node->hasNUsesOfValue(1, 0) &&
|
2016-04-15 22:42:36 +08:00
|
|
|
Node->use_begin()->isMachineOpcode() &&
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
Node->use_begin()->getMachineOpcode() == AMDGPU::EXTRACT_SUBREG &&
|
|
|
|
!Node->use_begin()->hasAnyUseOfValue(0))) {
|
2016-07-01 06:52:52 +08:00
|
|
|
unsigned Def = MI.getOperand(0).getReg();
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
|
|
|
|
// Change this into a noret atomic.
|
2016-07-01 06:52:52 +08:00
|
|
|
MI.setDesc(TII->get(NoRetAtomicOp));
|
|
|
|
MI.RemoveOperand(0);
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
|
|
|
|
// If we only remove the def operand from the atomic instruction, the
|
|
|
|
// extract_subreg will be left with a use of a vreg without a def.
|
|
|
|
// So we need to insert an implicit_def to avoid machine verifier
|
|
|
|
// errors.
|
2016-07-01 06:52:52 +08:00
|
|
|
BuildMI(*MI.getParent(), MI, MI.getDebugLoc(),
|
AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}
Summary:
Implement BUFFER_ATOMIC_CMPSWAP{,_X2} instructions on all GCN targets, and FLAT_ATOMIC_CMPSWAP{,_X2} on CI+.
32-bit instruction variants tested manually on Kabini and Bonaire. Tests and parts of code provided by Jan Veselý.
Patch by: Vedran Miletić
Reviewers: arsenm, tstellarAMD, nhaehnle
Subscribers: jvesely, scchan, kanarayan, arsenm
Differential Revision: http://reviews.llvm.org/D17280
llvm-svn: 265170
2016-04-02 02:27:37 +08:00
|
|
|
TII->get(AMDGPU::IMPLICIT_DEF), Def);
|
|
|
|
}
|
2014-09-08 23:07:31 +08:00
|
|
|
return;
|
|
|
|
}
|
2013-04-10 16:39:16 +08:00
|
|
|
}
|
2013-06-04 01:39:58 +08:00
|
|
|
|
2016-06-12 23:39:02 +08:00
|
|
|
static SDValue buildSMovImm32(SelectionDAG &DAG, const SDLoc &DL,
|
|
|
|
uint64_t Val) {
|
2015-04-28 22:05:47 +08:00
|
|
|
SDValue K = DAG.getTargetConstant(Val, DL, MVT::i32);
|
2014-11-06 03:01:17 +08:00
|
|
|
return SDValue(DAG.getMachineNode(AMDGPU::S_MOV_B32, DL, MVT::i32, K), 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
MachineSDNode *SITargetLowering::wrapAddr64Rsrc(SelectionDAG &DAG,
|
2016-06-12 23:39:02 +08:00
|
|
|
const SDLoc &DL,
|
2014-11-06 03:01:17 +08:00
|
|
|
SDValue Ptr) const {
|
2016-06-24 14:30:11 +08:00
|
|
|
const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
|
2015-09-26 01:08:42 +08:00
|
|
|
|
|
|
|
// Build the half of the subregister with the constants before building the
|
|
|
|
// full 128-bit register. If we are building multiple resource descriptors,
|
|
|
|
// this will allow CSEing of the 2-component register.
|
|
|
|
const SDValue Ops0[] = {
|
|
|
|
DAG.getTargetConstant(AMDGPU::SGPR_64RegClassID, DL, MVT::i32),
|
|
|
|
buildSMovImm32(DAG, DL, 0),
|
|
|
|
DAG.getTargetConstant(AMDGPU::sub0, DL, MVT::i32),
|
|
|
|
buildSMovImm32(DAG, DL, TII->getDefaultRsrcDataFormat() >> 32),
|
|
|
|
DAG.getTargetConstant(AMDGPU::sub1, DL, MVT::i32)
|
|
|
|
};
|
|
|
|
|
|
|
|
SDValue SubRegHi = SDValue(DAG.getMachineNode(AMDGPU::REG_SEQUENCE, DL,
|
|
|
|
MVT::v2i32, Ops0), 0);
|
|
|
|
|
|
|
|
// Combine the constants and the pointer.
|
|
|
|
const SDValue Ops1[] = {
|
|
|
|
DAG.getTargetConstant(AMDGPU::SReg_128RegClassID, DL, MVT::i32),
|
|
|
|
Ptr,
|
|
|
|
DAG.getTargetConstant(AMDGPU::sub0_sub1, DL, MVT::i32),
|
|
|
|
SubRegHi,
|
|
|
|
DAG.getTargetConstant(AMDGPU::sub2_sub3, DL, MVT::i32)
|
|
|
|
};
|
|
|
|
|
|
|
|
return DAG.getMachineNode(AMDGPU::REG_SEQUENCE, DL, MVT::v4i32, Ops1);
|
2014-11-06 03:01:17 +08:00
|
|
|
}
|
|
|
|
|
2014-11-06 03:01:19 +08:00
|
|
|
/// \brief Return a resource descriptor with the 'Add TID' bit enabled
|
2015-08-09 02:27:36 +08:00
|
|
|
/// The TID (Thread ID) is multiplied by the stride value (bits [61:48]
|
|
|
|
/// of the resource descriptor) to create an offset, which is added to
|
|
|
|
/// the resource pointer.
|
2016-06-12 23:39:02 +08:00
|
|
|
MachineSDNode *SITargetLowering::buildRSRC(SelectionDAG &DAG, const SDLoc &DL,
|
|
|
|
SDValue Ptr, uint32_t RsrcDword1,
|
2014-11-06 03:01:19 +08:00
|
|
|
uint64_t RsrcDword2And3) const {
|
|
|
|
SDValue PtrLo = DAG.getTargetExtractSubreg(AMDGPU::sub0, DL, MVT::i32, Ptr);
|
|
|
|
SDValue PtrHi = DAG.getTargetExtractSubreg(AMDGPU::sub1, DL, MVT::i32, Ptr);
|
|
|
|
if (RsrcDword1) {
|
|
|
|
PtrHi = SDValue(DAG.getMachineNode(AMDGPU::S_OR_B32, DL, MVT::i32, PtrHi,
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getConstant(RsrcDword1, DL, MVT::i32)),
|
|
|
|
0);
|
2014-11-06 03:01:19 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
SDValue DataLo = buildSMovImm32(DAG, DL,
|
|
|
|
RsrcDword2And3 & UINT64_C(0xFFFFFFFF));
|
|
|
|
SDValue DataHi = buildSMovImm32(DAG, DL, RsrcDword2And3 >> 32);
|
|
|
|
|
|
|
|
const SDValue Ops[] = {
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getTargetConstant(AMDGPU::SReg_128RegClassID, DL, MVT::i32),
|
2014-11-06 03:01:19 +08:00
|
|
|
PtrLo,
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getTargetConstant(AMDGPU::sub0, DL, MVT::i32),
|
2014-11-06 03:01:19 +08:00
|
|
|
PtrHi,
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getTargetConstant(AMDGPU::sub1, DL, MVT::i32),
|
2014-11-06 03:01:19 +08:00
|
|
|
DataLo,
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getTargetConstant(AMDGPU::sub2, DL, MVT::i32),
|
2014-11-06 03:01:19 +08:00
|
|
|
DataHi,
|
2015-04-28 22:05:47 +08:00
|
|
|
DAG.getTargetConstant(AMDGPU::sub3, DL, MVT::i32)
|
2014-11-06 03:01:19 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
return DAG.getMachineNode(AMDGPU::REG_SEQUENCE, DL, MVT::v4i32, Ops);
|
|
|
|
}
|
|
|
|
|
2013-06-04 01:40:18 +08:00
|
|
|
SDValue SITargetLowering::CreateLiveInRegister(SelectionDAG &DAG,
|
|
|
|
const TargetRegisterClass *RC,
|
|
|
|
unsigned Reg, EVT VT) const {
|
|
|
|
SDValue VReg = AMDGPUTargetLowering::CreateLiveInRegister(DAG, RC, Reg, VT);
|
|
|
|
|
|
|
|
return DAG.getCopyFromReg(DAG.getEntryNode(), SDLoc(DAG.getEntryNode()),
|
|
|
|
cast<RegisterSDNode>(VReg)->getReg(), VT);
|
|
|
|
}
|
2015-04-08 09:09:26 +08:00
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// SI Inline Assembly Support
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
std::pair<unsigned, const TargetRegisterClass *>
|
|
|
|
SITargetLowering::getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
|
2015-07-06 03:29:18 +08:00
|
|
|
StringRef Constraint,
|
2015-04-08 09:09:26 +08:00
|
|
|
MVT VT) const {
|
2015-12-10 10:12:53 +08:00
|
|
|
|
|
|
|
if (Constraint.size() == 1) {
|
|
|
|
switch (Constraint[0]) {
|
|
|
|
case 's':
|
|
|
|
case 'r':
|
|
|
|
switch (VT.getSizeInBits()) {
|
|
|
|
default:
|
|
|
|
return std::make_pair(0U, nullptr);
|
|
|
|
case 32:
|
2015-04-08 09:09:26 +08:00
|
|
|
return std::make_pair(0U, &AMDGPU::SGPR_32RegClass);
|
2015-12-10 10:12:53 +08:00
|
|
|
case 64:
|
|
|
|
return std::make_pair(0U, &AMDGPU::SGPR_64RegClass);
|
|
|
|
case 128:
|
|
|
|
return std::make_pair(0U, &AMDGPU::SReg_128RegClass);
|
|
|
|
case 256:
|
|
|
|
return std::make_pair(0U, &AMDGPU::SReg_256RegClass);
|
|
|
|
}
|
|
|
|
|
|
|
|
case 'v':
|
|
|
|
switch (VT.getSizeInBits()) {
|
|
|
|
default:
|
|
|
|
return std::make_pair(0U, nullptr);
|
|
|
|
case 32:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VGPR_32RegClass);
|
|
|
|
case 64:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VReg_64RegClass);
|
|
|
|
case 96:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VReg_96RegClass);
|
|
|
|
case 128:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VReg_128RegClass);
|
|
|
|
case 256:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VReg_256RegClass);
|
|
|
|
case 512:
|
|
|
|
return std::make_pair(0U, &AMDGPU::VReg_512RegClass);
|
|
|
|
}
|
2015-04-08 09:09:26 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (Constraint.size() > 1) {
|
|
|
|
const TargetRegisterClass *RC = nullptr;
|
|
|
|
if (Constraint[1] == 'v') {
|
|
|
|
RC = &AMDGPU::VGPR_32RegClass;
|
|
|
|
} else if (Constraint[1] == 's') {
|
|
|
|
RC = &AMDGPU::SGPR_32RegClass;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (RC) {
|
2015-06-23 10:05:55 +08:00
|
|
|
uint32_t Idx;
|
|
|
|
bool Failed = Constraint.substr(2).getAsInteger(10, Idx);
|
|
|
|
if (!Failed && Idx < RC->getNumRegs())
|
2015-04-08 09:09:26 +08:00
|
|
|
return std::make_pair(RC->getRegister(Idx), RC);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return TargetLowering::getRegForInlineAsmConstraint(TRI, Constraint, VT);
|
|
|
|
}
|
2015-12-10 10:12:53 +08:00
|
|
|
|
|
|
|
SITargetLowering::ConstraintType
|
|
|
|
SITargetLowering::getConstraintType(StringRef Constraint) const {
|
|
|
|
if (Constraint.size() == 1) {
|
|
|
|
switch (Constraint[0]) {
|
|
|
|
default: break;
|
|
|
|
case 's':
|
|
|
|
case 'v':
|
|
|
|
return C_RegisterClass;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return TargetLowering::getConstraintType(Constraint);
|
|
|
|
}
|