[PATCH v4 1/1] R600: Add carry and borrow instructions. Use them to implement UADDO/USUBO
Tom Stellard
tom at stellard.net
Tue Oct 14 10:27:48 PDT 2014
On Mon, Oct 13, 2014 at 08:25:33PM -0400, Jan Vesely wrote:
> On Mon, 2014-10-13 at 16:31 -0700, Matt Arsenault wrote:
> > On Oct 13, 2014, at 3:49 PM, Jan Vesely <jan.vesely at rutgers.edu> wrote:
> >
> > > v2: tighten the sub64 tests
> > > v3: rename to CARRY/BORROW
> > > v4: fixup test cmdline
> > > add known bits computation
> > > use sign extend instead of sub 0,x
> > > better add test
> > >
> > > Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
> > > ---
> > >
> > > Test changes in this patch need both:
> > > LegalizeDAG: Try to use Overflow operations when expanding ADD/SUB
> > > SelectionDAG: Add sext_inreg optimizations
> >
> >
> > LGTM with a few trivial issues
>
> thanks.
> I'll push all three together once the last patch is reviewed.
Which patch still needs to be reivewed?
-Tom
>
> >
> > >
> > > lib/Target/R600/AMDGPUISelLowering.cpp | 12 +++
> > > lib/Target/R600/AMDGPUISelLowering.h | 2 +
> > > lib/Target/R600/AMDGPUInstrInfo.td | 6 ++
> > > lib/Target/R600/AMDGPUSubtarget.h | 8 ++
> > > lib/Target/R600/EvergreenInstructions.td | 3 +
> > > lib/Target/R600/R600ISelLowering.cpp | 42 +++++++-
> > > test/CodeGen/R600/add.ll | 170 ++++++++++++++++++-------------
> > > test/CodeGen/R600/sub.ll | 18 ++--
> > > test/CodeGen/R600/uaddo.ll | 17 +++-
> > > test/CodeGen/R600/usubo.ll | 23 ++++-
> > > 10 files changed, 217 insertions(+), 84 deletions(-)
> > >
> > > diff --git a/lib/Target/R600/AMDGPUISelLowering.cpp b/lib/Target/R600/AMDGPUISelLowering.cpp
> > > index b03ec72..0106cbb 100644
> > > --- a/lib/Target/R600/AMDGPUISelLowering.cpp
> > > +++ b/lib/Target/R600/AMDGPUISelLowering.cpp
> > > @@ -2385,6 +2385,12 @@ void AMDGPUTargetLowering::computeKnownBitsForTargetNode(
> > > KnownZero, KnownOne, DAG, Depth);
> > > break;
> > >
> > > + case AMDGPUISD::CARRY:
> > > + case AMDGPUISD::BORROW: {
> > > + KnownZero = APInt::getHighBitsSet(32, 31);
> > > + break;
> > > + }
> > > +
> > > case AMDGPUISD::BFE_I32:
> > > case AMDGPUISD::BFE_U32: {
> > > ConstantSDNode *CWidth = dyn_cast<ConstantSDNode>(Op.getOperand(2));
> > > @@ -2436,6 +2442,12 @@ unsigned AMDGPUTargetLowering::ComputeNumSignBitsForTargetNode(
> > > return Width ? 32 - (Width->getZExtValue() & 0x1f) : 1;
> > > }
> > >
> > > + case AMDGPUISD::CARRY:
> > > + case AMDGPUISD::BORROW: {
> > > + return 31;
> > > + break;
> > Don’t need break
>
> I removed the brackets too.
>
> > > + }
> > > +
> > > default:
> > > return 1;
> > > }
> > > diff --git a/lib/Target/R600/AMDGPUISelLowering.h b/lib/Target/R600/AMDGPUISelLowering.h
> > > index 05068a5..4388dea 100644
> > > --- a/lib/Target/R600/AMDGPUISelLowering.h
> > > +++ b/lib/Target/R600/AMDGPUISelLowering.h
> > > @@ -211,6 +211,8 @@ enum {
> > > RSQ_CLAMPED,
> > > LDEXP,
> > > DOT4,
> > > + CARRY,
> > > + BORROW,
> > > BFE_U32, // Extract range of bits with zero extension to 32-bits.
> > > BFE_I32, // Extract range of bits with sign extension to 32-bits.
> > > BFI, // (src0 & src1) | (~src0 & src2)
> > > diff --git a/lib/Target/R600/AMDGPUInstrInfo.td b/lib/Target/R600/AMDGPUInstrInfo.td
> > > index 3d70791..1600c4a 100644
> > > --- a/lib/Target/R600/AMDGPUInstrInfo.td
> > > +++ b/lib/Target/R600/AMDGPUInstrInfo.td
> > > @@ -91,6 +91,12 @@ def AMDGPUumin : SDNode<"AMDGPUISD::UMIN", SDTIntBinOp,
> > > [SDNPCommutative, SDNPAssociative]
> > >> ;
> > >
> > > +// out = (src0 + src1 > 0xFFFFFFFF) ? 1 : 0
> > > +def AMDGPUcarry : SDNode<"AMDGPUISD::CARRY", SDTIntBinOp, []>;
> > > +
> > > +// out = (src1 > src0) ? 1 : 0
> > > +def AMDGPUborrow : SDNode<"AMDGPUISD::BORROW", SDTIntBinOp, []>;
> > > +
> > >
> > > def AMDGPUcvt_f32_ubyte0 : SDNode<"AMDGPUISD::CVT_F32_UBYTE0",
> > > SDTIntToFPOp, []>;
> > > diff --git a/lib/Target/R600/AMDGPUSubtarget.h b/lib/Target/R600/AMDGPUSubtarget.h
> > > index 2bba6e0..4d0b705 100644
> > > --- a/lib/Target/R600/AMDGPUSubtarget.h
> > > +++ b/lib/Target/R600/AMDGPUSubtarget.h
> > > @@ -173,6 +173,14 @@ public:
> > > return (getGeneration() >= EVERGREEN) && hasHWFP64();
> > > }
> > >
> > > + bool hasCARRY() const {
> > > + return (getGeneration() >= EVERGREEN);
> > > + }
> > > +
> > > + bool hasBORROW() const {
> > > + return (getGeneration() >= EVERGREEN);
> > > + }
> > > +
> > > bool IsIRStructurizerEnabled() const {
> > > return EnableIRStructurizer;
> > > }
> > > diff --git a/lib/Target/R600/EvergreenInstructions.td b/lib/Target/R600/EvergreenInstructions.td
> > > index 92e37cd..a15f750 100644
> > > --- a/lib/Target/R600/EvergreenInstructions.td
> > > +++ b/lib/Target/R600/EvergreenInstructions.td
> > > @@ -340,6 +340,9 @@ defm CUBE_eg : CUBE_Common<0xC0>;
> > >
> > > def BCNT_INT : R600_1OP_Helper <0xAA, "BCNT_INT", ctpop, VecALU>;
> > >
> > > +def ADDC_UINT : R600_2OP_Helper <0x52, "ADDC_UINT", AMDGPUcarry>;
> > > +def SUBB_UINT : R600_2OP_Helper <0x53, "SUBB_UINT", AMDGPUborrow>;
> > > +
> > > def FFBH_UINT : R600_1OP_Helper <0xAB, "FFBH_UINT", ctlz_zero_undef, VecALU>;
> > > def FFBL_INT : R600_1OP_Helper <0xAC, "FFBL_INT", cttz_zero_undef, VecALU>;
> > >
> > > diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
> > > index 7c60bbe..8feb378 100644
> > > --- a/lib/Target/R600/R600ISelLowering.cpp
> > > +++ b/lib/Target/R600/R600ISelLowering.cpp
> > > @@ -91,6 +91,15 @@ R600TargetLowering::R600TargetLowering(TargetMachine &TM) :
> > > setOperationAction(ISD::SELECT, MVT::v2i32, Expand);
> > > setOperationAction(ISD::SELECT, MVT::v4i32, Expand);
> > >
> > > + // ADD, SUB overflow. These need to be Custom because
> > > + // SelectionDAGLegalize::LegalizeOp (LegalizeDAG.cpp)
> > > + // turns Legal into expand
> > > + if (Subtarget->hasCARRY())
> > > + setOperationAction(ISD::UADDO, MVT::i32, Custom);
> > > +
> > > + if (Subtarget->hasBORROW())
> > > + setOperationAction(ISD::USUBO, MVT::i32, Custom);
> > > +
> > > // Expand sign extension of vectors
> > > if (!Subtarget->hasBFE())
> > > setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i1, Expand);
> > > @@ -156,8 +165,6 @@ R600TargetLowering::R600TargetLowering(TargetMachine &TM) :
> > > setTargetDAGCombine(ISD::SELECT_CC);
> > > setTargetDAGCombine(ISD::INSERT_VECTOR_ELT);
> > >
> > > - setOperationAction(ISD::SUB, MVT::i64, Expand);
> > > -
> > > // These should be replaced by UDVIREM, but it does not happen automatically
> > > // during Type Legalization
> > > setOperationAction(ISD::UDIV, MVT::i64, Custom);
> > > @@ -580,6 +587,37 @@ SDValue R600TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const
> > > case ISD::SHL_PARTS: return LowerSHLParts(Op, DAG);
> > > case ISD::SRA_PARTS:
> > > case ISD::SRL_PARTS: return LowerSRXParts(Op, DAG);
> > > + case ISD::UADDO: {
> > > + SDLoc DL(Op);
> > > + EVT VT = Op.getValueType();
> > > +
> > > + SDValue Lo = Op.getOperand(0);
> > > + SDValue Hi = Op.getOperand(1);
> > > +
> > > + SDValue OVF = DAG.getNode(AMDGPUISD::CARRY, DL, VT, Lo, Hi);
> > > + //extend sign
> > Space after //, capitalize and punctuate comments
> > > + OVF = DAG.getNode(ISD::SIGN_EXTEND_INREG, DL, VT, OVF,
> > > + DAG.getValueType(MVT::i1));
> > > +
> > > + SDValue Res = DAG.getNode(ISD::ADD, DL, VT, Lo, Hi);
> > > +
> > > + return DAG.getNode(ISD::MERGE_VALUES, DL, DAG.getVTList(VT, VT), Res, OVF);
> > > + }
> > > + case ISD::USUBO: {
> > > + SDLoc DL(Op);
> > > + EVT VT = Op.getValueType();
> > > +
> > > + SDValue Arg0 = Op.getOperand(0);
> > > + SDValue Arg1 = Op.getOperand(1);
> > > +
> > > + SDValue OVF = DAG.getNode(AMDGPUISD::BORROW, DL, VT, Arg0, Arg1);
> > > + //extend sign
> > > + OVF = DAG.getNode(ISD::SIGN_EXTEND_INREG, DL, VT, OVF,
> > > + DAG.getValueType(MVT::i1));
> > > + SDValue Res = DAG.getNode(ISD::SUB, DL, VT, Arg0, Arg1);
> > > +
> > > + return DAG.getNode(ISD::MERGE_VALUES, DL, DAG.getVTList(VT, VT), Res, OVF);
> > > + }
> >
> > Can you move these to their own functions like the others?
>
> I created a common function for both. quick style question.
> should I stick to (SDValue Op, SelectionDAG &DAG) arguments or is it ok
> to use:
> case ISD::UADDO: return LowerUADDSUBO(Op, DAG, ISD::ADD, AMDGPUISD::CARRY);
>
> >
> > > case ISD::FCOS:
> > > case ISD::FSIN: return LowerTrig(Op, DAG);
> > > case ISD::SELECT_CC: return LowerSELECT_CC(Op, DAG);
> > > diff --git a/test/CodeGen/R600/add.ll b/test/CodeGen/R600/add.ll
> > > index 9bea9be..8e7af3b 100644
> > > --- a/test/CodeGen/R600/add.ll
> > > +++ b/test/CodeGen/R600/add.ll
> > > @@ -1,12 +1,12 @@
> > > -; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK --check-prefix=FUNC %s
> > > -; RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=SI-CHECK --check-prefix=FUNC %s
> > > +; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefix=EG --check-prefix=FUNC %s
> > > +; RUN: llc -march=r600 -mcpu=verde -verify-machineinstrs < %s | FileCheck --check-prefix=SI --check-prefix=FUNC %s
> > >
> > > ;FUNC-LABEL: {{^}}test1:
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > >
> > > -;SI-CHECK: V_ADD_I32_e32 [[REG:v[0-9]+]], {{v[0-9]+, v[0-9]+}}
> > > -;SI-CHECK-NOT: [[REG]]
> > > -;SI-CHECK: BUFFER_STORE_DWORD [[REG]],
> > > +;SI: V_ADD_I32_e32 [[REG:v[0-9]+]], {{v[0-9]+, v[0-9]+}}
> > > +;SI-NOT: [[REG]]
> > > +;SI: BUFFER_STORE_DWORD [[REG]],
> > > define void @test1(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
> > > %b_ptr = getelementptr i32 addrspace(1)* %in, i32 1
> > > %a = load i32 addrspace(1)* %in
> > > @@ -17,11 +17,11 @@ define void @test1(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
> > > }
> > >
> > > ;FUNC-LABEL: {{^}}test2:
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > >
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > >
> > > define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
> > > %b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
> > > @@ -33,16 +33,15 @@ define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
> > > }
> > >
> > > ;FUNC-LABEL: {{^}}test4:
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > -;EG-CHECK: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > -
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > -;SI-CHECK: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > -
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +;EG: ADD_INT {{[* ]*}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
> > > +
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > +;SI: V_ADD_I32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
> > > define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
> > > %b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
> > > %a = load <4 x i32> addrspace(1)* %in
> > > @@ -53,22 +52,22 @@ define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
> > > }
> > >
> > > ; FUNC-LABEL: {{^}}test8:
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > define void @test8(<8 x i32> addrspace(1)* %out, <8 x i32> %a, <8 x i32> %b) {
> > > entry:
> > > %0 = add <8 x i32> %a, %b
> > > @@ -77,38 +76,39 @@ entry:
> > > }
> > >
> > > ; FUNC-LABEL: {{^}}test16:
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; EG-CHECK: ADD_INT
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > -; SI-CHECK: S_ADD_I32
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; EG: ADD_INT
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +; SI: S_ADD_I32
> > > +
> > > define void @test16(<16 x i32> addrspace(1)* %out, <16 x i32> %a, <16 x i32> %b) {
> > > entry:
> > > %0 = add <16 x i32> %a, %b
> > > @@ -117,8 +117,16 @@ entry:
> > > }
> > >
> > > ; FUNC-LABEL: {{^}}add64:
> > > -; SI-CHECK: S_ADD_U32
> > > -; SI-CHECK: S_ADDC_U32
> > > +; SI: S_ADD_U32
> > > +; SI: S_ADDC_U32
> > > +
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.[XYZW]]]
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[HI:T[0-9]+\.[XYZW]]]
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[LO]]
> > > +; EG-DAG: ADDC_UINT
> > > +; EG-DAG: ADD_INT
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[HI]]
> > > +; EG-NOT: SUB
> > > define void @add64(i64 addrspace(1)* %out, i64 %a, i64 %b) {
> > > entry:
> > > %0 = add i64 %a, %b
> > > @@ -132,7 +140,15 @@ entry:
> > > ; to a VGPR before doing the add.
> > >
> > > ; FUNC-LABEL: {{^}}add64_sgpr_vgpr:
> > > -; SI-CHECK-NOT: V_ADDC_U32_e32 s
> > > +; SI-NOT: V_ADDC_U32_e32 s
> > > +
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.[XYZW]]]
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[HI:T[0-9]+\.[XYZW]]]
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[LO]]
> > > +; EG-DAG: ADDC_UINT
> > > +; EG-DAG: ADD_INT
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[HI]]
> > > +; EG-NOT: SUB
> > > define void @add64_sgpr_vgpr(i64 addrspace(1)* %out, i64 %a, i64 addrspace(1)* %in) {
> > > entry:
> > > %0 = load i64 addrspace(1)* %in
> > > @@ -143,8 +159,16 @@ entry:
> > >
> > > ; Test i64 add inside a branch.
> > > ; FUNC-LABEL: {{^}}add64_in_branch:
> > > -; SI-CHECK: S_ADD_U32
> > > -; SI-CHECK: S_ADDC_U32
> > > +; SI: S_ADD_U32
> > > +; SI: S_ADDC_U32
> > > +
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.[XYZW]]]
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[HI:T[0-9]+\.[XYZW]]]
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[LO]]
> > > +; EG-DAG: ADDC_UINT
> > > +; EG-DAG: ADD_INT
> > > +; EG-DAG: ADD_INT {{[* ]*}}[[HI]]
> > > +; EG-NOT: SUB
> > > define void @add64_in_branch(i64 addrspace(1)* %out, i64 addrspace(1)* %in, i64 %a, i64 %b, i64 %c) {
> > > entry:
> > > %0 = icmp eq i64 %a, 0
> > > diff --git a/test/CodeGen/R600/sub.ll b/test/CodeGen/R600/sub.ll
> > > index 7334d4f..9623948 100644
> > > --- a/test/CodeGen/R600/sub.ll
> > > +++ b/test/CodeGen/R600/sub.ll
> > > @@ -43,10 +43,13 @@ define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
> > > ; SI: S_SUB_U32
> > > ; SI: S_SUBB_U32
> > >
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.[XYZW]]]
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[HI:T[0-9]+\.[XYZW]]]
> > > +; EG-DAG: SUB_INT {{[* ]*}}[[LO]]
> > > +; EG-DAG: SUBB_UINT
> > > ; EG-DAG: SUB_INT
> > > -; EG-DAG: SETGT_UINT
> > > -; EG-DAG: SUB_INT
> > > -; EG-DAG: ADD_INT
> > > +; EG-DAG: SUB_INT {{[* ]*}}[[HI]]
> > > +; EG-NOT: SUB
> > > define void @s_sub_i64(i64 addrspace(1)* noalias %out, i64 %a, i64 %b) nounwind {
> > > %result = sub i64 %a, %b
> > > store i64 %result, i64 addrspace(1)* %out, align 8
> > > @@ -57,10 +60,13 @@ define void @s_sub_i64(i64 addrspace(1)* noalias %out, i64 %a, i64 %b) nounwind
> > > ; SI: V_SUB_I32_e32
> > > ; SI: V_SUBB_U32_e32
> > >
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[LO:T[0-9]+\.[XYZW]]]
> > > +; EG: MEM_RAT_CACHELESS STORE_RAW [[HI:T[0-9]+\.[XYZW]]]
> > > +; EG-DAG: SUB_INT {{[* ]*}}[[LO]]
> > > +; EG-DAG: SUBB_UINT
> > > ; EG-DAG: SUB_INT
> > > -; EG-DAG: SETGT_UINT
> > > -; EG-DAG: SUB_INT
> > > -; EG-DAG: ADD_INT
> > > +; EG-DAG: SUB_INT {{[* ]*}}[[HI]]
> > > +; EG-NOT: SUB
> > > define void @v_sub_i64(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %inA, i64 addrspace(1)* noalias %inB) nounwind {
> > > %tid = call i32 @llvm.r600.read.tidig.x() readnone
> > > %a_ptr = getelementptr i64 addrspace(1)* %inA, i32 %tid
> > > diff --git a/test/CodeGen/R600/uaddo.ll b/test/CodeGen/R600/uaddo.ll
> > > index acdbb18..24da159 100644
> > > --- a/test/CodeGen/R600/uaddo.ll
> > > +++ b/test/CodeGen/R600/uaddo.ll
> > > @@ -1,5 +1,5 @@
> > > ; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs< %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
> > > -; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs< %s
> > > +; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs< %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
> > >
> > > declare { i32, i1 } @llvm.uadd.with.overflow.i32(i32, i32) nounwind readnone
> > > declare { i64, i1 } @llvm.uadd.with.overflow.i64(i64, i64) nounwind readnone
> > > @@ -8,6 +8,9 @@ declare { i64, i1 } @llvm.uadd.with.overflow.i64(i64, i64) nounwind readnone
> > > ; SI: ADD
> > > ; SI: ADDC
> > > ; SI: ADDC
> > > +
> > > +; EG: ADDC_UINT
> > > +; EG: ADDC_UINT
> > > define void @uaddo_i64_zext(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
> > > %uadd = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 %a, i64 %b) nounwind
> > > %val = extractvalue { i64, i1 } %uadd, 0
> > > @@ -20,6 +23,9 @@ define void @uaddo_i64_zext(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
> > >
> > > ; FUNC-LABEL: {{^}}s_uaddo_i32:
> > > ; SI: S_ADD_I32
> > > +
> > > +; EG: ADDC_UINT
> > > +; EG: ADD_INT
> > > define void @s_uaddo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32 %a, i32 %b) nounwind {
> > > %uadd = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b) nounwind
> > > %val = extractvalue { i32, i1 } %uadd, 0
> > > @@ -31,6 +37,9 @@ define void @s_uaddo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32
> > >
> > > ; FUNC-LABEL: {{^}}v_uaddo_i32:
> > > ; SI: V_ADD_I32
> > > +
> > > +; EG: ADDC_UINT
> > > +; EG: ADD_INT
> > > define void @v_uaddo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
> > > %a = load i32 addrspace(1)* %aptr, align 4
> > > %b = load i32 addrspace(1)* %bptr, align 4
> > > @@ -45,6 +54,9 @@ define void @v_uaddo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32
> > > ; FUNC-LABEL: {{^}}s_uaddo_i64:
> > > ; SI: S_ADD_U32
> > > ; SI: S_ADDC_U32
> > > +
> > > +; EG: ADDC_UINT
> > > +; EG: ADD_INT
> > > define void @s_uaddo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64 %a, i64 %b) nounwind {
> > > %uadd = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 %a, i64 %b) nounwind
> > > %val = extractvalue { i64, i1 } %uadd, 0
> > > @@ -57,6 +69,9 @@ define void @s_uaddo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64
> > > ; FUNC-LABEL: {{^}}v_uaddo_i64:
> > > ; SI: V_ADD_I32
> > > ; SI: V_ADDC_U32
> > > +
> > > +; EG: ADDC_UINT
> > > +; EG: ADD_INT
> > > define void @v_uaddo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) nounwind {
> > > %a = load i64 addrspace(1)* %aptr, align 4
> > > %b = load i64 addrspace(1)* %bptr, align 4
> > > diff --git a/test/CodeGen/R600/usubo.ll b/test/CodeGen/R600/usubo.ll
> > > index 10e79d7..e17f654 100644
> > > --- a/test/CodeGen/R600/usubo.ll
> > > +++ b/test/CodeGen/R600/usubo.ll
> > > @@ -1,10 +1,13 @@
> > > -; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs< %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
> > > -; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs< %s
> > > +; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
> > > +; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
> > >
> > > declare { i32, i1 } @llvm.usub.with.overflow.i32(i32, i32) nounwind readnone
> > > declare { i64, i1 } @llvm.usub.with.overflow.i64(i64, i64) nounwind readnone
> > >
> > > ; FUNC-LABEL: {{^}}usubo_i64_zext:
> > > +
> > > +; EG: SUBB_UINT
> > > +; EG: ADDC_UINT
> > > define void @usubo_i64_zext(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
> > > %usub = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 %a, i64 %b) nounwind
> > > %val = extractvalue { i64, i1 } %usub, 0
> > > @@ -17,6 +20,9 @@ define void @usubo_i64_zext(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
> > >
> > > ; FUNC-LABEL: {{^}}s_usubo_i32:
> > > ; SI: S_SUB_I32
> > > +
> > > +; EG-DAG: SUBB_UINT
> > > +; EG-DAG: SUB_INT
> > > define void @s_usubo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32 %a, i32 %b) nounwind {
> > > %usub = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 %a, i32 %b) nounwind
> > > %val = extractvalue { i32, i1 } %usub, 0
> > > @@ -28,6 +34,9 @@ define void @s_usubo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32
> > >
> > > ; FUNC-LABEL: {{^}}v_usubo_i32:
> > > ; SI: V_SUBREV_I32_e32
> > > +
> > > +; EG-DAG: SUBB_UINT
> > > +; EG-DAG: SUB_INT
> > > define void @v_usubo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind {
> > > %a = load i32 addrspace(1)* %aptr, align 4
> > > %b = load i32 addrspace(1)* %bptr, align 4
> > > @@ -42,6 +51,11 @@ define void @v_usubo_i32(i32 addrspace(1)* %out, i1 addrspace(1)* %carryout, i32
> > > ; FUNC-LABEL: {{^}}s_usubo_i64:
> > > ; SI: S_SUB_U32
> > > ; SI: S_SUBB_U32
> > > +
> > > +; EG-DAG: SUBB_UINT
> > > +; EG-DAG: SUB_INT
> > > +; EG-DAG: SUB_INT
> > > +; EG: SUB_INT
> > > define void @s_usubo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64 %a, i64 %b) nounwind {
> > > %usub = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 %a, i64 %b) nounwind
> > > %val = extractvalue { i64, i1 } %usub, 0
> > > @@ -54,6 +68,11 @@ define void @s_usubo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64
> > > ; FUNC-LABEL: {{^}}v_usubo_i64:
> > > ; SI: V_SUB_I32
> > > ; SI: V_SUBB_U32
> > > +
> > > +; EG-DAG: SUBB_UINT
> > > +; EG-DAG: SUB_INT
> > > +; EG-DAG: SUB_INT
> > > +; EG: SUB_INT
> > > define void @v_usubo_i64(i64 addrspace(1)* %out, i1 addrspace(1)* %carryout, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) nounwind {
> > > %a = load i64 addrspace(1)* %aptr, align 4
> > > %b = load i64 addrspace(1)* %bptr, align 4
> > > --
> > > 1.9.3
> > >
> > > _______________________________________________
> > > llvm-commits mailing list
> > > llvm-commits at cs.uiuc.edu
> > > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
> >
>
> --
> Jan Vesely <jan.vesely at rutgers.edu>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
More information about the llvm-commits
mailing list