AMDGPU/GlobalISel: Select llvm.amdgcn.raw.buffer.store.format

This needs special handling due to some subtargets that have a
nonstandard register layout for f16 vectors

Also reject some illegal types on other targets.

llvm-svn: 372293
This commit is contained in:
Matt Arsenault 2019-09-19 02:35:08 +00:00
parent 67f1f6ff8c
commit 494243597b
5 changed files with 955 additions and 20 deletions

View File

@ -787,6 +787,91 @@ getBaseWithConstantOffset(MachineRegisterInfo &MRI, Register Reg) {
return {Reg, 0, Def};
}
static unsigned getBufferStoreOpcode(LLT Ty,
const unsigned MemSize,
const bool Offen) {
const int Size = Ty.getSizeInBits();
switch (8 * MemSize) {
case 8:
return Offen ? AMDGPU::BUFFER_STORE_BYTE_OFFEN_exact :
AMDGPU::BUFFER_STORE_BYTE_OFFSET_exact;
case 16:
return Offen ? AMDGPU::BUFFER_STORE_SHORT_OFFEN_exact :
AMDGPU::BUFFER_STORE_SHORT_OFFSET_exact;
default:
unsigned Opc = Offen ? AMDGPU::BUFFER_STORE_DWORD_OFFEN_exact :
AMDGPU::BUFFER_STORE_DWORD_OFFSET_exact;
if (Size > 32)
Opc = AMDGPU::getMUBUFOpcode(Opc, Size / 32);
return Opc;
}
}
static unsigned getBufferStoreFormatOpcode(LLT Ty,
const unsigned MemSize,
const bool Offen) {
bool IsD16Packed = Ty.getScalarSizeInBits() == 16;
bool IsD16Unpacked = 8 * MemSize < Ty.getSizeInBits();
int NumElts = Ty.isVector() ? Ty.getNumElements() : 1;
if (IsD16Packed) {
switch (NumElts) {
case 1:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_X_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_X_OFFSET_exact;
case 2:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XY_OFFSET_exact;
case 3:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XYZ_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XYZ_OFFSET_exact;
case 4:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XYZW_OFFSET_exact;
default:
return -1;
}
}
if (IsD16Unpacked) {
switch (NumElts) {
case 1:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_X_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_X_OFFSET_exact;
case 2:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFSET_exact;
case 3:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XYZ_gfx80_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XYZ_gfx80_OFFSET_exact;
case 4:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFSET_exact;
default:
return -1;
}
}
switch (NumElts) {
case 1:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_X_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_X_OFFSET_exact;
case 2:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_XY_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_XY_OFFSET_exact;
case 3:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_XYZ_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_XYZ_OFFSET_exact;
case 4:
return Offen ? AMDGPU::BUFFER_STORE_FORMAT_XYZW_OFFEN_exact :
AMDGPU::BUFFER_STORE_FORMAT_XYZW_OFFSET_exact;
default:
return -1;
}
llvm_unreachable("unhandled buffer store");
}
// TODO: Move this to combiner
// Returns base register, imm offset, total constant offset.
std::tuple<Register, unsigned, unsigned>
@ -878,23 +963,10 @@ bool AMDGPUInstructionSelector::selectStoreIntrinsic(MachineInstr &MI,
const bool Offen = !isZero(VOffset, MRI);
unsigned Opc = AMDGPU::BUFFER_STORE_DWORD_OFFEN_exact;
switch (8 * MemSize) {
case 8:
Opc = Offen ? AMDGPU::BUFFER_STORE_BYTE_OFFEN_exact :
AMDGPU::BUFFER_STORE_BYTE_OFFSET_exact;
break;
case 16:
Opc = Offen ? AMDGPU::BUFFER_STORE_SHORT_OFFEN_exact :
AMDGPU::BUFFER_STORE_SHORT_OFFSET_exact;
break;
default:
Opc = Offen ? AMDGPU::BUFFER_STORE_DWORD_OFFEN_exact :
AMDGPU::BUFFER_STORE_DWORD_OFFSET_exact;
if (Size > 32)
Opc = AMDGPU::getMUBUFOpcode(Opc, Size / 32);
break;
}
int Opc = IsFormat ? getBufferStoreFormatOpcode(Ty, MemSize, Offen) :
getBufferStoreOpcode(Ty, MemSize, Offen);
if (Opc == -1)
return false;
MachineInstrBuilder MIB = B.buildInstr(Opc)
.addUse(VData);
@ -972,6 +1044,8 @@ bool AMDGPUInstructionSelector::selectG_INTRINSIC_W_SIDE_EFFECTS(
}
case Intrinsic::amdgcn_raw_buffer_store:
return selectStoreIntrinsic(I, false);
case Intrinsic::amdgcn_raw_buffer_store_format:
return selectStoreIntrinsic(I, true);
default:
return selectImpl(I, *CoverageInfo);
}

View File

@ -1751,12 +1751,33 @@ bool AMDGPULegalizerInfo::legalizeIsAddrSpace(MachineInstr &MI,
return true;
}
/// Handle register layout difference for f16 images for some subtargets.
Register AMDGPULegalizerInfo::handleD16VData(MachineIRBuilder &B,
MachineRegisterInfo &MRI,
Register Reg) const {
if (!ST.hasUnpackedD16VMem())
return Reg;
const LLT S16 = LLT::scalar(16);
const LLT S32 = LLT::scalar(32);
LLT StoreVT = MRI.getType(Reg);
assert(StoreVT.isVector() && StoreVT.getElementType() == S16);
auto Unmerge = B.buildUnmerge(S16, Reg);
SmallVector<Register, 4> WideRegs;
for (int I = 0, E = Unmerge->getNumOperands() - 1; I != E; ++I)
WideRegs.push_back(B.buildAnyExt(S32, Unmerge.getReg(I)).getReg(0));
int NumElts = StoreVT.getNumElements();
return B.buildBuildVector(LLT::vector(NumElts, S32), WideRegs).getReg(0);
}
bool AMDGPULegalizerInfo::legalizeRawBufferStore(MachineInstr &MI,
MachineRegisterInfo &MRI,
MachineIRBuilder &B,
bool IsFormat) const {
assert(!IsFormat && "format buffer stores not implemented");
// TODO: Reject f16 format on targets where unsupported.
Register VData = MI.getOperand(1).getReg();
LLT Ty = MRI.getType(VData);
@ -1774,8 +1795,11 @@ bool AMDGPULegalizerInfo::legalizeRawBufferStore(MachineInstr &MI,
}
if (Ty.isVector()) {
if (Ty.getElementType() == S16 && Ty.getNumElements() <= 4)
if (Ty.getElementType() == S16 && Ty.getNumElements() <= 4) {
if (IsFormat)
MI.getOperand(1).setReg(handleD16VData(B, MRI, VData));
return true;
}
return Ty.getElementType() == S32 && Ty.getNumElements() <= 4;
}
@ -1877,6 +1901,8 @@ bool AMDGPULegalizerInfo::legalizeIntrinsic(MachineInstr &MI,
}
case Intrinsic::amdgcn_raw_buffer_store:
return legalizeRawBufferStore(MI, MRI, B, false);
case Intrinsic::amdgcn_raw_buffer_store_format:
return legalizeRawBufferStore(MI, MRI, B, true);
default:
return true;
}

View File

@ -84,6 +84,8 @@ public:
bool legalizeIsAddrSpace(MachineInstr &MI, MachineRegisterInfo &MRI,
MachineIRBuilder &B, unsigned AddrSpace) const;
Register handleD16VData(MachineIRBuilder &B, MachineRegisterInfo &MRI,
Register Reg) const;
bool legalizeRawBufferStore(MachineInstr &MI, MachineRegisterInfo &MRI,
MachineIRBuilder &B, bool IsFormat) const;
bool legalizeIntrinsic(MachineInstr &MI, MachineRegisterInfo &MRI,

View File

@ -0,0 +1,519 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga -stop-after=instruction-select -o - %s | FileCheck -check-prefix=UNPACKED %s
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx810 -stop-after=instruction-select -o - %s | FileCheck -check-prefix=PACKED %s
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f16(<4 x i32> inreg %rsrc, half %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 2 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f16
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 2 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f16(<4 x i32> inreg %rsrc, half %val, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], $noreg, [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 2 into custom TargetCustom7 + 4095, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f16
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], $noreg, [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 2 into custom TargetCustom7 + 4095, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.f16(half %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY7]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16(<4 x i32> inreg %rsrc, <4 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; UNPACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
; UNPACKED: [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY9]], [[COPY5]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY5]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
; UNPACKED: BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; PACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; PACKED: BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
; Make sure unpack code is emitted outside of loop
define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16(<4 x i32> %rsrc, <4 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: successors: %bb.2(0x80000000)
; UNPACKED: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
; UNPACKED: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; UNPACKED: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; UNPACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; UNPACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr2
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
; UNPACKED: [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY9]], [[COPY5]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY5]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
; UNPACKED: [[COPY10:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; UNPACKED: [[COPY11:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; UNPACKED: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; UNPACKED: bb.2:
; UNPACKED: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; UNPACKED: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub0, implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub1, implicit $exec
; UNPACKED: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; UNPACKED: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY10]], implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub0, implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub1, implicit $exec
; UNPACKED: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; UNPACKED: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY11]], implicit $exec
; UNPACKED: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; UNPACKED: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; UNPACKED: BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; UNPACKED: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; UNPACKED: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; UNPACKED: bb.3:
; UNPACKED: successors: %bb.4(0x80000000)
; UNPACKED: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; UNPACKED: bb.4:
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16
; PACKED: bb.1 (%ir-block.0):
; PACKED: successors: %bb.2(0x80000000)
; PACKED: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
; PACKED: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; PACKED: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; PACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; PACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr2
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; PACKED: [[COPY8:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; PACKED: [[COPY9:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; PACKED: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; PACKED: bb.2:
; PACKED: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; PACKED: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY8]].sub0, implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY8]].sub1, implicit $exec
; PACKED: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; PACKED: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY9]].sub0, implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY9]].sub1, implicit $exec
; PACKED: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; PACKED: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY9]], implicit $exec
; PACKED: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; PACKED: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; PACKED: BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; PACKED: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; PACKED: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; PACKED: bb.3:
; PACKED: successors: %bb.4(0x80000000)
; PACKED: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; PACKED: bb.4:
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4095(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4095
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
; UNPACKED: [[S_MOV_B32_1:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY6]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4095
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4096(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4096
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
; UNPACKED: [[S_MOV_B32_1:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY6]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4096
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_16(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_16
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: %11:vgpr_32, dead %21:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_16
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; PACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; PACKED: %11:vgpr_32, dead %13:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
%voffset.add = add i32 %voffset, 16
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4095(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4095
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4095
; UNPACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: %11:vgpr_32, dead %22:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; UNPACKED: [[S_MOV_B32_1:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4095
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4095
; PACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; PACKED: %11:vgpr_32, dead %13:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4095
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4096(<4 x i32> inreg %rsrc, <2 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4096
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; UNPACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; UNPACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; UNPACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; UNPACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; UNPACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: %11:vgpr_32, dead %22:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; UNPACKED: [[S_MOV_B32_1:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
; UNPACKED: BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4096
; PACKED: bb.1 (%ir-block.0):
; PACKED: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; PACKED: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; PACKED: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; PACKED: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; PACKED: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; PACKED: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; PACKED: %11:vgpr_32, dead %13:sreg_64_xexec = V_ADD_I32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
; PACKED: BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4096
call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
; Check what happens with offset add inside a waterfall loop
define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16_add_4096(<4 x i32> %rsrc, <4 x half> %val, i32 %voffset, i32 inreg %soffset) {
; UNPACKED-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16_add_4096
; UNPACKED: bb.1 (%ir-block.0):
; UNPACKED: successors: %bb.2(0x80000000)
; UNPACKED: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
; UNPACKED: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; UNPACKED: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; UNPACKED: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; UNPACKED: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; UNPACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; UNPACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; UNPACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; UNPACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr2
; UNPACKED: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; UNPACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; UNPACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; UNPACKED: %13:vgpr_32, dead %47:sreg_64_xexec = V_ADD_I32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
; UNPACKED: [[S_MOV_B32_1:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; UNPACKED: [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY9]], [[COPY4]], implicit $exec
; UNPACKED: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
; UNPACKED: [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY10]], [[COPY5]], implicit $exec
; UNPACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY5]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
; UNPACKED: [[COPY11:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; UNPACKED: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; UNPACKED: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; UNPACKED: bb.2:
; UNPACKED: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; UNPACKED: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub0, implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub1, implicit $exec
; UNPACKED: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; UNPACKED: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY11]], implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY12]].sub0, implicit $exec
; UNPACKED: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY12]].sub1, implicit $exec
; UNPACKED: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; UNPACKED: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY12]], implicit $exec
; UNPACKED: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; UNPACKED: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; UNPACKED: BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; UNPACKED: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; UNPACKED: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; UNPACKED: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; UNPACKED: bb.3:
; UNPACKED: successors: %bb.4(0x80000000)
; UNPACKED: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; UNPACKED: bb.4:
; UNPACKED: S_ENDPGM 0
; PACKED-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16_add_4096
; PACKED: bb.1 (%ir-block.0):
; PACKED: successors: %bb.2(0x80000000)
; PACKED: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6
; PACKED: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; PACKED: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; PACKED: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; PACKED: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; PACKED: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; PACKED: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; PACKED: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; PACKED: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr2
; PACKED: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; PACKED: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; PACKED: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; PACKED: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; PACKED: %13:vgpr_32, dead %31:sreg_64_xexec = V_ADD_I32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
; PACKED: [[COPY9:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; PACKED: [[COPY10:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; PACKED: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; PACKED: bb.2:
; PACKED: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; PACKED: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY9]].sub0, implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY9]].sub1, implicit $exec
; PACKED: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; PACKED: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY9]], implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub0, implicit $exec
; PACKED: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub1, implicit $exec
; PACKED: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; PACKED: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY10]], implicit $exec
; PACKED: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; PACKED: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; PACKED: BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; PACKED: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; PACKED: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; PACKED: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; PACKED: bb.3:
; PACKED: successors: %bb.4(0x80000000)
; PACKED: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; PACKED: bb.4:
; PACKED: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4096
call void @llvm.amdgcn.raw.buffer.store.format.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
declare void @llvm.amdgcn.raw.buffer.store.format.f16(half, <4 x i32>, i32, i32, i32 immarg)
declare void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half>, <4 x i32>, i32, i32, i32 immarg)
declare void @llvm.amdgcn.raw.buffer.store.format.v4f16(<4 x half>, <4 x i32>, i32, i32, i32 immarg)

View File

@ -0,0 +1,314 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga -stop-after=instruction-select -o - %s | FileCheck %s
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx810 -stop-after=instruction-select -o - %s | FileCheck %s
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f32(<4 x i32> inreg %rsrc, float %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: BUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f32(<4 x i32> inreg %rsrc, float %val, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: BUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY4]], $noreg, [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 4 into custom TargetCustom7 + 4095, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.f32(float %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v3f32(<4 x i32> inreg %rsrc, <3 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v3f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; CHECK: [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_96 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2
; CHECK: BUFFER_STORE_FORMAT_XYZ_OFFEN_exact [[REG_SEQUENCE1]], [[COPY7]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 12 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32(<4 x i32> inreg %rsrc, <4 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; CHECK: [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
; CHECK: BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE]], [[COPY9]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 16 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32(<4 x i32> %rsrc, <4 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32
; CHECK: bb.1 (%ir-block.0):
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
; CHECK: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; CHECK: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr7
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; CHECK: [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr2
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
; CHECK: [[COPY10:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; CHECK: [[COPY11:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; CHECK: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; CHECK: bb.2:
; CHECK: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub0, implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY10]].sub1, implicit $exec
; CHECK: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; CHECK: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY10]], implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub0, implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub1, implicit $exec
; CHECK: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; CHECK: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY11]], implicit $exec
; CHECK: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; CHECK: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; CHECK: BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 16 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; CHECK: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; CHECK: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; CHECK: bb.3:
; CHECK: successors: %bb.4(0x80000000)
; CHECK: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; CHECK: bb.4:
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_soffset4095(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_soffset4095
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_soffset4096(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_soffset4096
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_16(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_16
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 16
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; CHECK: %13:vgpr_32, dead %15:sreg_64_xexec = V_ADD_I32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
%voffset.add = add i32 %voffset, 16
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_4095(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_4095
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4095
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; CHECK: %13:vgpr_32, dead %15:sreg_64_xexec = V_ADD_I32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4095
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_4096(<4 x i32> inreg %rsrc, <2 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f32_voffset_add_4096
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $vgpr0, $vgpr1, $vgpr2
; CHECK: [[COPY:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr2
; CHECK: [[COPY1:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr3
; CHECK: [[COPY2:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr4
; CHECK: [[COPY3:%[0-9]+]]:sreg_32_xm0 = COPY $sgpr5
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; CHECK: %13:vgpr_32, dead %15:sreg_64_xexec = V_ADD_I32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
; CHECK: BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 8 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4096
call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
; Check what happens with offset add inside a waterfall loop
define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32_add_4096(<4 x i32> %rsrc, <4 x float> %val, i32 %voffset, i32 inreg %soffset) {
; CHECK-LABEL: name: raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f32_add_4096
; CHECK: bb.1 (%ir-block.0):
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $sgpr2, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
; CHECK: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr6
; CHECK: [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr7
; CHECK: [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr8
; CHECK: [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr2
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
; CHECK: [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32_xm0 = S_MOV_B32 4096
; CHECK: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
; CHECK: %15:vgpr_32, dead %33:sreg_64_xexec = V_ADD_I32_e64 [[COPY8]], [[COPY10]], 0, implicit $exec
; CHECK: [[COPY11:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
; CHECK: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
; CHECK: [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
; CHECK: bb.2:
; CHECK: successors: %bb.3(0x40000000), %bb.2(0x40000000)
; CHECK: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub0, implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_1:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY11]].sub1, implicit $exec
; CHECK: [[REG_SEQUENCE2:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1
; CHECK: [[V_CMP_EQ_U64_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY11]], implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_2:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY12]].sub0, implicit $exec
; CHECK: [[V_READFIRSTLANE_B32_3:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY12]].sub1, implicit $exec
; CHECK: [[REG_SEQUENCE3:%[0-9]+]]:sreg_64_xexec = REG_SEQUENCE [[V_READFIRSTLANE_B32_2]], %subreg.sub0, [[V_READFIRSTLANE_B32_3]], %subreg.sub1
; CHECK: [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY12]], implicit $exec
; CHECK: [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
; CHECK: [[REG_SEQUENCE4:%[0-9]+]]:sreg_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
; CHECK: BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %15, [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable store 16 into custom TargetCustom7, align 1, addrspace 4)
; CHECK: [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
; CHECK: $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
; CHECK: S_CBRANCH_EXECNZ %bb.2, implicit $exec
; CHECK: bb.3:
; CHECK: successors: %bb.4(0x80000000)
; CHECK: $exec = S_MOV_B64_term [[S_MOV_B64_term]]
; CHECK: bb.4:
; CHECK: S_ENDPGM 0
%voffset.add = add i32 %voffset, 4096
call void @llvm.amdgcn.raw.buffer.store.format.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
ret void
}
declare void @llvm.amdgcn.raw.buffer.store.format.f32(float, <4 x i32>, i32, i32, i32 immarg)
declare void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float>, <4 x i32>, i32, i32, i32 immarg)
declare void @llvm.amdgcn.raw.buffer.store.format.v3f32(<3 x float>, <4 x i32>, i32, i32, i32 immarg)
declare void @llvm.amdgcn.raw.buffer.store.format.v4f32(<4 x float>, <4 x i32>, i32, i32, i32 immarg)