[llvm] 29eb3dc - [PowerPC] Materialize i64 constants by enumerated patterns.
via llvm-commits
llvm-commits at lists.llvm.org
Sun Dec 20 21:21:59 PST 2020
Author: Esme-Yi
Date: 2020-12-21T05:21:07Z
New Revision: 29eb3dcfe628e9fc89047ceb1502e22a0831cb87
URL: https://github.com/llvm/llvm-project/commit/29eb3dcfe628e9fc89047ceb1502e22a0831cb87
DIFF: https://github.com/llvm/llvm-project/commit/29eb3dcfe628e9fc89047ceb1502e22a0831cb87.diff
LOG: [PowerPC] Materialize i64 constants by enumerated patterns.
Summary: Some constants can be handled with less instructions than our current results. And it seems our original approach is not very easy to extend. Therefore this patch proposes to materialize all 64-bit constants by enumerated patterns.
I traversed almost all constants to verified the functionality of these pattens. A traversed comparison of the number of instructions used by the original method and the new method has also been completed, where no degradation was caused by this patch. This patch also passed Bootstrap test and SPEC test.
Improvements of this patch are shown in llvm/test/CodeGen/PowerPC/constants-i64.ll
Reviewed By: steven.zhang, stefanp
Differential Revision: https://reviews.llvm.org/D92089
Added:
Modified:
llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
llvm/test/CodeGen/PowerPC/aix-cc-abi.ll
llvm/test/CodeGen/PowerPC/arr-fp-arg-no-copy.ll
llvm/test/CodeGen/PowerPC/bperm.ll
llvm/test/CodeGen/PowerPC/combine_ext_trunc.ll
llvm/test/CodeGen/PowerPC/constants-i64.ll
llvm/test/CodeGen/PowerPC/f128-fma.ll
llvm/test/CodeGen/PowerPC/f128-passByValue.ll
llvm/test/CodeGen/PowerPC/fast-isel-pcrel.ll
llvm/test/CodeGen/PowerPC/fp-strict-f128.ll
llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
llvm/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
llvm/test/CodeGen/PowerPC/funnel-shift.ll
llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
llvm/test/CodeGen/PowerPC/negctr.ll
llvm/test/CodeGen/PowerPC/ori_imm32.ll
llvm/test/CodeGen/PowerPC/ori_imm64.ll
llvm/test/CodeGen/PowerPC/pr43976.ll
llvm/test/CodeGen/PowerPC/pr45448.ll
llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
llvm/test/CodeGen/PowerPC/sms-grp-order.ll
llvm/test/CodeGen/PowerPC/srem-vector-lkk.ll
llvm/test/CodeGen/PowerPC/tailcall-speculatable-callee.ll
llvm/test/CodeGen/PowerPC/unaligned-addressing-mode.ll
llvm/test/CodeGen/PowerPC/urem-vector-lkk.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
index 3b580d4ff272..cd609af0ffe6 100644
--- a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
@@ -743,251 +743,6 @@ bool PPCDAGToDAGISel::tryBitfieldInsert(SDNode *N) {
return false;
}
-// Predict the number of instructions that would be generated by calling
-// selectI64Imm(N).
-static unsigned selectI64ImmInstrCountDirect(int64_t Imm) {
- // Assume no remaining bits.
- unsigned Remainder = 0;
- // Assume no shift required.
- unsigned Shift = 0;
-
- // If it can't be represented as a 32 bit value.
- if (!isInt<32>(Imm)) {
- Shift = countTrailingZeros<uint64_t>(Imm);
- int64_t ImmSh = static_cast<uint64_t>(Imm) >> Shift;
-
- // If the shifted value fits 32 bits.
- if (isInt<32>(ImmSh)) {
- // Go with the shifted value.
- Imm = ImmSh;
- } else {
- // Still stuck with a 64 bit value.
- Remainder = Imm;
- Shift = 32;
- Imm >>= 32;
- }
- }
-
- // Intermediate operand.
- unsigned Result = 0;
-
- // Handle first 32 bits.
- unsigned Lo = Imm & 0xFFFF;
-
- // Simple value.
- if (isInt<16>(Imm)) {
- // Just the Lo bits.
- ++Result;
- } else if (Lo) {
- // Handle the Hi bits and Lo bits.
- Result += 2;
- } else {
- // Just the Hi bits.
- ++Result;
- }
-
- // If no shift, we're done.
- if (!Shift) return Result;
-
- // If Hi word == Lo word,
- // we can use rldimi to insert the Lo word into Hi word.
- if ((unsigned)(Imm & 0xFFFFFFFF) == Remainder) {
- ++Result;
- return Result;
- }
-
- // Shift for next step if the upper 32-bits were not zero.
- if (Imm)
- ++Result;
-
- // Add in the last bits as required.
- if ((Remainder >> 16) & 0xFFFF)
- ++Result;
- if (Remainder & 0xFFFF)
- ++Result;
-
- return Result;
-}
-
-static uint64_t Rot64(uint64_t Imm, unsigned R) {
- return (Imm << R) | (Imm >> (64 - R));
-}
-
-static unsigned selectI64ImmInstrCount(int64_t Imm) {
- unsigned Count = selectI64ImmInstrCountDirect(Imm);
-
- // If the instruction count is 1 or 2, we do not need further analysis
- // since rotate + load constant requires at least 2 instructions.
- if (Count <= 2)
- return Count;
-
- for (unsigned r = 1; r < 63; ++r) {
- uint64_t RImm = Rot64(Imm, r);
- unsigned RCount = selectI64ImmInstrCountDirect(RImm) + 1;
- Count = std::min(Count, RCount);
-
- // See comments in selectI64Imm for an explanation of the logic below.
- unsigned LS = findLastSet(RImm);
- if (LS != r-1)
- continue;
-
- uint64_t OnesMask = -(int64_t) (UINT64_C(1) << (LS+1));
- uint64_t RImmWithOnes = RImm | OnesMask;
-
- RCount = selectI64ImmInstrCountDirect(RImmWithOnes) + 1;
- Count = std::min(Count, RCount);
- }
-
- return Count;
-}
-
-// Select a 64-bit constant. For cost-modeling purposes, selectI64ImmInstrCount
-// (above) needs to be kept in sync with this function.
-static SDNode *selectI64ImmDirect(SelectionDAG *CurDAG, const SDLoc &dl,
- int64_t Imm) {
- // Assume no remaining bits.
- unsigned Remainder = 0;
- // Assume no shift required.
- unsigned Shift = 0;
-
- // If it can't be represented as a 32 bit value.
- if (!isInt<32>(Imm)) {
- Shift = countTrailingZeros<uint64_t>(Imm);
- int64_t ImmSh = static_cast<uint64_t>(Imm) >> Shift;
-
- // If the shifted value fits 32 bits.
- if (isInt<32>(ImmSh)) {
- // Go with the shifted value.
- Imm = ImmSh;
- } else {
- // Still stuck with a 64 bit value.
- Remainder = Imm;
- Shift = 32;
- Imm >>= 32;
- }
- }
-
- // Intermediate operand.
- SDNode *Result;
-
- // Handle first 32 bits.
- unsigned Lo = Imm & 0xFFFF;
- unsigned Hi = (Imm >> 16) & 0xFFFF;
-
- auto getI32Imm = [CurDAG, dl](unsigned Imm) {
- return CurDAG->getTargetConstant(Imm, dl, MVT::i32);
- };
-
- // Simple value.
- if (isInt<16>(Imm)) {
- uint64_t SextImm = SignExtend64(Lo, 16);
- SDValue SDImm = CurDAG->getTargetConstant(SextImm, dl, MVT::i64);
- // Just the Lo bits.
- Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64, SDImm);
- } else if (Lo) {
- // Handle the Hi bits.
- unsigned OpC = Hi ? PPC::LIS8 : PPC::LI8;
- Result = CurDAG->getMachineNode(OpC, dl, MVT::i64, getI32Imm(Hi));
- // And Lo bits.
- Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64,
- SDValue(Result, 0), getI32Imm(Lo));
- } else {
- // Just the Hi bits.
- Result = CurDAG->getMachineNode(PPC::LIS8, dl, MVT::i64, getI32Imm(Hi));
- }
-
- // If no shift, we're done.
- if (!Shift) return Result;
-
- // If Hi word == Lo word,
- // we can use rldimi to insert the Lo word into Hi word.
- if ((unsigned)(Imm & 0xFFFFFFFF) == Remainder) {
- SDValue Ops[] =
- { SDValue(Result, 0), SDValue(Result, 0), getI32Imm(Shift), getI32Imm(0)};
- return CurDAG->getMachineNode(PPC::RLDIMI, dl, MVT::i64, Ops);
- }
-
- // Shift for next step if the upper 32-bits were not zero.
- if (Imm) {
- Result = CurDAG->getMachineNode(PPC::RLDICR, dl, MVT::i64,
- SDValue(Result, 0),
- getI32Imm(Shift),
- getI32Imm(63 - Shift));
- }
-
- // Add in the last bits as required.
- if ((Hi = (Remainder >> 16) & 0xFFFF)) {
- Result = CurDAG->getMachineNode(PPC::ORIS8, dl, MVT::i64,
- SDValue(Result, 0), getI32Imm(Hi));
- }
- if ((Lo = Remainder & 0xFFFF)) {
- Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64,
- SDValue(Result, 0), getI32Imm(Lo));
- }
-
- return Result;
-}
-
-static SDNode *selectI64Imm(SelectionDAG *CurDAG, const SDLoc &dl,
- int64_t Imm) {
- unsigned Count = selectI64ImmInstrCountDirect(Imm);
-
- // If the instruction count is 1 or 2, we do not need further analysis
- // since rotate + load constant requires at least 2 instructions.
- if (Count <= 2)
- return selectI64ImmDirect(CurDAG, dl, Imm);
-
- unsigned RMin = 0;
-
- int64_t MatImm;
- unsigned MaskEnd;
-
- for (unsigned r = 1; r < 63; ++r) {
- uint64_t RImm = Rot64(Imm, r);
- unsigned RCount = selectI64ImmInstrCountDirect(RImm) + 1;
- if (RCount < Count) {
- Count = RCount;
- RMin = r;
- MatImm = RImm;
- MaskEnd = 63;
- }
-
- // If the immediate to generate has many trailing zeros, it might be
- // worthwhile to generate a rotated value with too many leading ones
- // (because that's free with li/lis's sign-extension semantics), and then
- // mask them off after rotation.
-
- unsigned LS = findLastSet(RImm);
- // We're adding (63-LS) higher-order ones, and we expect to mask them off
- // after performing the inverse rotation by (64-r). So we need that:
- // 63-LS == 64-r => LS == r-1
- if (LS != r-1)
- continue;
-
- uint64_t OnesMask = -(int64_t) (UINT64_C(1) << (LS+1));
- uint64_t RImmWithOnes = RImm | OnesMask;
-
- RCount = selectI64ImmInstrCountDirect(RImmWithOnes) + 1;
- if (RCount < Count) {
- Count = RCount;
- RMin = r;
- MatImm = RImmWithOnes;
- MaskEnd = LS;
- }
- }
-
- if (!RMin)
- return selectI64ImmDirect(CurDAG, dl, Imm);
-
- auto getI32Imm = [CurDAG, dl](unsigned Imm) {
- return CurDAG->getTargetConstant(Imm, dl, MVT::i32);
- };
-
- SDValue Val = SDValue(selectI64ImmDirect(CurDAG, dl, MatImm), 0);
- return CurDAG->getMachineNode(PPC::RLDICR, dl, MVT::i64, Val,
- getI32Imm(64 - RMin), getI32Imm(MaskEnd));
-}
-
static unsigned allUsesTruncate(SelectionDAG *CurDAG, SDNode *N) {
unsigned MaxTruncation = 0;
// Cannot use range-based for loop here as we need the actual use (i.e. we
@@ -1044,6 +799,273 @@ static unsigned allUsesTruncate(SelectionDAG *CurDAG, SDNode *N) {
return MaxTruncation;
}
+// For any 32 < Num < 64, check if the Imm contains at least Num consecutive
+// zeros and return the number of bits by the left of these consecutive zeros.
+static int findContiguousZerosAtLeast(uint64_t Imm, unsigned Num) {
+ unsigned HiTZ = countTrailingZeros<uint32_t>(Hi_32(Imm));
+ unsigned LoLZ = countLeadingZeros<uint32_t>(Lo_32(Imm));
+ if ((HiTZ + LoLZ) >= Num)
+ return (32 + HiTZ);
+ return 0;
+}
+
+// Direct materialization of 64-bit constants by enumerated patterns.
+static SDNode *selectI64ImmDirect(SelectionDAG *CurDAG, const SDLoc &dl,
+ uint64_t Imm, unsigned &InstCnt) {
+ unsigned TZ = countTrailingZeros<uint64_t>(Imm);
+ unsigned LZ = countLeadingZeros<uint64_t>(Imm);
+ unsigned TO = countTrailingOnes<uint64_t>(Imm);
+ unsigned LO = countLeadingOnes<uint64_t>(Imm);
+ // Count of ones follwing the leading zeros.
+ unsigned FO = countLeadingOnes<uint64_t>(Imm << LZ);
+ unsigned Hi32 = Hi_32(Imm);
+ unsigned Lo32 = Lo_32(Imm);
+ SDNode *Result = nullptr;
+ unsigned Shift = 0;
+
+ auto getI32Imm = [CurDAG, dl](unsigned Imm) {
+ return CurDAG->getTargetConstant(Imm, dl, MVT::i32);
+ };
+
+ // Following patterns use 1 instructions to materialize the Imm.
+ InstCnt = 1;
+ // 1-1) Patterns : {zeros}{15-bit valve}
+ // {ones}{15-bit valve}
+ if (isInt<16>(Imm)) {
+ SDValue SDImm = CurDAG->getTargetConstant(Imm, dl, MVT::i64);
+ return CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64, SDImm);
+ }
+ // 1-2) Patterns : {zeros}{15-bit valve}{16 zeros}
+ // {ones}{15-bit valve}{16 zeros}
+ if (TZ > 15 && (LZ > 32 || LO > 32))
+ return CurDAG->getMachineNode(PPC::LIS8, dl, MVT::i64,
+ getI32Imm((Imm >> 16) & 0xffff));
+
+ // Following patterns use 2 instructions to materialize the Imm.
+ InstCnt = 2;
+ // 2-1) Patterns : {zeros}{31-bit value}
+ // {ones}{31-bit value}
+ if (isInt<32>(Imm)) {
+ uint64_t ImmHi16 = (Imm >> 16) & 0xffff;
+ unsigned Opcode = ImmHi16 ? PPC::LIS8 : PPC::LI8;
+ Result = CurDAG->getMachineNode(Opcode, dl, MVT::i64, getI32Imm(ImmHi16));
+ return CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Imm & 0xffff));
+ }
+ // 2-2) Patterns : {zeros}{ones}{15-bit value}{zeros}
+ // {zeros}{15-bit value}{zeros}
+ // {zeros}{ones}{15-bit value}
+ // {ones}{15-bit value}{zeros}
+ // We can take advantage of LI's sign-extension semantics to generate leading
+ // ones, and then use RLDIC to mask off the ones in both sides after rotation.
+ if ((LZ + FO + TZ) > 48) {
+ Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64,
+ getI32Imm((Imm >> TZ) & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDIC, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(TZ), getI32Imm(LZ));
+ }
+ // 2-3) Pattern : {zeros}{15-bit value}{ones}
+ // Shift right the Imm by (48 - LZ) bits to construct a negtive 16 bits value,
+ // therefore we can take advantage of LI's sign-extension semantics, and then
+ // mask them off after rotation.
+ //
+ // +--LZ--||-15-bit-||--TO--+ +-------------|--16-bit--+
+ // |00000001bbbbbbbbb1111111| -> |00000000000001bbbbbbbbb1|
+ // +------------------------+ +------------------------+
+ // 63 0 63 0
+ // Imm (Imm >> (48 - LZ) & 0xffff)
+ // +----sext-----|--16-bit--+ +clear-|-----------------+
+ // |11111111111111bbbbbbbbb1| -> |00000001bbbbbbbbb1111111|
+ // +------------------------+ +------------------------+
+ // 63 0 63 0
+ // LI8: sext many leading zeros RLDICL: rotate left (48 - LZ), clear left LZ
+ if ((LZ + TO) > 48) {
+ // Since the immediates with (LZ > 32) have been handled by previous
+ // patterns, here we have (LZ <= 32) to make sure we will not shift right
+ // the Imm by a negative value.
+ assert(LZ <= 32 && "Unexpected shift value.");
+ Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64,
+ getI32Imm((Imm >> (48 - LZ) & 0xffff)));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(48 - LZ), getI32Imm(LZ));
+ }
+ // 2-4) Patterns : {zeros}{ones}{15-bit value}{ones}
+ // {ones}{15-bit value}{ones}
+ // We can take advantage of LI's sign-extension semantics to generate leading
+ // ones, and then use RLDICL to mask off the ones in left sides (if required)
+ // after rotation.
+ //
+ // +-LZ-FO||-15-bit-||--TO--+ +-------------|--16-bit--+
+ // |00011110bbbbbbbbb1111111| -> |000000000011110bbbbbbbbb|
+ // +------------------------+ +------------------------+
+ // 63 0 63 0
+ // Imm (Imm >> TO) & 0xffff
+ // +----sext-----|--16-bit--+ +LZ|---------------------+
+ // |111111111111110bbbbbbbbb| -> |00011110bbbbbbbbb1111111|
+ // +------------------------+ +------------------------+
+ // 63 0 63 0
+ // LI8: sext many leading zeros RLDICL: rotate left TO, clear left LZ
+ if ((LZ + FO + TO) > 48) {
+ Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64,
+ getI32Imm((Imm >> TO) & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(TO), getI32Imm(LZ));
+ }
+ // 2-5) Pattern : {32 zeros}{****}{0}{15-bit value}
+ // If Hi32 is zero and the Lo16(in Lo32) can be presented as a positive 16 bit
+ // value, we can use LI for Lo16 without generating leading ones then add the
+ // Hi16(in Lo32).
+ if (LZ == 32 && ((Lo32 & 0x8000) == 0)) {
+ Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64,
+ getI32Imm(Lo32 & 0xffff));
+ return CurDAG->getMachineNode(PPC::ORIS8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Lo32 >> 16));
+ }
+ // 2-6) Patterns : {******}{49 zeros}{******}
+ // {******}{49 ones}{******}
+ // If the Imm contains 49 consecutive zeros/ones, it means that a total of 15
+ // bits remain on both sides. Rotate right the Imm to construct an int<16>
+ // value, use LI for int<16> value and then use RLDICL without mask to rotate
+ // it back.
+ //
+ // 1) findContiguousZerosAtLeast(Imm, 49)
+ // +------|--zeros-|------+ +---ones--||---15 bit--+
+ // |bbbbbb0000000000aaaaaa| -> |0000000000aaaaaabbbbbb|
+ // +----------------------+ +----------------------+
+ // 63 0 63 0
+ //
+ // 2) findContiguousZerosAtLeast(~Imm, 49)
+ // +------|--ones--|------+ +---ones--||---15 bit--+
+ // |bbbbbb1111111111aaaaaa| -> |1111111111aaaaaabbbbbb|
+ // +----------------------+ +----------------------+
+ // 63 0 63 0
+ if ((Shift = findContiguousZerosAtLeast(Imm, 49)) ||
+ (Shift = findContiguousZerosAtLeast(~Imm, 49))) {
+ uint64_t RotImm = (Imm >> Shift) | (Imm << (64 - Shift));
+ Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64,
+ getI32Imm(RotImm & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Shift), getI32Imm(0));
+ }
+
+ // Following patterns use 3 instructions to materialize the Imm.
+ InstCnt = 3;
+ // 3-1) Patterns : {zeros}{ones}{31-bit value}{zeros}
+ // {zeros}{31-bit value}{zeros}
+ // {zeros}{ones}{31-bit value}
+ // {ones}{31-bit value}{zeros}
+ // We can take advantage of LIS's sign-extension semantics to generate leading
+ // ones, add the remaining bits with ORI, and then use RLDIC to mask off the
+ // ones in both sides after rotation.
+ if ((LZ + FO + TZ) > 32) {
+ uint64_t ImmHi16 = (Imm >> (TZ + 16)) & 0xffff;
+ unsigned Opcode = ImmHi16 ? PPC::LIS8 : PPC::LI8;
+ Result = CurDAG->getMachineNode(Opcode, dl, MVT::i64, getI32Imm(ImmHi16));
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm((Imm >> TZ) & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDIC, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(TZ), getI32Imm(LZ));
+ }
+ // 3-2) Pattern : {zeros}{31-bit value}{ones}
+ // Shift right the Imm by (32 - LZ) bits to construct a negtive 32 bits value,
+ // therefore we can take advantage of LIS's sign-extension semantics, add
+ // the remaining bits with ORI, and then mask them off after rotation.
+ // This is similar to Pattern 2-3, please refer to the diagram there.
+ if ((LZ + TO) > 32) {
+ // Since the immediates with (LZ > 32) have been handled by previous
+ // patterns, here we have (LZ <= 32) to make sure we will not shift right
+ // the Imm by a negative value.
+ assert(LZ <= 32 && "Unexpected shift value.");
+ Result = CurDAG->getMachineNode(PPC::LIS8, dl, MVT::i64,
+ getI32Imm((Imm >> (48 - LZ)) & 0xffff));
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm((Imm >> (32 - LZ)) & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(32 - LZ), getI32Imm(LZ));
+ }
+ // 3-3) Patterns : {zeros}{ones}{31-bit value}{ones}
+ // {ones}{31-bit value}{ones}
+ // We can take advantage of LIS's sign-extension semantics to generate leading
+ // ones, add the remaining bits with ORI, and then use RLDICL to mask off the
+ // ones in left sides (if required) after rotation.
+ // This is similar to Pattern 2-4, please refer to the diagram there.
+ if ((LZ + FO + TO) > 32) {
+ Result = CurDAG->getMachineNode(PPC::LIS8, dl, MVT::i64,
+ getI32Imm((Imm >> (TO + 16)) & 0xffff));
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm((Imm >> TO) & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(TO), getI32Imm(LZ));
+ }
+ // 3-4) Patterns : High word == Low word
+ if (Hi32 == Lo32) {
+ // Handle the first 32 bits.
+ uint64_t ImmHi16 = (Lo32 >> 16) & 0xffff;
+ unsigned Opcode = ImmHi16 ? PPC::LIS8 : PPC::LI8;
+ Result = CurDAG->getMachineNode(Opcode, dl, MVT::i64, getI32Imm(ImmHi16));
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Lo32 & 0xffff));
+ // Use rldimi to insert the Low word into High word.
+ SDValue Ops[] = {SDValue(Result, 0), SDValue(Result, 0), getI32Imm(32),
+ getI32Imm(0)};
+ return CurDAG->getMachineNode(PPC::RLDIMI, dl, MVT::i64, Ops);
+ }
+ // 3-5) Patterns : {******}{33 zeros}{******}
+ // {******}{33 ones}{******}
+ // If the Imm contains 33 consecutive zeros/ones, it means that a total of 31
+ // bits remain on both sides. Rotate right the Imm to construct an int<32>
+ // value, use LIS + ORI for int<32> value and then use RLDICL without mask to
+ // rotate it back.
+ // This is similar to Pattern 2-6, please refer to the diagram there.
+ if ((Shift = findContiguousZerosAtLeast(Imm, 33)) ||
+ (Shift = findContiguousZerosAtLeast(~Imm, 33))) {
+ uint64_t RotImm = (Imm >> Shift) | (Imm << (64 - Shift));
+ uint64_t ImmHi16 = (RotImm >> 16) & 0xffff;
+ unsigned Opcode = ImmHi16 ? PPC::LIS8 : PPC::LI8;
+ Result = CurDAG->getMachineNode(Opcode, dl, MVT::i64, getI32Imm(ImmHi16));
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(RotImm & 0xffff));
+ return CurDAG->getMachineNode(PPC::RLDICL, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Shift), getI32Imm(0));
+ }
+
+ InstCnt = 0;
+ return nullptr;
+}
+
+static SDNode *selectI64Imm(SelectionDAG *CurDAG, const SDLoc &dl, uint64_t Imm,
+ unsigned *InstCnt = nullptr) {
+ unsigned InstCntDirect = 0;
+ // No more than 3 instructions is used if we can select the i64 immediate
+ // directly.
+ SDNode *Result = selectI64ImmDirect(CurDAG, dl, Imm, InstCntDirect);
+ if (Result) {
+ if (InstCnt)
+ *InstCnt = InstCntDirect;
+ return Result;
+ }
+ auto getI32Imm = [CurDAG, dl](unsigned Imm) {
+ return CurDAG->getTargetConstant(Imm, dl, MVT::i32);
+ };
+ // Handle the upper 32 bit value.
+ Result =
+ selectI64ImmDirect(CurDAG, dl, Imm & 0xffffffff00000000, InstCntDirect);
+ // Add in the last bits as required.
+ if (uint32_t Hi16 = (Lo_32(Imm) >> 16) & 0xffff) {
+ Result = CurDAG->getMachineNode(PPC::ORIS8, dl, MVT::i64,
+ SDValue(Result, 0), getI32Imm(Hi16));
+ ++InstCntDirect;
+ }
+ if (uint32_t Lo16 = Lo_32(Imm) & 0xffff) {
+ Result = CurDAG->getMachineNode(PPC::ORI8, dl, MVT::i64, SDValue(Result, 0),
+ getI32Imm(Lo16));
+ ++InstCntDirect;
+ }
+ if (InstCnt)
+ *InstCnt = InstCntDirect;
+ return Result;
+}
+
// Select a 64-bit constant.
static SDNode *selectI64Imm(SelectionDAG *CurDAG, SDNode *N) {
SDLoc dl(N);
@@ -2092,11 +2114,14 @@ class BitPermutationSelector {
unsigned NumAndInsts = (unsigned) NeedsRotate +
(unsigned) (bool) Res;
+ unsigned NumOfSelectInsts = 0;
+ selectI64Imm(CurDAG, dl, Mask, &NumOfSelectInsts);
+ assert(NumOfSelectInsts > 0 && "Failed to select an i64 constant.");
if (Use32BitInsts)
NumAndInsts += (unsigned) (ANDIMask != 0) + (unsigned) (ANDISMask != 0) +
(unsigned) (ANDIMask != 0 && ANDISMask != 0);
else
- NumAndInsts += selectI64ImmInstrCount(Mask) + /* and */ 1;
+ NumAndInsts += NumOfSelectInsts + /* and */ 1;
unsigned NumRLInsts = 0;
bool FirstBG = true;
@@ -2320,12 +2345,14 @@ class BitPermutationSelector {
Res = SDValue(CurDAG->getMachineNode(PPC::OR8, dl, MVT::i64,
ExtendToInt64(ANDIVal, dl), ANDISVal), 0);
} else {
- if (InstCnt) *InstCnt += selectI64ImmInstrCount(Mask) + /* and */ 1;
-
- SDValue MaskVal = SDValue(selectI64Imm(CurDAG, dl, Mask), 0);
- Res =
- SDValue(CurDAG->getMachineNode(PPC::AND8, dl, MVT::i64,
- ExtendToInt64(Res, dl), MaskVal), 0);
+ unsigned NumOfSelectInsts = 0;
+ SDValue MaskVal =
+ SDValue(selectI64Imm(CurDAG, dl, Mask, &NumOfSelectInsts), 0);
+ Res = SDValue(CurDAG->getMachineNode(PPC::AND8, dl, MVT::i64,
+ ExtendToInt64(Res, dl), MaskVal),
+ 0);
+ if (InstCnt)
+ *InstCnt += NumOfSelectInsts + /* and */ 1;
}
}
diff --git a/llvm/test/CodeGen/PowerPC/aix-cc-abi.ll b/llvm/test/CodeGen/PowerPC/aix-cc-abi.ll
index 0682d022c5e3..d7272fb2179b 100644
--- a/llvm/test/CodeGen/PowerPC/aix-cc-abi.ll
+++ b/llvm/test/CodeGen/PowerPC/aix-cc-abi.ll
@@ -241,7 +241,7 @@ entry:
; 64BIT: ADJCALLSTACKDOWN 112, 0, implicit-def dead $r1, implicit $r1
; 64BIT: renamable $x3 = LI8 1
-; 64BIT: renamable $x5 = RLDICR killed renamable $x3, 31, 32
+; 64BIT: renamable $x5 = RLDIC killed renamable $x3, 31, 32
; 64BIT: $x3 = LI8 1
; 64BIT: $x4 = LI8 1
; 64BIT: $x6 = LIS8 32768
diff --git a/llvm/test/CodeGen/PowerPC/arr-fp-arg-no-copy.ll b/llvm/test/CodeGen/PowerPC/arr-fp-arg-no-copy.ll
index aa6d8a7bfa73..b040de75cbe8 100644
--- a/llvm/test/CodeGen/PowerPC/arr-fp-arg-no-copy.ll
+++ b/llvm/test/CodeGen/PowerPC/arr-fp-arg-no-copy.ll
@@ -11,8 +11,8 @@ entry:
; CHECK-LABEL: @bar
; CHECK-DAG: li [[REG1:[0-9]+]], 1023
; CHECK-DAG: li [[REG2:[0-9]+]], {{1$}}
-; CHECK-DAG: sldi 3, [[REG1]], 52
-; CHECK-DAG: sldi 4, [[REG2]], 62
+; CHECK-DAG: rldic 3, [[REG1]], 52, 2
+; CHECK-DAG: rldic 4, [[REG2]], 62, 1
; CHECK: bl xxx
; CHECK: blr
}
diff --git a/llvm/test/CodeGen/PowerPC/bperm.ll b/llvm/test/CodeGen/PowerPC/bperm.ll
index 53b19620ec13..fb268b5399f6 100644
--- a/llvm/test/CodeGen/PowerPC/bperm.ll
+++ b/llvm/test/CodeGen/PowerPC/bperm.ll
@@ -47,7 +47,7 @@ entry:
; CHECK-LABEL: @test1
; CHECK-DAG: li [[REG1:[0-9]+]], 11375
; CHECK-DAG: rotldi [[REG3:[0-9]+]], 4, 56
-; CHECK-DAG: sldi [[REG2:[0-9]+]], [[REG1]], 19
+; CHECK-DAG: rldic [[REG2:[0-9]+]], [[REG1]], 19, 31
; CHECK: and 3, [[REG3]], [[REG2]]
; CHECK: blr
}
@@ -59,10 +59,10 @@ entry:
ret i64 %and
; CHECK-LABEL: @test2
-; CHECK-DAG: lis [[REG1:[0-9]+]], 474
+; CHECK-DAG: lis [[REG1:[0-9]+]], 7
; CHECK-DAG: rotldi [[REG5:[0-9]+]], 4, 58
-; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 3648
-; CHECK-DAG: sldi [[REG3:[0-9]+]], [[REG2]], 32
+; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 26681
+; CHECK-DAG: rldic [[REG3:[0-9]+]], [[REG2]], 38, 7
; CHECK-DAG: oris [[REG4:[0-9]+]], [[REG3]], 25464
; CHECK: and 3, [[REG5]], [[REG4]]
; CHECK: blr
@@ -78,7 +78,7 @@ entry:
; CHECK-DAG: lis [[REG1:[0-9]+]], 170
; CHECK-DAG: rotldi [[REG4:[0-9]+]], 3, 34
; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 22861
-; CHECK-DAG: sldi [[REG3:[0-9]+]], [[REG2]], 34
+; CHECK-DAG: rldic [[REG3:[0-9]+]], [[REG2]], 34, 6
; CHECK: and 3, [[REG4]], [[REG3]]
; CHECK: blr
}
@@ -105,7 +105,7 @@ entry:
; CHECK-DAG: lis [[REG1:[0-9]+]], 3703
; CHECK-DAG: rotldi [[REG4:[0-9]+]], 4, 12
; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 35951
-; CHECK-DAG: sldi [[REG3:[0-9]+]], [[REG2]], 19
+; CHECK-DAG: rldic [[REG3:[0-9]+]], [[REG2]], 19, 17
; CHECK: and 3, [[REG4]], [[REG3]]
; CHECK: blr
}
@@ -150,7 +150,7 @@ entry:
; CHECK-DAG: lis [[REG1:[0-9]+]], 4
; CHECK-DAG: rotldi [[REG4:[0-9]+]], 3, 63
; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 60527
-; CHECK-DAG: sldi [[REG3:[0-9]+]], [[REG2]], 19
+; CHECK-DAG: rldic [[REG3:[0-9]+]], [[REG2]], 19, 26
; CHECK: and 3, [[REG4]], [[REG3]]
; CHECK: blr
}
@@ -165,12 +165,12 @@ entry:
ret i64 %or4
; CHECK-LABEL: @test9
-; CHECK-DAG: lis [[REG1:[0-9]+]], 1440
+; CHECK-DAG: lis [[REG1:[0-9]+]], 360
; CHECK-DAG: rotldi [[REG5:[0-9]+]], 4, 62
; CHECK-DAG: rotldi [[REG6:[0-9]+]], 4, 50
-; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 4
+; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 1
; CHECK-DAG: rldimi [[REG6]], [[REG5]], 53, 0
-; CHECK-DAG: sldi [[REG3:[0-9]+]], [[REG2]], 32
+; CHECK-DAG: rldic [[REG3:[0-9]+]], [[REG2]], 34, 5
; CHECK-DAG: oris [[REG4:[0-9]+]], [[REG3]], 25464
; CHECK: and 3, [[REG6]], [[REG4]]
; CHECK: blr
@@ -190,9 +190,9 @@ entry:
; CHECK-DAG: rotldi [[REG6:[0-9]+]], 3, 25
; CHECK-DAG: rotldi [[REG7:[0-9]+]], 3, 37
; CHECK-DAG: ori [[REG2:[0-9]+]], [[REG1]], 8183
-; CHECK-DAG: ori [[REG3:[0-9]+]], [[REG1]], 50017
-; CHECK-DAG: sldi [[REG4:[0-9]+]], [[REG2]], 25
-; CHECK-DAG: sldi [[REG5:[0-9]+]], [[REG3]], 37
+; CHECK-DAG: li [[REG3:[0-9]+]], -15519
+; CHECK-DAG: rldic [[REG4:[0-9]+]], [[REG2]], 25, 22
+; CHECK-DAG: rldic [[REG5:[0-9]+]], [[REG3]], 37, 10
; CHECK-DAG: and [[REG8:[0-9]+]], [[REG6]], [[REG4]]
; CHECK-DAG: and [[REG9:[0-9]+]], [[REG7]], [[REG5]]
; CHECK: or 3, [[REG9]], [[REG8]]
diff --git a/llvm/test/CodeGen/PowerPC/combine_ext_trunc.ll b/llvm/test/CodeGen/PowerPC/combine_ext_trunc.ll
index 67768bfe51f3..d23d062024d2 100644
--- a/llvm/test/CodeGen/PowerPC/combine_ext_trunc.ll
+++ b/llvm/test/CodeGen/PowerPC/combine_ext_trunc.ll
@@ -38,10 +38,9 @@ define i32 @pattern2(i32 %x, i32 %y){
define i32 @pattern3(i1 %cond, i32 %x) {
; CHECK-LABEL: pattern3:
; CHECK: # %bb.0:
-; CHECK-NEXT: li 5, 0
+; CHECK-NEXT: li 5, -1
; CHECK-NEXT: andi. 3, 3, 1
-; CHECK-NEXT: oris 3, 5, 65535
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: rldic 3, 5, 0, 32
; CHECK-NEXT: iselgt 3, 0, 3
; CHECK-NEXT: and 3, 3, 4
; CHECK-NEXT: blr
@@ -54,10 +53,10 @@ define i32 @pattern3(i1 %cond, i32 %x) {
define i32 @pattern4(i1 %cond, i32 %x) {
; CHECK-LABEL: pattern4:
; CHECK: # %bb.0:
-; CHECK-NEXT: li 5, 0
+; CHECK-NEXT: li 5, -1
; CHECK-NEXT: andi. 3, 3, 1
-; CHECK-NEXT: oris 3, 5, 65535
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: rldic 3, 5, 0, 32
+; CHECK-NEXT: li 5, 0
; CHECK-NEXT: iselgt 3, 3, 5
; CHECK-NEXT: or 3, 4, 3
; CHECK-NEXT: blr
diff --git a/llvm/test/CodeGen/PowerPC/constants-i64.ll b/llvm/test/CodeGen/PowerPC/constants-i64.ll
index 81228a1c09f5..842e81f560ae 100644
--- a/llvm/test/CodeGen/PowerPC/constants-i64.ll
+++ b/llvm/test/CodeGen/PowerPC/constants-i64.ll
@@ -7,8 +7,8 @@ target triple = "powerpc64-unknown-linux-gnu"
define i64 @cn1() #0 {
; CHECK-LABEL: cn1:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, -1
-; CHECK-NEXT: rldicr 3, 3, 48, 63
+; CHECK-NEXT: li 3, -1
+; CHECK-NEXT: rldic 3, 3, 0, 16
; CHECK-NEXT: blr
entry:
ret i64 281474976710655
@@ -19,8 +19,8 @@ entry:
define i64 @cnb() #0 {
; CHECK-LABEL: cnb:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, -81
-; CHECK-NEXT: rldicr 3, 3, 48, 63
+; CHECK-NEXT: li 3, -81
+; CHECK-NEXT: rldic 3, 3, 0, 16
; CHECK-NEXT: blr
entry:
ret i64 281474976710575
@@ -32,7 +32,7 @@ define i64 @f2(i64 %x) #0 {
; CHECK-LABEL: f2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, -1
-; CHECK-NEXT: sldi 3, 3, 36
+; CHECK-NEXT: rldic 3, 3, 36, 0
; CHECK-NEXT: blr
entry:
ret i64 -68719476736
@@ -44,7 +44,7 @@ define i64 @f2a(i64 %x) #0 {
; CHECK-LABEL: f2a:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, -337
-; CHECK-NEXT: sldi 3, 3, 30
+; CHECK-NEXT: rldic 3, 3, 30, 0
; CHECK-NEXT: blr
entry:
ret i64 -361850994688
@@ -55,8 +55,8 @@ entry:
define i64 @f2n(i64 %x) #0 {
; CHECK-LABEL: f2n:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, -4096
-; CHECK-NEXT: rldicr 3, 3, 36, 63
+; CHECK-NEXT: li 3, -1
+; CHECK-NEXT: rldic 3, 3, 0, 28
; CHECK-NEXT: blr
entry:
ret i64 68719476735
@@ -67,8 +67,8 @@ entry:
define i64 @f3(i64 %x) #0 {
; CHECK-LABEL: f3:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, -32768
-; CHECK-NEXT: rldicr 3, 3, 33, 63
+; CHECK-NEXT: li 3, -1
+; CHECK-NEXT: rldic 3, 3, 0, 31
; CHECK-NEXT: blr
entry:
ret i64 8589934591
@@ -81,7 +81,7 @@ define i64 @cn2n() #0 {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lis 3, -5121
; CHECK-NEXT: ori 3, 3, 65534
-; CHECK-NEXT: rldicr 3, 3, 22, 63
+; CHECK-NEXT: rotldi 3, 3, 22
; CHECK-NEXT: blr
entry:
ret i64 -1407374887747585
@@ -91,9 +91,8 @@ entry:
define i64 @uint32_1() #0 {
; CHECK-LABEL: uint32_1:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, 232
-; CHECK-NEXT: ori 3, 3, 30023
-; CHECK-NEXT: sldi 3, 3, 8
+; CHECK-NEXT: li 3, 18176
+; CHECK-NEXT: oris 3, 3, 59509
; CHECK-NEXT: blr
entry:
ret i64 3900000000
@@ -103,9 +102,8 @@ entry:
define i32 @uint32_1_i32() #0 {
; CHECK-LABEL: uint32_1_i32:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, 232
-; CHECK-NEXT: ori 3, 3, 30023
-; CHECK-NEXT: sldi 3, 3, 8
+; CHECK-NEXT: li 3, 18176
+; CHECK-NEXT: oris 3, 3, 59509
; CHECK-NEXT: blr
entry:
ret i32 -394967296
@@ -115,9 +113,8 @@ entry:
define i64 @uint32_2() #0 {
; CHECK-LABEL: uint32_2:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: oris 3, 3, 65535
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -1
+; CHECK-NEXT: rldic 3, 3, 0, 32
; CHECK-NEXT: blr
entry:
ret i64 4294967295
@@ -127,9 +124,8 @@ entry:
define i32 @uint32_2_i32() #0 {
; CHECK-LABEL: uint32_2_i32:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: oris 3, 3, 65535
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -1
+; CHECK-NEXT: rldic 3, 3, 0, 32
; CHECK-NEXT: blr
entry:
ret i32 -1
@@ -140,7 +136,7 @@ define i64 @uint32_3() #0 {
; CHECK-LABEL: uint32_3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, 1
-; CHECK-NEXT: sldi 3, 3, 31
+; CHECK-NEXT: rldic 3, 3, 31, 32
; CHECK-NEXT: blr
entry:
ret i64 2147483648
@@ -150,10 +146,9 @@ entry:
define i64 @uint32_4() #0 {
; CHECK-LABEL: uint32_4:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 29
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 3752
-; CHECK-NEXT: ori 3, 3, 57376
+; CHECK-NEXT: lis 3, -6027
+; CHECK-NEXT: ori 3, 3, 18177
+; CHECK-NEXT: rldic 3, 3, 5, 27
; CHECK-NEXT: blr
entry:
ret i64 124800000032
@@ -163,10 +158,8 @@ entry:
define i64 @cn_ones_1() #0 {
; CHECK-LABEL: cn_ones_1:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 2
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 28543
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -25633
+; CHECK-NEXT: rldicl 3, 3, 18, 30
; CHECK-NEXT: blr
entry:
ret i64 10460594175
@@ -176,10 +169,9 @@ entry:
define i64 @cn_ones_2() #0 {
; CHECK-LABEL: cn_ones_2:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 2
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 28521
-; CHECK-NEXT: ori 3, 3, 32767
+; CHECK-NEXT: lis 3, -25638
+; CHECK-NEXT: ori 3, 3, 24575
+; CHECK-NEXT: rldicl 3, 3, 2, 30
; CHECK-NEXT: blr
entry:
ret i64 10459119615
@@ -190,7 +182,7 @@ define i64 @imm1() #0 {
; CHECK-LABEL: imm1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, 8465
-; CHECK-NEXT: sldi 3, 3, 28
+; CHECK-NEXT: rldic 3, 3, 28, 22
; CHECK-NEXT: blr
entry:
ret i64 2272306135040 ;0x21110000000
@@ -199,9 +191,8 @@ entry:
define i64 @imm2() #0 {
; CHECK-LABEL: imm2:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: oris 3, 3, 65535
-; CHECK-NEXT: ori 3, 3, 8465
+; CHECK-NEXT: li 3, -28536
+; CHECK-NEXT: rldicl 3, 3, 1, 32
; CHECK-NEXT: blr
entry:
ret i64 4294910225 ;0xFFFF2111
@@ -210,9 +201,8 @@ entry:
define i64 @imm3() #0 {
; CHECK-LABEL: imm3:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: oris 3, 3, 65535
-; CHECK-NEXT: ori 3, 3, 33041
+; CHECK-NEXT: li 3, -32495
+; CHECK-NEXT: rldic 3, 3, 0, 32
; CHECK-NEXT: blr
entry:
ret i64 4294934801 ;0xFFFF8111
@@ -233,7 +223,7 @@ define i64 @imm5() #0 {
; CHECK-LABEL: imm5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, 28685
-; CHECK-NEXT: rldicr 3, 3, 52, 63
+; CHECK-NEXT: rotldi 3, 3, 52
; CHECK-NEXT: blr
entry:
ret i64 58546795155816455 ;0xd0000000000007
@@ -244,7 +234,7 @@ define i64 @imm6() #0 {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lis 3, -1
; CHECK-NEXT: ori 3, 3, 28674
-; CHECK-NEXT: rldicr 3, 3, 52, 63
+; CHECK-NEXT: rotldi 3, 3, 52
; CHECK-NEXT: blr
entry:
ret i64 13510798882111479 ;0x2ffffffffffff7
@@ -253,9 +243,8 @@ entry:
define i64 @imm7() #0 {
; CHECK-LABEL: imm7:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: ori 3, 3, 61713
-; CHECK-NEXT: sldi 3, 3, 28
+; CHECK-NEXT: li 3, -3823
+; CHECK-NEXT: rldic 3, 3, 28, 20
; CHECK-NEXT: blr
entry:
ret i64 16565957296128 ;0xf1110000000
@@ -264,9 +253,8 @@ entry:
define i64 @imm8() #0 {
; CHECK-LABEL: imm8:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, 15
-; CHECK-NEXT: ori 3, 3, 57617
-; CHECK-NEXT: sldi 3, 3, 22
+; CHECK-NEXT: li 3, -7919
+; CHECK-NEXT: rldic 3, 3, 22, 22
; CHECK-NEXT: blr
entry:
ret i64 4364831817728 ;0x3f844400000
@@ -277,7 +265,7 @@ define i64 @imm9() #0 {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lis 3, -1
; CHECK-NEXT: ori 3, 3, 28674
-; CHECK-NEXT: rldicr 3, 3, 52, 63
+; CHECK-NEXT: rotldi 3, 3, 52
; CHECK-NEXT: blr
entry:
ret i64 13510798882111479 ;0x2ffffffffffff7
@@ -286,9 +274,8 @@ entry:
define i64 @imm10() #0 {
; CHECK-LABEL: imm10:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 0
-; CHECK-NEXT: ori 3, 3, 61713
-; CHECK-NEXT: sldi 3, 3, 28
+; CHECK-NEXT: li 3, -3823
+; CHECK-NEXT: rldic 3, 3, 28, 20
; CHECK-NEXT: blr
entry:
ret i64 16565957296128 ;0xf1110000000
@@ -297,9 +284,8 @@ entry:
define i64 @imm11() #0 {
; CHECK-LABEL: imm11:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, 15
-; CHECK-NEXT: ori 3, 3, 57617
-; CHECK-NEXT: sldi 3, 3, 22
+; CHECK-NEXT: li 3, -7919
+; CHECK-NEXT: rldic 3, 3, 22, 22
; CHECK-NEXT: blr
entry:
ret i64 4364831817728 ;0x3f844400000
@@ -308,10 +294,9 @@ entry:
define i64 @imm12() #0 {
; CHECK-LABEL: imm12:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 4094
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 16324
-; CHECK-NEXT: ori 3, 3, 4096
+; CHECK-NEXT: lis 3, -29
+; CHECK-NEXT: ori 3, 3, 64577
+; CHECK-NEXT: rldic 3, 3, 12, 20
; CHECK-NEXT: blr
entry:
ret i64 17584665923584 ;0xffe3fc41000
@@ -320,10 +305,8 @@ entry:
define i64 @imm13() #0 {
; CHECK-LABEL: imm13:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 19
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 56895
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -24847
+; CHECK-NEXT: rldicl 3, 3, 21, 27
; CHECK-NEXT: blr
entry:
ret i64 85333114879 ;0x13de3fffff
@@ -332,10 +315,8 @@ entry:
define i64 @imm13_2() #0 {
; CHECK-LABEL: imm13_2:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 51
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 56895
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -12424
+; CHECK-NEXT: rldicl 3, 3, 22, 26
; CHECK-NEXT: blr
entry:
ret i64 222772068351 ;0x33de3fffff
@@ -344,10 +325,8 @@ entry:
define i64 @imm14() #0 {
; CHECK-LABEL: imm14:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 254
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 4383
-; CHECK-NEXT: ori 3, 3, 65535
+; CHECK-NEXT: li 3, -3960
+; CHECK-NEXT: rldicl 3, 3, 21, 24
; CHECK-NEXT: blr
entry:
ret i64 1091209003007 ;0xfe111fffff
@@ -357,7 +336,7 @@ define i64 @imm15() #0 {
; CHECK-LABEL: imm15:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 3, -8065
-; CHECK-NEXT: sldi 3, 3, 24
+; CHECK-NEXT: rldic 3, 3, 24, 0
; CHECK-NEXT: blr
entry:
ret i64 -135308247040
@@ -366,9 +345,9 @@ entry:
define i64 @imm16() #0 {
; CHECK-LABEL: imm16:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, -16392
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: oris 3, 3, 57217
+; CHECK-NEXT: lis 3, -16392
+; CHECK-NEXT: ori 3, 3, 57217
+; CHECK-NEXT: rldic 3, 3, 16, 0
; CHECK-NEXT: blr
entry:
ret i64 -70399354142720
@@ -377,9 +356,9 @@ entry:
define i64 @imm17() #0 {
; CHECK-LABEL: imm17:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: lis 3, 158
-; CHECK-NEXT: sldi 3, 3, 32
-; CHECK-NEXT: ori 3, 3, 40689
+; CHECK-NEXT: lis 3, 20344
+; CHECK-NEXT: ori 3, 3, 32847
+; CHECK-NEXT: rotldi 3, 3, 49
; CHECK-NEXT: blr
entry:
ret i64 44473046320324337 ;0x9e000000009ef1
@@ -388,8 +367,8 @@ entry:
define i64 @imm18() #0 {
; CHECK-LABEL: imm18:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 3, 2
-; CHECK-NEXT: sldi 3, 3, 32
+; CHECK-NEXT: li 3, 1
+; CHECK-NEXT: rldic 3, 3, 33, 30
; CHECK-NEXT: oris 3, 3, 39436
; CHECK-NEXT: ori 3, 3, 61633
; CHECK-NEXT: blr
diff --git a/llvm/test/CodeGen/PowerPC/f128-fma.ll b/llvm/test/CodeGen/PowerPC/f128-fma.ll
index e26867d1d734..7f49bcc38157 100644
--- a/llvm/test/CodeGen/PowerPC/f128-fma.ll
+++ b/llvm/test/CodeGen/PowerPC/f128-fma.ll
@@ -227,7 +227,7 @@ define void @qpFnmadd(fp128* nocapture readonly %a,
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
; CHECK-P8-NEXT: std r3, 0(r28)
-; CHECK-P8-NEXT: sldi r5, r5, 63
+; CHECK-P8-NEXT: rldic r5, r5, 63, 0
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: std r4, 8(r28)
; CHECK-P8-NEXT: addi r1, r1, 64
@@ -289,7 +289,7 @@ define void @qpFnmadd_02(fp128* nocapture readonly %a,
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
; CHECK-P8-NEXT: std r3, 0(r30)
-; CHECK-P8-NEXT: sldi r5, r5, 63
+; CHECK-P8-NEXT: rldic r5, r5, 63, 0
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: std r4, 8(r30)
; CHECK-P8-NEXT: addi r1, r1, 64
@@ -474,7 +474,7 @@ define void @qpFnmsub(fp128* nocapture readonly %a,
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
; CHECK-P8-NEXT: std r3, 0(r28)
-; CHECK-P8-NEXT: sldi r5, r5, 63
+; CHECK-P8-NEXT: rldic r5, r5, 63, 0
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: std r4, 8(r28)
; CHECK-P8-NEXT: addi r1, r1, 64
@@ -536,7 +536,7 @@ define void @qpFnmsub_02(fp128* nocapture readonly %a,
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
; CHECK-P8-NEXT: std r3, 0(r30)
-; CHECK-P8-NEXT: sldi r5, r5, 63
+; CHECK-P8-NEXT: rldic r5, r5, 63, 0
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: std r4, 8(r30)
; CHECK-P8-NEXT: addi r1, r1, 64
diff --git a/llvm/test/CodeGen/PowerPC/f128-passByValue.ll b/llvm/test/CodeGen/PowerPC/f128-passByValue.ll
index ceae50431fdf..3acfc5bcf0c4 100644
--- a/llvm/test/CodeGen/PowerPC/f128-passByValue.ll
+++ b/llvm/test/CodeGen/PowerPC/f128-passByValue.ll
@@ -18,7 +18,7 @@ define fp128 @loadConstant() {
; CHECK-P8: # %bb.0: # %entry
; CHECK-P8-NEXT: lis r3, 1
; CHECK-P8-NEXT: ori r3, r3, 5
-; CHECK-P8-NEXT: sldi r4, r3, 46
+; CHECK-P8-NEXT: rldic r4, r3, 46, 1
; CHECK-P8-NEXT: li r3, 0
; CHECK-P8-NEXT: blr
entry:
@@ -47,7 +47,7 @@ define fp128 @loadConstant2(fp128 %a, fp128 %b) {
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: lis r5, 1
; CHECK-P8-NEXT: ori r5, r5, 5
-; CHECK-P8-NEXT: sldi r6, r5, 46
+; CHECK-P8-NEXT: rldic r6, r5, 46, 1
; CHECK-P8-NEXT: li r5, 0
; CHECK-P8-NEXT: bl __addkf3
; CHECK-P8-NEXT: nop
diff --git a/llvm/test/CodeGen/PowerPC/fast-isel-pcrel.ll b/llvm/test/CodeGen/PowerPC/fast-isel-pcrel.ll
index 484162d089e5..5bdbaf25fb4b 100644
--- a/llvm/test/CodeGen/PowerPC/fast-isel-pcrel.ll
+++ b/llvm/test/CodeGen/PowerPC/fast-isel-pcrel.ll
@@ -22,9 +22,9 @@ define internal void @loadFP(double* %d) #0 {
; CHECK-NEXT: paddi r3, 0, .L.str at PCREL, 1
; CHECK-NEXT: bl printf at notoc
; CHECK-NEXT: ld r4, 104(r1)
-; CHECK-NEXT: lis r3, 16403
-; CHECK-NEXT: ori r3, r3, 62914
-; CHECK-NEXT: sldi r3, r3, 32
+; CHECK-NEXT: lis r3, 8201
+; CHECK-NEXT: ori r3, r3, 64225
+; CHECK-NEXT: rldic r3, r3, 33, 1
; CHECK-NEXT: oris r3, r3, 36700
; CHECK-NEXT: ori r3, r3, 10486
; CHECK-NEXT: std r3, 0(r4)
diff --git a/llvm/test/CodeGen/PowerPC/fp-strict-f128.ll b/llvm/test/CodeGen/PowerPC/fp-strict-f128.ll
index cb40d09c31b7..ff165fd6ced6 100644
--- a/llvm/test/CodeGen/PowerPC/fp-strict-f128.ll
+++ b/llvm/test/CodeGen/PowerPC/fp-strict-f128.ll
@@ -158,7 +158,7 @@ define fp128 @fmsub_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: li r9, 1
-; CHECK-P8-NEXT: sldi r9, r9, 63
+; CHECK-P8-NEXT: rldic r9, r9, 63, 0
; CHECK-P8-NEXT: xor r8, r8, r9
; CHECK-P8-NEXT: bl fmaf128
; CHECK-P8-NEXT: nop
@@ -191,7 +191,7 @@ define fp128 @fnmadd_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
; CHECK-P8-NEXT: bl fmaf128
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r5, 1
-; CHECK-P8-NEXT: sldi r5, r5, 63
+; CHECK-P8-NEXT: rldic r5, r5, 63, 0
; CHECK-P8-NEXT: xor r4, r4, r5
; CHECK-P8-NEXT: addi r1, r1, 32
; CHECK-P8-NEXT: ld r0, 16(r1)
@@ -222,7 +222,7 @@ define fp128 @fnmsub_f128(fp128 %f0, fp128 %f1, fp128 %f2) #0 {
; CHECK-P8-NEXT: std r0, 16(r1)
; CHECK-P8-NEXT: stdu r1, -48(r1)
; CHECK-P8-NEXT: li r9, 1
-; CHECK-P8-NEXT: sldi r30, r9, 63
+; CHECK-P8-NEXT: rldic r30, r9, 63, 0
; CHECK-P8-NEXT: xor r8, r8, r30
; CHECK-P8-NEXT: bl fmaf128
; CHECK-P8-NEXT: nop
diff --git a/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll b/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
index b7aec7e6494a..41f2ab49b8dc 100644
--- a/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
+++ b/llvm/test/CodeGen/PowerPC/fp-to-int-to-fp.ll
@@ -68,7 +68,7 @@ define float @fooul(float %X) #0 {
; PPC64-NEXT: addis 3, 2, .LCPI2_0 at toc@ha
; PPC64-NEXT: li 4, 1
; PPC64-NEXT: lfs 0, .LCPI2_0 at toc@l(3)
-; PPC64-NEXT: sldi 4, 4, 63
+; PPC64-NEXT: rldic 4, 4, 63, 0
; PPC64-NEXT: fsubs 2, 1, 0
; PPC64-NEXT: fcmpu 0, 1, 0
; PPC64-NEXT: fctidz 2, 2
@@ -150,7 +150,7 @@ define double @fooudl(double %X) #0 {
; PPC64-NEXT: addis 3, 2, .LCPI3_0 at toc@ha
; PPC64-NEXT: li 4, 1
; PPC64-NEXT: lfs 0, .LCPI3_0 at toc@l(3)
-; PPC64-NEXT: sldi 4, 4, 63
+; PPC64-NEXT: rldic 4, 4, 63, 0
; PPC64-NEXT: fsub 2, 1, 0
; PPC64-NEXT: fcmpu 0, 1, 0
; PPC64-NEXT: fctidz 2, 2
@@ -161,7 +161,7 @@ define double @fooudl(double %X) #0 {
; PPC64-NEXT: ld 5, -16(1)
; PPC64-NEXT: xor 3, 3, 4
; PPC64-NEXT: li 4, 1107
-; PPC64-NEXT: sldi 4, 4, 52
+; PPC64-NEXT: rldic 4, 4, 52, 1
; PPC64-NEXT: bc 12, 0, .LBB3_1
; PPC64-NEXT: b .LBB3_2
; PPC64-NEXT: .LBB3_1: # %entry
@@ -173,7 +173,7 @@ define double @fooudl(double %X) #0 {
; PPC64-NEXT: addis 5, 2, .LCPI3_1 at toc@ha
; PPC64-NEXT: std 4, -24(1)
; PPC64-NEXT: li 4, 1075
-; PPC64-NEXT: sldi 4, 4, 52
+; PPC64-NEXT: rldic 4, 4, 52, 1
; PPC64-NEXT: or 3, 3, 4
; PPC64-NEXT: lfd 0, .LCPI3_1 at toc@l(5)
; PPC64-NEXT: std 3, -32(1)
diff --git a/llvm/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll b/llvm/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
index fa57f50cb43d..e0f54792a563 100644
--- a/llvm/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
+++ b/llvm/test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
@@ -45,7 +45,7 @@ entry:
; PPC64-DAG: stfd 2, [[OFFSET_HI:-?[0-9]+]]([[SP:[0-9]+]])
; PPC64-DAG: stfd 1, [[OFFSET_LO:-?[0-9]+]]([[SP]])
; PPC64-DAG: li [[FLIP_BIT:[0-9]+]], 1
-; PPC64-DAG: sldi [[FLIP_BIT]], [[FLIP_BIT]], 63
+; PPC64-DAG: rldic [[FLIP_BIT]], [[FLIP_BIT]], 63, 0
; PPC64-DAG: ld [[HI:[0-9]+]], [[OFFSET_LO]]([[SP]])
; PPC64-DAG: ld [[LO:[0-9]+]], [[OFFSET_HI]]([[SP]])
; PPC64-NOT: BARRIER
@@ -57,7 +57,7 @@ entry:
; PPC64-P8-DAG: mffprd [[LO:[0-9]+]], 2
; PPC64-P8-DAG: mffprd [[HI:[0-9]+]], 1
; PPC64-P8-DAG: li [[IMM1:[0-9]+]], 1
-; PPC64-P8-DAG: sldi [[FLIP_BIT:[0-9]+]], [[IMM1]], 63
+; PPC64-P8-DAG: rldic [[FLIP_BIT:[0-9]+]], [[IMM1]], 63, 0
; PPC64-P8-NOT: BARRIER
; PPC64-P8-DAG: xor 3, [[HI]], [[FLIP_BIT]]
; PPC64-P8-DAG: xor 4, [[LO]], [[FLIP_BIT]]
@@ -85,8 +85,8 @@ entry:
; PPC64-DAG: li [[HI_TMP:[0-9]+]], 16399
; PPC64-DAG: li [[LO_TMP:[0-9]+]], 3019
; PPC64-NOT: BARRIER
-; PPC64-DAG: sldi [[CST_HI:[0-9]+]], [[HI_TMP]], 48
-; PPC64-DAG: sldi [[CST_LO:[0-9]+]], [[LO_TMP]], 52
+; PPC64-DAG: rldic [[CST_HI:[0-9]+]], [[HI_TMP]], 48, 1
+; PPC64-DAG: rldic [[CST_LO:[0-9]+]], [[LO_TMP]], 52, 0
; PPC64-DAG: ld [[X_HI:[0-9]+]], [[OFFSET]](1)
; PPC64-DAG: rldicr [[NEW_HI_TMP:[0-9]+]], [[X_HI]], 0, 0
; PPC64-DAG: or 3, [[NEW_HI_TMP]], [[CST_HI]]
@@ -98,8 +98,8 @@ entry:
; PPC64-P8-DAG: li [[HI_TMP:[0-9]+]], 16399
; PPC64-P8-DAG: li [[LO_TMP:[0-9]+]], 3019
; PPC64-P8-NOT: BARRIER
-; PPC64-P8-DAG: sldi [[CST_HI:[0-9]+]], [[HI_TMP]], 48
-; PPC64-P8-DAG: sldi [[CST_LO:[0-9]+]], [[LO_TMP]], 52
+; PPC64-P8-DAG: rldic [[CST_HI:[0-9]+]], [[HI_TMP]], 48, 1
+; PPC64-P8-DAG: rldic [[CST_LO:[0-9]+]], [[LO_TMP]], 52, 0
; PPC64-P8-DAG: rldicr [[NEW_HI_TMP:[0-9]+]], [[X_HI]], 0, 0
; PPC64-P8-DAG: or 3, [[NEW_HI_TMP]], [[CST_HI]]
; PPC64-P8-DAG: xor 4, [[NEW_HI_TMP]], [[CST_LO]]
diff --git a/llvm/test/CodeGen/PowerPC/funnel-shift.ll b/llvm/test/CodeGen/PowerPC/funnel-shift.ll
index e938444e5226..9a4398b90ab4 100644
--- a/llvm/test/CodeGen/PowerPC/funnel-shift.ll
+++ b/llvm/test/CodeGen/PowerPC/funnel-shift.ll
@@ -227,10 +227,10 @@ define i37 @fshl_i37(i37 %x, i37 %y, i37 %z) {
;
; CHECK64-LABEL: fshl_i37:
; CHECK64: # %bb.0:
-; CHECK64-NEXT: lis 6, -8857
+; CHECK64-NEXT: lis 6, 28339
; CHECK64-NEXT: sldi 4, 4, 27
-; CHECK64-NEXT: ori 6, 6, 51366
-; CHECK64-NEXT: sldi 6, 6, 32
+; CHECK64-NEXT: ori 6, 6, 58451
+; CHECK64-NEXT: rldic 6, 6, 33, 0
; CHECK64-NEXT: oris 6, 6, 3542
; CHECK64-NEXT: ori 6, 6, 31883
; CHECK64-NEXT: mulhdu 6, 5, 6
@@ -540,10 +540,10 @@ define i37 @fshr_i37(i37 %x, i37 %y, i37 %z) {
;
; CHECK64-LABEL: fshr_i37:
; CHECK64: # %bb.0:
-; CHECK64-NEXT: lis 6, -8857
+; CHECK64-NEXT: lis 6, 28339
; CHECK64-NEXT: sldi 4, 4, 27
-; CHECK64-NEXT: ori 6, 6, 51366
-; CHECK64-NEXT: sldi 6, 6, 32
+; CHECK64-NEXT: ori 6, 6, 58451
+; CHECK64-NEXT: rldic 6, 6, 33, 0
; CHECK64-NEXT: oris 6, 6, 3542
; CHECK64-NEXT: ori 6, 6, 31883
; CHECK64-NEXT: mulhdu 6, 5, 6
diff --git a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
index f6efcdd7d852..aaf6a9e4cb35 100644
--- a/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
+++ b/llvm/test/CodeGen/PowerPC/memCmpUsedInZeroEqualityComparison.ll
@@ -127,14 +127,14 @@ define signext i32 @equalityFoldOneConstant(i8* %X) {
; CHECK: # %bb.0:
; CHECK-NEXT: ld 4, 0(3)
; CHECK-NEXT: li 5, 1
-; CHECK-NEXT: sldi 5, 5, 32
+; CHECK-NEXT: rldic 5, 5, 32, 31
; CHECK-NEXT: cmpld 4, 5
; CHECK-NEXT: bne 0, .LBB6_2
; CHECK-NEXT: # %bb.1: # %loadbb1
-; CHECK-NEXT: li 4, 3
+; CHECK-NEXT: lis 4, -32768
; CHECK-NEXT: ld 3, 8(3)
-; CHECK-NEXT: sldi 4, 4, 32
-; CHECK-NEXT: ori 4, 4, 2
+; CHECK-NEXT: ori 4, 4, 1
+; CHECK-NEXT: rldic 4, 4, 1, 30
; CHECK-NEXT: cmpld 3, 4
; CHECK-NEXT: li 3, 0
; CHECK-NEXT: beq 0, .LBB6_3
diff --git a/llvm/test/CodeGen/PowerPC/negctr.ll b/llvm/test/CodeGen/PowerPC/negctr.ll
index 4e6200106032..93c7daed64f6 100644
--- a/llvm/test/CodeGen/PowerPC/negctr.ll
+++ b/llvm/test/CodeGen/PowerPC/negctr.ll
@@ -15,10 +15,9 @@ for.body: ; preds = %for.body, %entry
br i1 %exitcond, label %for.end, label %for.body
; CHECK: @main
-; CHECK: li [[REG:[0-9]+]], 0
-; CHECK: oris [[REG2:[0-9]+]], [[REG]], 65535
-; CHECK: ori [[REG3:[0-9]+]], [[REG2]], 65535
-; CHECK: mtctr [[REG3]]
+; CHECK: li [[REG:[0-9]+]], -1
+; CHECK: rldic [[REG2:[0-9]+]], [[REG]], 0, 32
+; CHECK: mtctr [[REG2]]
; CHECK: bdnz
for.end: ; preds = %for.body, %entry
diff --git a/llvm/test/CodeGen/PowerPC/ori_imm32.ll b/llvm/test/CodeGen/PowerPC/ori_imm32.ll
index 3077c4e0fe35..301164f432e9 100644
--- a/llvm/test/CodeGen/PowerPC/ori_imm32.ll
+++ b/llvm/test/CodeGen/PowerPC/ori_imm32.ll
@@ -70,7 +70,7 @@ define i64 @xori_test_b(i64 %a) {
; CHECK-LABEL: xori_test_b:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 4, 1
-; CHECK-NEXT: sldi 4, 4, 32
+; CHECK-NEXT: rldic 4, 4, 32, 31
; CHECK-NEXT: xor 3, 3, 4
; CHECK-NEXT: blr
entry:
diff --git a/llvm/test/CodeGen/PowerPC/ori_imm64.ll b/llvm/test/CodeGen/PowerPC/ori_imm64.ll
index b1bb42e3f805..c48086aa3e66 100644
--- a/llvm/test/CodeGen/PowerPC/ori_imm64.ll
+++ b/llvm/test/CodeGen/PowerPC/ori_imm64.ll
@@ -37,10 +37,9 @@ entry:
define i64 @ori_test_4(i64 %a) {
; CHECK-LABEL: ori_test_4:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: li 4, 4112
-; CHECK-NEXT: sldi 4, 4, 32
-; CHECK-NEXT: oris 4, 4, 4112
-; CHECK-NEXT: ori 4, 4, 65535
+; CHECK-NEXT: lis 4, -32640
+; CHECK-NEXT: ori 4, 4, 32903
+; CHECK-NEXT: rldicl 4, 4, 13, 19
; CHECK-NEXT: or 3, 3, 4
; CHECK-NEXT: blr
entry:
@@ -53,7 +52,7 @@ define i64 @test_test_5(i64 %a, i64 %b) {
; CHECK-LABEL: test_test_5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li 5, 1
-; CHECK-NEXT: sldi 5, 5, 32
+; CHECK-NEXT: rldic 5, 5, 32, 31
; CHECK-NEXT: or 5, 3, 5
; CHECK-NEXT: add 4, 5, 4
; CHECK-NEXT: sub 3, 3, 4
diff --git a/llvm/test/CodeGen/PowerPC/pr43976.ll b/llvm/test/CodeGen/PowerPC/pr43976.ll
index 9dc1a52c567f..debf4399a678 100644
--- a/llvm/test/CodeGen/PowerPC/pr43976.ll
+++ b/llvm/test/CodeGen/PowerPC/pr43976.ll
@@ -13,7 +13,7 @@ define dso_local signext i32 @b() local_unnamed_addr #0 {
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: lfd f0, a at toc@l(r3)
; CHECK-NEXT: addis r3, r2, .LCPI0_0 at toc@ha
-; CHECK-NEXT: sldi r4, r4, 63
+; CHECK-NEXT: rldic r4, r4, 63, 0
; CHECK-NEXT: lfs f1, .LCPI0_0 at toc@l(r3)
; CHECK-NEXT: fsub f2, f0, f1
; CHECK-NEXT: fctidz f2, f2
diff --git a/llvm/test/CodeGen/PowerPC/pr45448.ll b/llvm/test/CodeGen/PowerPC/pr45448.ll
index ce6d19ed24fb..f6849f7e27b4 100644
--- a/llvm/test/CodeGen/PowerPC/pr45448.ll
+++ b/llvm/test/CodeGen/PowerPC/pr45448.ll
@@ -19,12 +19,11 @@ define hidden void @julia_tryparse_internal_45896() #0 {
; CHECK-NEXT: bc 4, 4*cr5+lt, .LBB0_7
; CHECK-NEXT: .LBB0_6: # %L1057.preheader
; CHECK-NEXT: .LBB0_7: # %L670
-; CHECK-NEXT: lis r5, 4095
+; CHECK-NEXT: li r5, -3
; CHECK-NEXT: cmpdi r3, 0
; CHECK-NEXT: sradi r4, r3, 63
-; CHECK-NEXT: ori r5, r5, 65533
+; CHECK-NEXT: rldic r5, r5, 4, 32
; CHECK-NEXT: crnot 4*cr5+gt, eq
-; CHECK-NEXT: sldi r5, r5, 4
; CHECK-NEXT: mulhdu r3, r3, r5
; CHECK-NEXT: maddld r6, r4, r5, r3
; CHECK-NEXT: cmpld r6, r3
diff --git a/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll b/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
index 67e353257dd6..0d67a7f44f37 100644
--- a/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
+++ b/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
@@ -27,106 +27,107 @@ define zeroext i32 @test1(i64 %0, i64* %1) {
; CHECK-NEXT: .cfi_offset r30, -16
; CHECK-NEXT: .cfi_offset r31, -8
; CHECK-NEXT: .cfi_offset r2, -152
-; CHECK-NEXT: lis 5, 4
+; CHECK-NEXT: lis 5, 1
; CHECK-NEXT: std 30, 704(1) # 8-byte Folded Spill
; CHECK-NEXT: std 29, 696(1) # 8-byte Folded Spill
-; CHECK-NEXT: ori 6, 5, 6292
+; CHECK-NEXT: ori 5, 5, 1573
; CHECK-NEXT: std 28, 688(1) # 8-byte Folded Spill
; CHECK-NEXT: std 27, 680(1) # 8-byte Folded Spill
; CHECK-NEXT: std 26, 672(1) # 8-byte Folded Spill
-; CHECK-NEXT: std 25, 664(1) # 8-byte Folded Spill
-; CHECK-NEXT: ori 5, 5, 6291
; CHECK-NEXT: std 14, 576(1) # 8-byte Folded Spill
+; CHECK-NEXT: rldic 5, 5, 34, 13
; CHECK-NEXT: std 15, 584(1) # 8-byte Folded Spill
; CHECK-NEXT: std 16, 592(1) # 8-byte Folded Spill
; CHECK-NEXT: std 17, 600(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 6, 5, 13030
+; CHECK-NEXT: oris 7, 5, 13066
+; CHECK-NEXT: oris 8, 5, 13054
+; CHECK-NEXT: oris 9, 5, 13042
+; CHECK-NEXT: oris 10, 5, 13078
+; CHECK-NEXT: oris 11, 5, 13115
+; CHECK-NEXT: oris 12, 5, 13103
+; CHECK-NEXT: oris 0, 5, 13091
+; CHECK-NEXT: oris 30, 5, 13127
+; CHECK-NEXT: oris 29, 5, 13164
+; CHECK-NEXT: oris 28, 5, 13152
+; CHECK-NEXT: oris 27, 5, 13139
+; CHECK-NEXT: oris 26, 5, 13176
+; CHECK-NEXT: ori 6, 6, 3704
+; CHECK-NEXT: ori 7, 7, 44408
+; CHECK-NEXT: ori 8, 8, 30840
+; CHECK-NEXT: ori 9, 9, 17272
+; CHECK-NEXT: ori 10, 10, 57976
+; CHECK-NEXT: ori 11, 11, 33144
+; CHECK-NEXT: ori 12, 12, 19576
+; CHECK-NEXT: ori 0, 0, 6008
+; CHECK-NEXT: ori 30, 30, 46712
+; CHECK-NEXT: ori 29, 29, 21880
+; CHECK-NEXT: ori 28, 28, 8312
+; CHECK-NEXT: ori 27, 27, 60280
+; CHECK-NEXT: ori 26, 26, 35448
; CHECK-NEXT: std 18, 608(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 6
; CHECK-NEXT: std 19, 616(1) # 8-byte Folded Spill
; CHECK-NEXT: std 20, 624(1) # 8-byte Folded Spill
; CHECK-NEXT: std 21, 632(1) # 8-byte Folded Spill
; CHECK-NEXT: std 22, 640(1) # 8-byte Folded Spill
; CHECK-NEXT: std 23, 648(1) # 8-byte Folded Spill
; CHECK-NEXT: std 24, 656(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 25, 664(1) # 8-byte Folded Spill
; CHECK-NEXT: std 31, 712(1) # 8-byte Folded Spill
; CHECK-NEXT: std 2, 568(1) # 8-byte Folded Spill
-; CHECK-NEXT: sldi 6, 6, 32
-; CHECK-NEXT: oris 7, 6, 13030
-; CHECK-NEXT: oris 8, 6, 13066
-; CHECK-NEXT: oris 9, 6, 13054
-; CHECK-NEXT: oris 10, 6, 13042
-; CHECK-NEXT: oris 11, 6, 13078
-; CHECK-NEXT: oris 12, 6, 13115
-; CHECK-NEXT: oris 0, 6, 13103
-; CHECK-NEXT: oris 30, 6, 13091
-; CHECK-NEXT: oris 29, 6, 13127
-; CHECK-NEXT: oris 28, 6, 13164
-; CHECK-NEXT: oris 27, 6, 13152
-; CHECK-NEXT: oris 26, 6, 13139
-; CHECK-NEXT: oris 25, 6, 13176
-; CHECK-NEXT: ori 7, 7, 3704
-; CHECK-NEXT: ori 8, 8, 44408
-; CHECK-NEXT: ori 9, 9, 30840
-; CHECK-NEXT: ori 10, 10, 17272
-; CHECK-NEXT: ori 11, 11, 57976
-; CHECK-NEXT: ori 12, 12, 33144
-; CHECK-NEXT: ori 0, 0, 19576
-; CHECK-NEXT: ori 30, 30, 6008
-; CHECK-NEXT: ori 29, 29, 46712
-; CHECK-NEXT: ori 28, 28, 21880
-; CHECK-NEXT: ori 27, 27, 8312
-; CHECK-NEXT: ori 26, 26, 60280
-; CHECK-NEXT: ori 25, 25, 35448
-; CHECK-NEXT: add 7, 4, 7
-; CHECK-NEXT: sldi 5, 5, 32
-; CHECK-NEXT: oris 5, 5, 29347
-; CHECK-NEXT: ori 5, 5, 20088
-; CHECK-NEXT: std 7, 384(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 8
+; CHECK-NEXT: std 6, 384(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 7
+; CHECK-NEXT: lis 7, 354
+; CHECK-NEXT: std 6, 376(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 8
; CHECK-NEXT: lis 8, 402
-; CHECK-NEXT: std 7, 376(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 9
+; CHECK-NEXT: std 6, 368(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 9
; CHECK-NEXT: lis 9, 451
-; CHECK-NEXT: std 7, 368(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 10
+; CHECK-NEXT: std 6, 360(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 10
; CHECK-NEXT: lis 10, 500
-; CHECK-NEXT: std 7, 360(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 11
+; CHECK-NEXT: std 6, 352(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 11
; CHECK-NEXT: lis 11, 549
-; CHECK-NEXT: std 7, 352(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 12
-; CHECK-NEXT: std 7, 344(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 0
-; CHECK-NEXT: std 7, 336(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 30
-; CHECK-NEXT: std 7, 328(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 29
-; CHECK-NEXT: std 7, 320(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 28
-; CHECK-NEXT: std 7, 312(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 27
-; CHECK-NEXT: std 7, 304(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 26
-; CHECK-NEXT: std 7, 296(1) # 8-byte Folded Spill
-; CHECK-NEXT: add 7, 4, 25
-; CHECK-NEXT: std 7, 288(1) # 8-byte Folded Spill
-; CHECK-NEXT: oris 7, 6, 13213
-; CHECK-NEXT: ori 7, 7, 10616
-; CHECK-NEXT: add 7, 4, 7
-; CHECK-NEXT: std 7, 280(1) # 8-byte Folded Spill
-; CHECK-NEXT: oris 7, 6, 13200
-; CHECK-NEXT: oris 6, 6, 13188
-; CHECK-NEXT: ori 7, 7, 62584
-; CHECK-NEXT: ori 6, 6, 49016
-; CHECK-NEXT: add 7, 4, 7
+; CHECK-NEXT: std 6, 344(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 12
+; CHECK-NEXT: std 6, 336(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 0
+; CHECK-NEXT: std 6, 328(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 30
+; CHECK-NEXT: std 6, 320(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 29
+; CHECK-NEXT: std 6, 312(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 28
+; CHECK-NEXT: std 6, 304(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 27
+; CHECK-NEXT: std 6, 296(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 6, 4, 26
+; CHECK-NEXT: std 6, 288(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 6, 5, 13213
+; CHECK-NEXT: ori 6, 6, 10616
; CHECK-NEXT: add 6, 4, 6
+; CHECK-NEXT: std 6, 280(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 6, 5, 13200
+; CHECK-NEXT: oris 5, 5, 13188
+; CHECK-NEXT: ori 5, 5, 49016
+; CHECK-NEXT: ori 6, 6, 62584
+; CHECK-NEXT: add 5, 4, 5
+; CHECK-NEXT: add 6, 4, 6
+; CHECK-NEXT: std 5, 264(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 5, 4
+; CHECK-NEXT: std 6, 272(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 6, 305
+; CHECK-NEXT: ori 5, 5, 6291
+; CHECK-NEXT: rldic 5, 5, 32, 13
+; CHECK-NEXT: oris 5, 5, 29347
+; CHECK-NEXT: ori 5, 5, 20088
; CHECK-NEXT: add 4, 4, 5
; CHECK-NEXT: lis 5, 268
; CHECK-NEXT: std 4, 256(1) # 8-byte Folded Spill
; CHECK-NEXT: lis 4, 585
-; CHECK-NEXT: std 6, 264(1) # 8-byte Folded Spill
-; CHECK-NEXT: lis 6, 305
-; CHECK-NEXT: std 7, 272(1) # 8-byte Folded Spill
-; CHECK-NEXT: lis 7, 354
; CHECK-NEXT: ori 4, 4, 61440
; CHECK-NEXT: std 4, 560(1) # 8-byte Folded Spill
; CHECK-NEXT: lis 4, 48
diff --git a/llvm/test/CodeGen/PowerPC/sms-grp-order.ll b/llvm/test/CodeGen/PowerPC/sms-grp-order.ll
index 5525a1975a7b..ce322ebb94f7 100644
--- a/llvm/test/CodeGen/PowerPC/sms-grp-order.ll
+++ b/llvm/test/CodeGen/PowerPC/sms-grp-order.ll
@@ -4,24 +4,24 @@
define void @lame_encode_buffer_interleaved() local_unnamed_addr {
; CHECK-LABEL: lame_encode_buffer_interleaved:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lha 3, 0(3)
-; CHECK-NEXT: li 5, 1
-; CHECK-NEXT: lhz 4, 0(0)
-; CHECK-NEXT: sldi 5, 5, 62
-; CHECK-NEXT: mtctr 5
-; CHECK-NEXT: srawi 3, 3, 1
-; CHECK-NEXT: addze 3, 3
-; CHECK-NEXT: .p2align 4
-; CHECK-NEXT: .LBB0_1:
-; CHECK-NEXT: extsh 4, 4
-; CHECK-NEXT: srawi 4, 4, 1
-; CHECK-NEXT: addze 4, 4
-; CHECK-NEXT: bdnz .LBB0_1
-; CHECK-NEXT: # %bb.2:
-; CHECK-NEXT: sth 4, 0(0)
-; CHECK-NEXT: sth 3, 0(3)
-; CHECK-NEXT: blr
+; CHECK: # %bb.0:
+; CHECK-NEXT: lha 3, 0(3)
+; CHECK-NEXT: li 5, 1
+; CHECK-NEXT: lhz 4, 0(0)
+; CHECK-NEXT: rldic 5, 5, 62, 1
+; CHECK-NEXT: mtctr 5
+; CHECK-NEXT: srawi 3, 3, 1
+; CHECK-NEXT: addze 3, 3
+; CHECK-NEXT: .p2align 4
+; CHECK-NEXT: .LBB0_1:
+; CHECK-NEXT: extsh 4, 4
+; CHECK-NEXT: srawi 4, 4, 1
+; CHECK-NEXT: addze 4, 4
+; CHECK-NEXT: bdnz .LBB0_1
+; CHECK-NEXT: # %bb.2:
+; CHECK-NEXT: sth 4, 0(0)
+; CHECK-NEXT: sth 3, 0(3)
+; CHECK-NEXT: blr
br label %1
1: ; preds = %1, %0
diff --git a/llvm/test/CodeGen/PowerPC/srem-vector-lkk.ll b/llvm/test/CodeGen/PowerPC/srem-vector-lkk.ll
index e2808a4ae141..01bc5bd552f2 100644
--- a/llvm/test/CodeGen/PowerPC/srem-vector-lkk.ll
+++ b/llvm/test/CodeGen/PowerPC/srem-vector-lkk.ll
@@ -1289,20 +1289,20 @@ define <4 x i16> @dont_fold_urem_i16_smax(<4 x i16> %x) {
define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
; P9LE-LABEL: dont_fold_srem_i64:
; P9LE: # %bb.0:
-; P9LE-NEXT: lis r4, 24749
+; P9LE-NEXT: lis r4, 12374
; P9LE-NEXT: mfvsrd r3, v3
-; P9LE-NEXT: ori r4, r4, 47142
-; P9LE-NEXT: sldi r4, r4, 32
+; P9LE-NEXT: ori r4, r4, 56339
+; P9LE-NEXT: rldic r4, r4, 33, 1
; P9LE-NEXT: oris r4, r4, 58853
; P9LE-NEXT: ori r4, r4, 6055
; P9LE-NEXT: mulhd r4, r3, r4
; P9LE-NEXT: rldicl r5, r4, 1, 63
; P9LE-NEXT: sradi r4, r4, 11
; P9LE-NEXT: add r4, r4, r5
-; P9LE-NEXT: lis r5, -19946
+; P9LE-NEXT: lis r5, 5698
; P9LE-NEXT: mulli r4, r4, 5423
-; P9LE-NEXT: ori r5, r5, 17096
-; P9LE-NEXT: sldi r5, r5, 32
+; P9LE-NEXT: ori r5, r5, 51289
+; P9LE-NEXT: rldic r5, r5, 35, 0
; P9LE-NEXT: oris r5, r5, 22795
; P9LE-NEXT: sub r3, r3, r4
; P9LE-NEXT: mfvsrld r4, v3
@@ -1315,10 +1315,10 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
; P9LE-NEXT: mulli r5, r5, 23
; P9LE-NEXT: sub r4, r4, r5
; P9LE-NEXT: mtvsrdd v3, r3, r4
-; P9LE-NEXT: lis r4, 25653
+; P9LE-NEXT: lis r4, 3206
; P9LE-NEXT: mfvsrd r3, v2
-; P9LE-NEXT: ori r4, r4, 15432
-; P9LE-NEXT: sldi r4, r4, 32
+; P9LE-NEXT: ori r4, r4, 42889
+; P9LE-NEXT: rldic r4, r4, 35, 1
; P9LE-NEXT: oris r4, r4, 1603
; P9LE-NEXT: ori r4, r4, 21445
; P9LE-NEXT: mulhd r4, r3, r4
@@ -1333,20 +1333,20 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
;
; P9BE-LABEL: dont_fold_srem_i64:
; P9BE: # %bb.0:
-; P9BE-NEXT: lis r4, 24749
+; P9BE-NEXT: lis r4, 12374
; P9BE-NEXT: mfvsrld r3, v3
-; P9BE-NEXT: ori r4, r4, 47142
-; P9BE-NEXT: sldi r4, r4, 32
+; P9BE-NEXT: ori r4, r4, 56339
+; P9BE-NEXT: rldic r4, r4, 33, 1
; P9BE-NEXT: oris r4, r4, 58853
; P9BE-NEXT: ori r4, r4, 6055
; P9BE-NEXT: mulhd r4, r3, r4
; P9BE-NEXT: rldicl r5, r4, 1, 63
; P9BE-NEXT: sradi r4, r4, 11
; P9BE-NEXT: add r4, r4, r5
-; P9BE-NEXT: lis r5, -19946
-; P9BE-NEXT: ori r5, r5, 17096
+; P9BE-NEXT: lis r5, 5698
+; P9BE-NEXT: ori r5, r5, 51289
; P9BE-NEXT: mulli r4, r4, 5423
-; P9BE-NEXT: sldi r5, r5, 32
+; P9BE-NEXT: rldic r5, r5, 35, 0
; P9BE-NEXT: oris r5, r5, 22795
; P9BE-NEXT: sub r3, r3, r4
; P9BE-NEXT: mfvsrd r4, v3
@@ -1359,10 +1359,10 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
; P9BE-NEXT: mulli r5, r5, 23
; P9BE-NEXT: sub r4, r4, r5
; P9BE-NEXT: mtvsrdd v3, r4, r3
-; P9BE-NEXT: lis r4, 25653
+; P9BE-NEXT: lis r4, 3206
; P9BE-NEXT: mfvsrld r3, v2
-; P9BE-NEXT: ori r4, r4, 15432
-; P9BE-NEXT: sldi r4, r4, 32
+; P9BE-NEXT: ori r4, r4, 42889
+; P9BE-NEXT: rldic r4, r4, 35, 1
; P9BE-NEXT: oris r4, r4, 1603
; P9BE-NEXT: ori r4, r4, 21445
; P9BE-NEXT: mulhd r4, r3, r4
@@ -1376,18 +1376,18 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
;
; P8LE-LABEL: dont_fold_srem_i64:
; P8LE: # %bb.0:
-; P8LE-NEXT: lis r3, 24749
-; P8LE-NEXT: lis r4, -19946
-; P8LE-NEXT: lis r5, 25653
+; P8LE-NEXT: lis r3, 12374
+; P8LE-NEXT: lis r4, 5698
+; P8LE-NEXT: lis r5, 3206
; P8LE-NEXT: xxswapd vs0, v3
; P8LE-NEXT: mfvsrd r6, v3
-; P8LE-NEXT: ori r3, r3, 47142
-; P8LE-NEXT: ori r4, r4, 17096
-; P8LE-NEXT: ori r5, r5, 15432
+; P8LE-NEXT: ori r3, r3, 56339
+; P8LE-NEXT: ori r4, r4, 51289
+; P8LE-NEXT: ori r5, r5, 42889
; P8LE-NEXT: mfvsrd r7, v2
-; P8LE-NEXT: sldi r3, r3, 32
-; P8LE-NEXT: sldi r4, r4, 32
-; P8LE-NEXT: sldi r5, r5, 32
+; P8LE-NEXT: rldic r3, r3, 33, 1
+; P8LE-NEXT: rldic r4, r4, 35, 0
+; P8LE-NEXT: rldic r5, r5, 35, 1
; P8LE-NEXT: oris r3, r3, 58853
; P8LE-NEXT: oris r4, r4, 22795
; P8LE-NEXT: mffprd r8, f0
@@ -1425,19 +1425,19 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) {
;
; P8BE-LABEL: dont_fold_srem_i64:
; P8BE: # %bb.0:
-; P8BE-NEXT: lis r4, -19946
-; P8BE-NEXT: lis r3, 24749
+; P8BE-NEXT: lis r4, 5698
+; P8BE-NEXT: lis r3, 12374
; P8BE-NEXT: xxswapd vs0, v3
-; P8BE-NEXT: lis r5, 25653
+; P8BE-NEXT: lis r5, 3206
; P8BE-NEXT: xxswapd vs1, v2
-; P8BE-NEXT: ori r4, r4, 17096
-; P8BE-NEXT: ori r3, r3, 47142
-; P8BE-NEXT: ori r5, r5, 15432
+; P8BE-NEXT: ori r4, r4, 51289
+; P8BE-NEXT: ori r3, r3, 56339
+; P8BE-NEXT: ori r5, r5, 42889
; P8BE-NEXT: mfvsrd r6, v3
-; P8BE-NEXT: sldi r4, r4, 32
-; P8BE-NEXT: sldi r3, r3, 32
+; P8BE-NEXT: rldic r4, r4, 35, 0
+; P8BE-NEXT: rldic r3, r3, 33, 1
; P8BE-NEXT: oris r4, r4, 22795
-; P8BE-NEXT: sldi r5, r5, 32
+; P8BE-NEXT: rldic r5, r5, 35, 1
; P8BE-NEXT: oris r3, r3, 58853
; P8BE-NEXT: mffprd r7, f0
; P8BE-NEXT: ori r4, r4, 8549
diff --git a/llvm/test/CodeGen/PowerPC/tailcall-speculatable-callee.ll b/llvm/test/CodeGen/PowerPC/tailcall-speculatable-callee.ll
index 9223c27d50aa..244dac534d07 100644
--- a/llvm/test/CodeGen/PowerPC/tailcall-speculatable-callee.ll
+++ b/llvm/test/CodeGen/PowerPC/tailcall-speculatable-callee.ll
@@ -68,9 +68,9 @@ define dso_local double @speculatable_callee_intermediate_instructions (double*
; CHECK-NEXT: stdu r1, -48(r1)
; CHECK-NEXT: mr r30, r3
; CHECK-NEXT: bl callee
- ; CHECK-NEXT: lis r3, 16404
- ; CHECK-NEXT: ori r3, r3, 52428
- ; CHECK-NEXT: sldi r3, r3, 32
+ ; CHECK-NEXT: lis r3, 4101
+ ; CHECK-NEXT: ori r3, r3, 13107
+ ; CHECK-NEXT: rldic r3, r3, 34, 1
; CHECK-NEXT: oris r3, r3, 52428
; CHECK-NEXT: ori r3, r3, 52429
; CHECK-NEXT: std r3, 0(r30)
diff --git a/llvm/test/CodeGen/PowerPC/unaligned-addressing-mode.ll b/llvm/test/CodeGen/PowerPC/unaligned-addressing-mode.ll
index 73ba4c93ac8a..1b91fe9d917a 100644
--- a/llvm/test/CodeGen/PowerPC/unaligned-addressing-mode.ll
+++ b/llvm/test/CodeGen/PowerPC/unaligned-addressing-mode.ll
@@ -80,15 +80,16 @@ define i64 @test_xaddrX4_loop(i8* %p) {
; CHECK-NEXT: li r5, 3
; CHECK-NEXT: mtctr r3
; CHECK-NEXT: li r3, 0
-; loop instruction number is changed from 5 to 4, so its align is changed from 5 to 4.
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB4_1: # %for.body
-; CHECK: ldu r6, 8(r4)
+; CHECK-NEXT: #
+; CHECK-NEXT: ldu r6, 8(r4)
; CHECK-NEXT: ldx r7, r4, r5
; CHECK-NEXT: maddld r3, r7, r6, r3
; CHECK-NEXT: bdnz .LBB4_1
; CHECK-NEXT: # %bb.2: # %for.end
; CHECK-NEXT: blr
+; loop instruction number is changed from 5 to 4, so its align is changed from 5 to 4.
entry:
br label %for.body
diff --git a/llvm/test/CodeGen/PowerPC/urem-vector-lkk.ll b/llvm/test/CodeGen/PowerPC/urem-vector-lkk.ll
index f889fad8df6c..b17853f6960a 100644
--- a/llvm/test/CodeGen/PowerPC/urem-vector-lkk.ll
+++ b/llvm/test/CodeGen/PowerPC/urem-vector-lkk.ll
@@ -1022,10 +1022,10 @@ define <4 x i16> @dont_fold_urem_i16_smax(<4 x i16> %x) {
define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
; P9LE-LABEL: dont_fold_urem_i64:
; P9LE: # %bb.0:
-; P9LE-NEXT: lis r4, 25644
+; P9LE-NEXT: lis r4, 1602
; P9LE-NEXT: mfvsrld r3, v3
-; P9LE-NEXT: ori r4, r4, 34192
-; P9LE-NEXT: sldi r4, r4, 32
+; P9LE-NEXT: ori r4, r4, 51289
+; P9LE-NEXT: rldic r4, r4, 36, 1
; P9LE-NEXT: oris r4, r4, 45590
; P9LE-NEXT: ori r4, r4, 17097
; P9LE-NEXT: mulhdu r4, r3, r4
@@ -1036,7 +1036,7 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
; P9LE-NEXT: rldicl r4, r4, 60, 4
; P9LE-NEXT: ori r5, r5, 28749
; P9LE-NEXT: mulli r4, r4, 23
-; P9LE-NEXT: sldi r5, r5, 32
+; P9LE-NEXT: rldic r5, r5, 32, 0
; P9LE-NEXT: oris r5, r5, 52170
; P9LE-NEXT: ori r5, r5, 12109
; P9LE-NEXT: sub r3, r3, r4
@@ -1045,11 +1045,11 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
; P9LE-NEXT: rldicl r5, r5, 52, 12
; P9LE-NEXT: mulli r5, r5, 5423
; P9LE-NEXT: sub r4, r4, r5
-; P9LE-NEXT: lis r5, 25653
-; P9LE-NEXT: ori r5, r5, 15432
+; P9LE-NEXT: lis r5, 3206
+; P9LE-NEXT: ori r5, r5, 42889
; P9LE-NEXT: mtvsrdd v3, r4, r3
; P9LE-NEXT: mfvsrd r3, v2
-; P9LE-NEXT: sldi r5, r5, 32
+; P9LE-NEXT: rldic r5, r5, 35, 1
; P9LE-NEXT: rldicl r4, r3, 63, 1
; P9LE-NEXT: oris r5, r5, 1603
; P9LE-NEXT: ori r5, r5, 21445
@@ -1063,10 +1063,10 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
;
; P9BE-LABEL: dont_fold_urem_i64:
; P9BE: # %bb.0:
-; P9BE-NEXT: lis r4, 25644
+; P9BE-NEXT: lis r4, 1602
; P9BE-NEXT: mfvsrd r3, v3
-; P9BE-NEXT: ori r4, r4, 34192
-; P9BE-NEXT: sldi r4, r4, 32
+; P9BE-NEXT: ori r4, r4, 51289
+; P9BE-NEXT: rldic r4, r4, 36, 1
; P9BE-NEXT: oris r4, r4, 45590
; P9BE-NEXT: ori r4, r4, 17097
; P9BE-NEXT: mulhdu r4, r3, r4
@@ -1077,7 +1077,7 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
; P9BE-NEXT: rldicl r4, r4, 60, 4
; P9BE-NEXT: ori r5, r5, 28749
; P9BE-NEXT: mulli r4, r4, 23
-; P9BE-NEXT: sldi r5, r5, 32
+; P9BE-NEXT: rldic r5, r5, 32, 0
; P9BE-NEXT: oris r5, r5, 52170
; P9BE-NEXT: ori r5, r5, 12109
; P9BE-NEXT: sub r3, r3, r4
@@ -1086,11 +1086,11 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
; P9BE-NEXT: rldicl r5, r5, 52, 12
; P9BE-NEXT: mulli r5, r5, 5423
; P9BE-NEXT: sub r4, r4, r5
-; P9BE-NEXT: lis r5, 25653
-; P9BE-NEXT: ori r5, r5, 15432
+; P9BE-NEXT: lis r5, 3206
+; P9BE-NEXT: ori r5, r5, 42889
; P9BE-NEXT: mtvsrdd v3, r3, r4
; P9BE-NEXT: mfvsrld r3, v2
-; P9BE-NEXT: sldi r5, r5, 32
+; P9BE-NEXT: rldic r5, r5, 35, 1
; P9BE-NEXT: rldicl r4, r3, 63, 1
; P9BE-NEXT: oris r5, r5, 1603
; P9BE-NEXT: ori r5, r5, 21445
@@ -1103,20 +1103,20 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
;
; P8LE-LABEL: dont_fold_urem_i64:
; P8LE: # %bb.0:
-; P8LE-NEXT: lis r3, 25644
+; P8LE-NEXT: lis r3, 1602
; P8LE-NEXT: xxswapd vs0, v3
; P8LE-NEXT: lis r4, -16037
-; P8LE-NEXT: lis r5, 25653
+; P8LE-NEXT: lis r5, 3206
; P8LE-NEXT: mfvsrd r6, v2
-; P8LE-NEXT: ori r3, r3, 34192
+; P8LE-NEXT: ori r3, r3, 51289
; P8LE-NEXT: ori r4, r4, 28749
-; P8LE-NEXT: ori r5, r5, 15432
+; P8LE-NEXT: ori r5, r5, 42889
; P8LE-NEXT: mfvsrd r8, v3
-; P8LE-NEXT: sldi r3, r3, 32
-; P8LE-NEXT: sldi r4, r4, 32
+; P8LE-NEXT: rldic r3, r3, 36, 1
+; P8LE-NEXT: rldic r4, r4, 32, 0
; P8LE-NEXT: oris r3, r3, 45590
; P8LE-NEXT: mffprd r7, f0
-; P8LE-NEXT: sldi r5, r5, 32
+; P8LE-NEXT: rldic r5, r5, 35, 1
; P8LE-NEXT: oris r4, r4, 52170
; P8LE-NEXT: ori r3, r3, 17097
; P8LE-NEXT: oris r5, r5, 1603
@@ -1149,19 +1149,19 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) {
;
; P8BE-LABEL: dont_fold_urem_i64:
; P8BE: # %bb.0:
-; P8BE-NEXT: lis r3, 25644
+; P8BE-NEXT: lis r3, 1602
; P8BE-NEXT: lis r4, -16037
; P8BE-NEXT: xxswapd vs0, v3
; P8BE-NEXT: xxswapd vs1, v2
-; P8BE-NEXT: lis r5, 25653
-; P8BE-NEXT: ori r3, r3, 34192
+; P8BE-NEXT: lis r5, 3206
+; P8BE-NEXT: ori r3, r3, 51289
; P8BE-NEXT: ori r4, r4, 28749
; P8BE-NEXT: mfvsrd r6, v3
-; P8BE-NEXT: ori r5, r5, 15432
-; P8BE-NEXT: sldi r3, r3, 32
-; P8BE-NEXT: sldi r4, r4, 32
+; P8BE-NEXT: ori r5, r5, 42889
+; P8BE-NEXT: rldic r3, r3, 36, 1
+; P8BE-NEXT: rldic r4, r4, 32, 0
; P8BE-NEXT: oris r3, r3, 45590
-; P8BE-NEXT: sldi r5, r5, 32
+; P8BE-NEXT: rldic r5, r5, 35, 1
; P8BE-NEXT: mffprd r7, f0
; P8BE-NEXT: oris r4, r4, 52170
; P8BE-NEXT: ori r3, r3, 17097
More information about the llvm-commits
mailing list