diff options
author | Evan Cheng <evan.cheng@apple.com> | 2006-04-15 05:37:34 +0000 |
---|---|---|
committer | Evan Cheng <evan.cheng@apple.com> | 2006-04-15 05:37:34 +0000 |
commit | 57ebe9fbf067422a267b5d46b0b0282e437c15c3 (patch) | |
tree | bc68148f1ec472821811051586861da54dec2acf | |
parent | 39fc1459953040a480e58142fb6adbfcc4082fe8 (diff) |
Silly bug
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27719 91177308-0d34-0410-b5e6-96231b3b80d8
-rw-r--r-- | lib/Target/X86/README.txt | 5 | ||||
-rw-r--r-- | lib/Target/X86/X86ISelLowering.cpp | 22 | ||||
-rw-r--r-- | lib/Target/X86/X86InstrSSE.td | 2 |
3 files changed, 11 insertions, 18 deletions
diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt index de768b0813..f58991728e 100644 --- a/lib/Target/X86/README.txt +++ b/lib/Target/X86/README.txt @@ -810,8 +810,3 @@ destination? How about andps, andpd, and pand? Do we really care about the type of the packed elements? If not, why not always use the "ps" variants which are likely to be shorter. - -//===---------------------------------------------------------------------===// - -Make sure XMM registers are spilled to 128-bit locations (if not already) and -add vector SSE opcodes to X86RegisterInfo::foldMemoryOperand(). diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index 409c39be5d..38e4614299 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -1724,27 +1724,26 @@ bool X86::isMOVSHDUPMask(SDNode *N) { return false; // Expect 1, 1, 3, 3 - unsigned NumNodes = 0; for (unsigned i = 0; i < 2; ++i) { SDOperand Arg = N->getOperand(i); if (Arg.getOpcode() == ISD::UNDEF) continue; assert(isa<ConstantSDNode>(Arg) && "Invalid VECTOR_SHUFFLE mask!"); unsigned Val = cast<ConstantSDNode>(Arg)->getValue(); if (Val != 1) return false; - NumNodes++; } + + bool HasHi = false; for (unsigned i = 2; i < 4; ++i) { SDOperand Arg = N->getOperand(i); if (Arg.getOpcode() == ISD::UNDEF) continue; assert(isa<ConstantSDNode>(Arg) && "Invalid VECTOR_SHUFFLE mask!"); unsigned Val = cast<ConstantSDNode>(Arg)->getValue(); if (Val != 3) return false; - NumNodes++; + HasHi = true; } - // Don't use movshdup if the resulting vector contains only one undef node. - // Use {p}shuf* instead. - return NumNodes > 1; + // Don't use movshdup if it can be done with a shufps. + return HasHi; } /// isMOVSLDUPMask - Return true if the specified VECTOR_SHUFFLE operand @@ -1756,27 +1755,26 @@ bool X86::isMOVSLDUPMask(SDNode *N) { return false; // Expect 0, 0, 2, 2 - unsigned NumNodes = 0; for (unsigned i = 0; i < 2; ++i) { SDOperand Arg = N->getOperand(i); if (Arg.getOpcode() == ISD::UNDEF) continue; assert(isa<ConstantSDNode>(Arg) && "Invalid VECTOR_SHUFFLE mask!"); unsigned Val = cast<ConstantSDNode>(Arg)->getValue(); if (Val != 0) return false; - NumNodes++; } + + bool HasHi = false; for (unsigned i = 2; i < 4; ++i) { SDOperand Arg = N->getOperand(i); if (Arg.getOpcode() == ISD::UNDEF) continue; assert(isa<ConstantSDNode>(Arg) && "Invalid VECTOR_SHUFFLE mask!"); unsigned Val = cast<ConstantSDNode>(Arg)->getValue(); if (Val != 2) return false; - NumNodes++; + HasHi = true; } - // Don't use movsldup if the resulting vector contains only one undef node. - // Use {p}shuf* instead. - return NumNodes > 1; + // Don't use movshdup if it can be done with a shufps. + return HasHi; } /// isSplatMask - Return true if the specified VECTOR_SHUFFLE operand specifies diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td index 430dfd9f86..c4e80fcf4f 100644 --- a/lib/Target/X86/X86InstrSSE.td +++ b/lib/Target/X86/X86InstrSSE.td @@ -169,7 +169,7 @@ def PSHUFD_binary_shuffle_mask : PatLeaf<(build_vector), [{ // PDIi8 - SSE2 instructions with ImmT == Imm8 and TB and OpSize prefixes. // S3I - SSE3 instructions with TB and OpSize prefixes. // S3SI - SSE3 instructions with XS prefix. -// S3SI - SSE3 instructions with XD prefix. +// S3DI - SSE3 instructions with XD prefix. class SSI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern> : I<o, F, ops, asm, pattern>, XS, Requires<[HasSSE1]>; class SDI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern> |