diff options
Diffstat (limited to 'lib/Target/X86/X86InstrShiftRotate.td')
| -rw-r--r-- | lib/Target/X86/X86InstrShiftRotate.td | 82 |
1 files changed, 44 insertions, 38 deletions
diff --git a/lib/Target/X86/X86InstrShiftRotate.td b/lib/Target/X86/X86InstrShiftRotate.td index e2be73532157e..0efb383e1c8d4 100644 --- a/lib/Target/X86/X86InstrShiftRotate.td +++ b/lib/Target/X86/X86InstrShiftRotate.td @@ -340,75 +340,71 @@ def SAR64m1 : RI<0xD1, MRM7m, (outs), (ins i64mem:$dst), let hasSideEffects = 0 in { let Constraints = "$src1 = $dst", SchedRW = [WriteShift] in { + +let Uses = [CL, EFLAGS] in { +def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src1), + "rcl{b}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src1), + "rcl{w}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize16; +def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src1), + "rcl{l}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize32; +def RCL64rCL : RI<0xD3, MRM2r, (outs GR64:$dst), (ins GR64:$src1), + "rcl{q}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +} // Uses = [CL, EFLAGS] + +let Uses = [EFLAGS] in { def RCL8r1 : I<0xD0, MRM2r, (outs GR8:$dst), (ins GR8:$src1), "rcl{b}\t$dst", [], IIC_SR>; def RCL8ri : Ii8<0xC0, MRM2r, (outs GR8:$dst), (ins GR8:$src1, u8imm:$cnt), "rcl{b}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>; -let Uses = [CL] in -def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src1), - "rcl{b}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; - def RCL16r1 : I<0xD1, MRM2r, (outs GR16:$dst), (ins GR16:$src1), "rcl{w}\t$dst", [], IIC_SR>, OpSize16; def RCL16ri : Ii8<0xC1, MRM2r, (outs GR16:$dst), (ins GR16:$src1, u8imm:$cnt), "rcl{w}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>, OpSize16; -let Uses = [CL] in -def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src1), - "rcl{w}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize16; - def RCL32r1 : I<0xD1, MRM2r, (outs GR32:$dst), (ins GR32:$src1), "rcl{l}\t$dst", [], IIC_SR>, OpSize32; def RCL32ri : Ii8<0xC1, MRM2r, (outs GR32:$dst), (ins GR32:$src1, u8imm:$cnt), "rcl{l}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>, OpSize32; -let Uses = [CL] in -def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src1), - "rcl{l}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize32; - - def RCL64r1 : RI<0xD1, MRM2r, (outs GR64:$dst), (ins GR64:$src1), "rcl{q}\t$dst", [], IIC_SR>; def RCL64ri : RIi8<0xC1, MRM2r, (outs GR64:$dst), (ins GR64:$src1, u8imm:$cnt), "rcl{q}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>; -let Uses = [CL] in -def RCL64rCL : RI<0xD3, MRM2r, (outs GR64:$dst), (ins GR64:$src1), - "rcl{q}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +} // Uses = [EFLAGS] +let Uses = [CL, EFLAGS] in { +def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src1), + "rcr{b}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src1), + "rcr{w}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize16; +def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src1), + "rcr{l}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize32; +def RCR64rCL : RI<0xD3, MRM3r, (outs GR64:$dst), (ins GR64:$src1), + "rcr{q}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +} // Uses = [CL, EFLAGS] +let Uses = [EFLAGS] in { def RCR8r1 : I<0xD0, MRM3r, (outs GR8:$dst), (ins GR8:$src1), "rcr{b}\t$dst", [], IIC_SR>; def RCR8ri : Ii8<0xC0, MRM3r, (outs GR8:$dst), (ins GR8:$src1, u8imm:$cnt), "rcr{b}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>; -let Uses = [CL] in -def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src1), - "rcr{b}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; - def RCR16r1 : I<0xD1, MRM3r, (outs GR16:$dst), (ins GR16:$src1), "rcr{w}\t$dst", [], IIC_SR>, OpSize16; def RCR16ri : Ii8<0xC1, MRM3r, (outs GR16:$dst), (ins GR16:$src1, u8imm:$cnt), "rcr{w}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>, OpSize16; -let Uses = [CL] in -def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src1), - "rcr{w}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize16; - def RCR32r1 : I<0xD1, MRM3r, (outs GR32:$dst), (ins GR32:$src1), "rcr{l}\t$dst", [], IIC_SR>, OpSize32; def RCR32ri : Ii8<0xC1, MRM3r, (outs GR32:$dst), (ins GR32:$src1, u8imm:$cnt), "rcr{l}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>, OpSize32; -let Uses = [CL] in -def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src1), - "rcr{l}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize32; - def RCR64r1 : RI<0xD1, MRM3r, (outs GR64:$dst), (ins GR64:$src1), "rcr{q}\t$dst", [], IIC_SR>; def RCR64ri : RIi8<0xC1, MRM3r, (outs GR64:$dst), (ins GR64:$src1, u8imm:$cnt), "rcr{q}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>; -let Uses = [CL] in -def RCR64rCL : RI<0xD3, MRM3r, (outs GR64:$dst), (ins GR64:$src1), - "rcr{q}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; +} // Uses = [EFLAGS] } // Constraints = "$src = $dst" -let SchedRW = [WriteShiftLd, WriteRMW] in { +let SchedRW = [WriteShiftLd, WriteRMW], mayStore = 1 in { +let Uses = [EFLAGS] in { def RCL8m1 : I<0xD0, MRM2m, (outs), (ins i8mem:$dst), "rcl{b}\t$dst", [], IIC_SR>; def RCL8mi : Ii8<0xC0, MRM2m, (outs), (ins i8mem:$dst, u8imm:$cnt), @@ -442,8 +438,9 @@ def RCR64m1 : RI<0xD1, MRM3m, (outs), (ins i64mem:$dst), "rcr{q}\t$dst", [], IIC_SR>; def RCR64mi : RIi8<0xC1, MRM3m, (outs), (ins i64mem:$dst, u8imm:$cnt), "rcr{q}\t{$cnt, $dst|$dst, $cnt}", [], IIC_SR>; +} // Uses = [EFLAGS] -let Uses = [CL] in { +let Uses = [CL, EFLAGS] in { def RCL8mCL : I<0xD2, MRM2m, (outs), (ins i8mem:$dst), "rcl{b}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; def RCL16mCL : I<0xD3, MRM2m, (outs), (ins i16mem:$dst), @@ -461,7 +458,7 @@ def RCR32mCL : I<0xD3, MRM3m, (outs), (ins i32mem:$dst), "rcr{l}\t{%cl, $dst|$dst, cl}", [], IIC_SR>, OpSize32; def RCR64mCL : RI<0xD3, MRM3m, (outs), (ins i64mem:$dst), "rcr{q}\t{%cl, $dst|$dst, cl}", [], IIC_SR>; -} +} // Uses = [CL, EFLAGS] } // SchedRW } // hasSideEffects = 0 @@ -665,19 +662,19 @@ def ROR64mi : RIi8<0xC1, MRM1m, (outs), (ins i64mem:$dst, u8imm:$src), // Rotate by 1 def ROR8m1 : I<0xD0, MRM1m, (outs), (ins i8mem :$dst), "ror{b}\t$dst", - [(store (rotr (loadi8 addr:$dst), (i8 1)), addr:$dst)], + [(store (rotl (loadi8 addr:$dst), (i8 7)), addr:$dst)], IIC_SR>; def ROR16m1 : I<0xD1, MRM1m, (outs), (ins i16mem:$dst), "ror{w}\t$dst", - [(store (rotr (loadi16 addr:$dst), (i8 1)), addr:$dst)], + [(store (rotl (loadi16 addr:$dst), (i8 15)), addr:$dst)], IIC_SR>, OpSize16; def ROR32m1 : I<0xD1, MRM1m, (outs), (ins i32mem:$dst), "ror{l}\t$dst", - [(store (rotr (loadi32 addr:$dst), (i8 1)), addr:$dst)], + [(store (rotl (loadi32 addr:$dst), (i8 31)), addr:$dst)], IIC_SR>, OpSize32; def ROR64m1 : RI<0xD1, MRM1m, (outs), (ins i64mem:$dst), "ror{q}\t$dst", - [(store (rotr (loadi64 addr:$dst), (i8 1)), addr:$dst)], + [(store (rotl (loadi64 addr:$dst), (i8 63)), addr:$dst)], IIC_SR>; } // SchedRW @@ -849,6 +846,15 @@ def SHRD64mri8 : RIi8<0xAC, MRMDestMem, } // Defs = [EFLAGS] +// Sandy Bridge and newer Intel processors support faster rotates using +// SHLD to avoid a partial flag update on the normal rotate instructions. +let Predicates = [HasFastSHLDRotate], AddedComplexity = 5 in { + def : Pat<(rotl GR32:$src, (i8 imm:$shamt)), + (SHLD32rri8 GR32:$src, GR32:$src, imm:$shamt)>; + def : Pat<(rotl GR64:$src, (i8 imm:$shamt)), + (SHLD64rri8 GR64:$src, GR64:$src, imm:$shamt)>; +} + def ROT32L2R_imm8 : SDNodeXForm<imm, [{ // Convert a ROTL shamt to a ROTR shamt on 32-bit integer. return getI8Imm(32 - N->getZExtValue(), SDLoc(N)); |