aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/X86/X86InstrMMX.td
Commit message (Collapse)AuthorAgeFilesLines
* X86: cvtpi2ps is just an SSE instruction with MMX operands. It has no AVX ↵Benjamin Kramer2013-06-141-7/+8
| | | | | | | | equivalent. Give it the right register format so we can also emit it when AVX is enabled. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183971 91177308-0d34-0410-b5e6-96231b3b80d8
* Reapply "Subtract isn't commutative, fix this for MMX psub." withEric Christopher2013-05-141-7/+7
| | | | | | | a somewhat randomly chosen cpu that will minimize cpu specific differences on bots. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181814 91177308-0d34-0410-b5e6-96231b3b80d8
* Temporarily revert "Subtract isn't commutative, fix this for MMX psub."Eric Christopher2013-05-141-7/+7
| | | | | | It's causing failures on the atom bot. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181812 91177308-0d34-0410-b5e6-96231b3b80d8
* Subtract isn't commutative, fix this for MMX psub.Eric Christopher2013-05-141-7/+7
| | | | | | Patch by Andrea DiBiagio. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181809 91177308-0d34-0410-b5e6-96231b3b80d8
* Annotate x87 and mmx instructions with SchedRW lists.Jakob Stoklund Olesen2013-03-261-24/+52
| | | | | | | This only covers the instructions that were given itinerary classes for the Atom model. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178050 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove IIC_DEFAULT from X86Schedule.tdJakob Stoklund Olesen2013-03-251-2/+2
| | | | | | | | All the instructions tagged with IIC_DEFAULT had nothing in common, and we already have a NoItineraries class to represent untagged instructions. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177937 91177308-0d34-0410-b5e6-96231b3b80d8
* X86 MMX: optimize transfer from mmx to i32Manman Ren2012-10-301-2/+8
| | | | | | | | | | We used to generate a store (movq) + a load. Now we use movd. rdar://9946746 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167056 91177308-0d34-0410-b5e6-96231b3b80d8
* Introduce 'UseSSEx' to force SSE legacy encodingMichael Liao2012-08-301-32/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Add 'UseSSEx' to force SSE legacy insn not being selected when AVX is enabled. As the penalty of inter-mixing SSE and AVX instructions, we need prevent SSE legacy insn from being generated except explicitly specified through some intrinsics. For patterns supported by both SSE and AVX, so far, we force AVX insn will be tried first relying on AddedComplexity or position in td file. It's error-prone and introduces bugs accidentally. 'UseSSEx' is disabled when AVX is turned on. For SSE insns inherited by AVX, we need this predicate to force VEX encoding or SSE legacy encoding only. For insns not inherited by AVX, we still use the previous predicates, i.e. 'HasSSEx'. So far, these insns fall into the following categories: * SSE insns with MMX operands * SSE insns with GPR/MEM operands only (xFENCE, PREFETCH, CLFLUSH, CRC, and etc.) * SSE4A insns. * MMX insns. * x87 insns added by SSE. 2 test cases are modified: - test/CodeGen/X86/fast-isel-x86-64.ll AVX code generation is different from SSE one. 'vcvtsi2sdq' cannot be selected by fast-isel due to complicated pattern and fast-isel fallback to materialize it from constant pool. - test/CodeGen/X86/widen_load-1.ll AVX code generation is different from SSE one after fixing SSE/AVX inter-mixing. Exec-domain fixing prefers 'vmovapd' instead of 'vmovaps'. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162919 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove the LowerMMXCONCAT_VECTORS function. It could never execute because ↵Craig Topper2012-08-131-14/+0
| | | | | | there are no legal 64-bit vector types that could be used as inputs to a 128-bit concat_vectors. Remove a target specific SDNode and its patterns that become unused as a result. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161742 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix patterns for CVTTPS2DQ to specify SSE2 instead of SSE1.Craig Topper2012-07-301-2/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160941 91177308-0d34-0410-b5e6-96231b3b80d8
* Added X86 Atom latencies to X86InstrMMX.td.Preston Gurd2012-05-111-129/+274
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156615 91177308-0d34-0410-b5e6-96231b3b80d8
* Emacs-tag and some comment fix for all ARM, CellSPU, Hexagon, MBlaze, ↵Jia Liu2012-02-181-1/+1
| | | | | | MSP430, PPC, PTX, Sparc, X86, XCore. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150878 91177308-0d34-0410-b5e6-96231b3b80d8
* Instruction scheduling itinerary for Intel Atom.Andrew Trick2012-02-011-4/+8
| | | | | | | | | | | | | | Adds an instruction itinerary to all x86 instructions, giving each a default latency of 1, using the InstrItinClass IIC_DEFAULT. Sets specific latencies for Atom for the instructions in files X86InstrCMovSetCC.td, X86InstrArithmetic.td, X86InstrControl.td, and X86InstrShiftRotate.td. The Atom latencies for the remainder of the x86 instructions will be set in subsequent patches. Adds a test to verify that the scheduler is working. Also changes the scheduling preference to "Hybrid" for i386 Atom, while leaving x86_64 as ILP. Patch by Preston Gurd! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149558 91177308-0d34-0410-b5e6-96231b3b80d8
* Instruction selection priority fixes to remove the XMM/XMMInt/orAVX ↵Craig Topper2012-01-101-20/+20
| | | | | | predicates. Another commit will remove orAVX functions from X86SubTarget. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147841 91177308-0d34-0410-b5e6-96231b3b80d8
* Don't disable MMX support when AVX is enabled. Fix predicates for MMX ↵Craig Topper2012-01-091-24/+24
| | | | | | instructions that were added along with SSE instructions to check for AVX in addition to SSE level. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@147762 91177308-0d34-0410-b5e6-96231b3b80d8
* PR9848: pandn is not commutative.Eli Friedman2011-05-051-1/+1
| | | | | | | | No test because I can't think of any way to write one that won't break quickly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130932 91177308-0d34-0410-b5e6-96231b3b80d8
* The pshufw instruction came about in MMX2 when SSE was introduced. Don't placeBill Wendling2010-10-041-3/+3
| | | | | | | | | | it in with the SSSE3 instructions. Steward! Could you place this chair by the aft sun deck? I'm trying to get away from the Astors. They are such boors! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115552 91177308-0d34-0410-b5e6-96231b3b80d8
* the immediate field of pshufw is actually an 8-bit field, not a 8-bit field ↵Chris Lattner2010-10-031-2/+2
| | | | | | that is sign extended. This fixes PR8288 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115473 91177308-0d34-0410-b5e6-96231b3b80d8
* add support for the prefetch/prefetchw instructions, move femms intoChris Lattner2010-10-031-3/+1
| | | | | | | | the right file. The assembler supports all the 3dnow instructions now, but not the "3dnowa" ones. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115468 91177308-0d34-0410-b5e6-96231b3b80d8
* stub out a header to put 3dNow! instructions into.Chris Lattner2010-10-021-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115429 91177308-0d34-0410-b5e6-96231b3b80d8
* fix a regression introduced in r115243, in which the instructionChris Lattner2010-10-021-0/+16
| | | | | | | backing int_x86_ssse3_pshuf_w got removed. This caused PR8280. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115422 91177308-0d34-0410-b5e6-96231b3b80d8
* Massive rewrite of MMX: Dale Johannesen2010-09-301-493/+69
| | | | | | | | | | | | | | | | | | | | | The x86_mmx type is used for MMX intrinsics, parameters and return values where these use MMX registers, and is also supported in load, store, and bitcast. Only the above operations generate MMX instructions, and optimizations do not operate on or produce MMX intrinsics. MMX-sized vectors <2 x i32> etc. are lowered to XMM or split into smaller pieces. Optimizations may occur on these forms and the result casted back to x86_mmx, provided the result feeds into a previous existing x86_mmx operation. The point of all this is prevent optimizations from introducing MMX operations, which is unsafe due to the EMMS problem. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115243 91177308-0d34-0410-b5e6-96231b3b80d8
* Move remaining MMX instructions from SSE to MMX.Dale Johannesen2010-09-091-62/+44
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113501 91177308-0d34-0410-b5e6-96231b3b80d8
* Move most MMX instructions (defined as anything thatDale Johannesen2010-09-091-1/+120
| | | | | | | | | uses MMX, even if it also uses other things) from InstrSSE into InstrMMX. No (intended) functional change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113462 91177308-0d34-0410-b5e6-96231b3b80d8
* Add intrinsic-based patterns for MMX PINSRW and PEXTRW.Dale Johannesen2010-09-081-0/+19
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113420 91177308-0d34-0410-b5e6-96231b3b80d8
* Slight cleanup, use only one form of MMXI_binop_rm_int.Dale Johannesen2010-09-081-53/+37
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113406 91177308-0d34-0410-b5e6-96231b3b80d8
* Add intrinsic forms of mmx<->sse conversions. Notes:Dale Johannesen2010-09-081-0/+51
| | | | | | | | | | | Omission of memory form of PI2PD is intentional; this does not use an MMX register and does not put the chip into MMX mode (PI2PS, oddly enough, does). Operands of PI2PS follow the gcc builtin, not Intel. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113388 91177308-0d34-0410-b5e6-96231b3b80d8
* Add patterns for MMX that use the new intrinsics.Dale Johannesen2010-09-071-14/+60
| | | | | | | | | Enable palignr intrinsic. These may need adjustment for a new VT in due course. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113233 91177308-0d34-0410-b5e6-96231b3b80d8
* fix the encoding of MMX_MOVFR642Qrr, it starts with 0xF2 not 0xF3,Chris Lattner2010-07-151-1/+1
| | | | | | | | | this fixes rdar://8192860. Unfortunately it can only be triggered with llc because llvm-mc matches another (correctly encoded) version of this, so no testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@108454 91177308-0d34-0410-b5e6-96231b3b80d8
* rip out even more sporadic v2f32 support.Chris Lattner2010-07-051-14/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@107610 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix an mmx movd encoding.Dan Gohman2010-05-241-4/+4
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@104552 91177308-0d34-0410-b5e6-96231b3b80d8
* Delete MMX_MOVQ64gmr. It was the same as MMX_MOVQ64mr, but it didn'tDan Gohman2010-05-201-3/+0
| | | | | | | have a pattern and it had an invalid encoding. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@104244 91177308-0d34-0410-b5e6-96231b3b80d8
* Fixed the encoding of two of the X86 movq instuctions. The Move quadword fromKevin Enderby2010-05-031-1/+1
| | | | | | | | mm to mm/m64 and the Move quadword from xmm2/mem64 to xmm1 had the incorrect encodings. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@102952 91177308-0d34-0410-b5e6-96231b3b80d8
* Add some missing x86 patterns for movdq2q. Fixes two (LLVM-)GCC DejaGNU ↵Stuart Hastings2010-04-231-0/+11
| | | | | | testcases. Radar 6881029. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@102199 91177308-0d34-0410-b5e6-96231b3b80d8
* remove a bunch of dead patterns.Chris Lattner2010-03-281-13/+0
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@99748 91177308-0d34-0410-b5e6-96231b3b80d8
* fix a few more ambiguous types.Chris Lattner2010-03-151-2/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98531 91177308-0d34-0410-b5e6-96231b3b80d8
* fix some more ambiguous patterns, remove another nontemporalstoreChris Lattner2010-03-081-4/+5
| | | | | | | pattern which is broken (source and address swapped). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97958 91177308-0d34-0410-b5e6-96231b3b80d8
* The mayHaveSideEffects flag is no longer used.Dan Gohman2010-02-271-1/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97348 91177308-0d34-0410-b5e6-96231b3b80d8
* remove a confused pattern that is trying to match an addressChris Lattner2010-02-231-7/+0
| | | | | | | then use it as an MMX register (!?). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96901 91177308-0d34-0410-b5e6-96231b3b80d8
* X86InstrInfoSSE.td declares PINSRW as having type v8i16,Chris Lattner2010-02-231-3/+5
| | | | | | | | don't alis it in the MMX .td file with a different width, split into two X86ISD opcodes. This fixes an x86 testcase. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96859 91177308-0d34-0410-b5e6-96231b3b80d8
* TableGen fragment refactoring.David Greene2010-02-091-50/+0
| | | | | | | | | | Move some utility TableGen defs, classes, etc. into a common file so they may be used my multiple pattern files. We will use this for the AVX specification to help with the transition from the current SSE specification. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95727 91177308-0d34-0410-b5e6-96231b3b80d8
* lower the last of the MRMInitReg instructions in MCInstLower.Chris Lattner2010-02-051-4/+3
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95435 91177308-0d34-0410-b5e6-96231b3b80d8
* Improved widening loads by adding support for wider loads ifMon P Wang2010-01-241-0/+14
| | | | | | | | the alignment allows. Fixed a bug where we didn't use a vector load/store for PR5626. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@94338 91177308-0d34-0410-b5e6-96231b3b80d8
* Instruction fixes, added instructions, and AsmString changes in theSean Callanan2009-12-181-19/+24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X86 instruction tables. Also (while I was at it) cleaned up the X86 tables, removing tabs and 80-line violations. This patch was reviewed by Chris Lattner, but please let me know if there are any problems. * X86*.td Removed tabs and fixed 80-line violations * X86Instr64bit.td (IRET, POPCNT, BT_, LSL, SWPGS, PUSH_S, POP_S, L_S, SMSW) Added (CALL, CMOV) Added qualifiers (JMP) Added PC-relative jump instruction (POPFQ/PUSHFQ) Added qualifiers; renamed PUSHFQ to indicate that it is 64-bit only (ambiguous since it has no REX prefix) (MOV) Added rr form going the other way, which is encoded differently (MOV) Changed immediates to offsets, which is more correct; also fixed MOV64o64a to have to a 64-bit offset (MOV) Fixed qualifiers (MOV) Added debug-register and condition-register moves (MOVZX) Added more forms (ADC, SUB, SBB, AND, OR, XOR) Added reverse forms, which (as with MOV) are encoded differently (ROL) Made REX.W required (BT) Uncommented mr form for disassembly only (CVT__2__) Added several missing non-intrinsic forms (LXADD, XCHG) Reordered operands to make more sense for MRMSrcMem (XCHG) Added register-to-register forms (XADD, CMPXCHG, XCHG) Added non-locked forms * X86InstrSSE.td (CVTSS2SI, COMISS, CVTTPS2DQ, CVTPS2PD, CVTPD2PS, MOVQ) Added * X86InstrFPStack.td (COM_FST0, COMP_FST0, COM_FI, COM_FIP, FFREE, FNCLEX, FNOP, FXAM, FLDL2T, FLDL2E, FLDPI, FLDLG2, FLDLN2, F2XM1, FYL2X, FPTAN, FPATAN, FXTRACT, FPREM1, FDECSTP, FINCSTP, FPREM, FYL2XP1, FSINCOS, FRNDINT, FSCALE, FCOMPP, FXSAVE, FXRSTOR) Added (FCOM, FCOMP) Added qualifiers (FSTENV, FSAVE, FSTSW) Fixed opcode names (FNSTSW) Added implicit register operand * X86InstrInfo.td (opaque512mem) Added for FXSAVE/FXRSTOR (offset8, offset16, offset32, offset64) Added for MOV (NOOPW, IRET, POPCNT, IN, BTC, BTR, BTS, LSL, INVLPG, STR, LTR, PUSHFS, PUSHGS, POPFS, POPGS, LDS, LSS, LES, LFS, LGS, VERR, VERW, SGDT, SIDT, SLDT, LGDT, LIDT, LLDT, LODSD, OUTSB, OUTSW, OUTSD, HLT, RSM, FNINIT, CLC, STC, CLI, STI, CLD, STD, CMC, CLTS, XLAT, WRMSR, RDMSR, RDPMC, SMSW, LMSW, CPUID, INVD, WBINVD, INVEPT, INVVPID, VMCALL, VMCLEAR, VMLAUNCH, VMRESUME, VMPTRLD, VMPTRST, VMREAD, VMWRITE, VMXOFF, VMXON) Added (NOOPL, POPF, POPFD, PUSHF, PUSHFD) Added qualifier (JO, JNO, JB, JAE, JE, JNE, JBE, JA, JS, JNS, JP, JNP, JL, JGE, JLE, JG, JCXZ) Added 32-bit forms (MOV) Changed some immediate forms to offset forms (MOV) Added reversed reg-reg forms, which are encoded differently (MOV) Added debug-register and condition-register moves (CMOV) Added qualifiers (AND, OR, XOR, ADC, SUB, SBB) Added reverse forms, like MOV (BT) Uncommented memory-register forms for disassembler (MOVSX, MOVZX) Added forms (XCHG, LXADD) Made operand order make sense for MRMSrcMem (XCHG) Added register-register forms (XADD, CMPXCHG) Added unlocked forms * X86InstrMMX.td (MMX_MOVD, MMV_MOVQ) Added forms * X86InstrInfo.cpp: Changed PUSHFQ to PUSHFQ64 to reflect table change * X86RegisterInfo.td: Added debug and condition register sets * x86-64-pic-3.ll: Fixed testcase to reflect call qualifier * peep-test-3.ll: Fixed testcase to reflect test qualifier * cmov.ll: Fixed testcase to reflect cmov qualifier * loop-blocks.ll: Fixed testcase to reflect call qualifier * x86-64-pic-11.ll: Fixed testcase to reflect call qualifier * 2009-11-04-SubregCoalescingBug.ll: Fixed testcase to reflect call qualifier * x86-64-pic-2.ll: Fixed testcase to reflect call qualifier * live-out-reg-info.ll: Fixed testcase to reflect test qualifier * tail-opts.ll: Fixed testcase to reflect call qualifiers * x86-64-pic-10.ll: Fixed testcase to reflect call qualifier * bss-pagealigned.ll: Fixed testcase to reflect call qualifier * x86-64-pic-1.ll: Fixed testcase to reflect call qualifier * widen_load-1.ll: Fixed testcase to reflect call qualifier git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91638 91177308-0d34-0410-b5e6-96231b3b80d8
* Rename usesCustomDAGSchedInserter to usesCustomInserter, and update aDan Gohman2009-10-291-4/+3
| | | | | | | | | bunch of associated comments, because it doesn't have anything to do with DAGs or scheduling. This is another step in decoupling MachineInstr emitting from scheduling. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@85517 91177308-0d34-0410-b5e6-96231b3b80d8
* Add 'isCodeGenOnly' bit to Instruction .td records.Daniel Dunbar2009-08-111-1/+1
| | | | | | | | | | | | | | | | - Used to mark fake instructions which don't correspond to an actual machine instruction (or are duplicates of a real instruction). This is to be used for "special cases" in the .td files, which should be ignored by things like the assembler and disassembler. We still need a good solution to handle pervasive duplication, like with the Int_ instructions. - Set the bit on fake "mov 0" style instructions, which allows turning an assembler matcher warning into a hard error. - -2 FIXMEs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78731 91177308-0d34-0410-b5e6-96231b3b80d8
* Whitespace, 80-column, and isTwoAddress -> Constraints = "" changes.Eric Christopher2009-08-101-32/+48
| | | | | | | No functional change. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@78608 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove neverHasSideEffects on MMX_MOVD64rrv164 since it has a matching pattern.Evan Cheng2009-08-031-2/+1
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@77978 91177308-0d34-0410-b5e6-96231b3b80d8
* Use movd instead of movqRafael Espindola2009-08-031-2/+5
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@77956 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix the instruction encoding.Rafael Espindola2009-08-031-2/+2
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@77944 91177308-0d34-0410-b5e6-96231b3b80d8