aboutsummaryrefslogtreecommitdiffstats
path: root/lib
Commit message (Expand)AuthorAgeFilesLines
* Promote v4i32, v8i16, v16i8 load to v2i64 load.Evan Cheng2006-04-122-57/+41
* Ensure that zero vectors are always v4i32, which forces them to CSE withChris Lattner2006-04-122-8/+13
* Vector type promotion for ISD::LOAD and ISD::SELECTEvan Cheng2006-04-121-9/+23
* Implement support for the formal_arguments node. To get this, targets should...Chris Lattner2006-04-123-3/+128
* Various SSE2 conversion intrinsicsEvan Cheng2006-04-121-39/+94
* Don't memoize vloads in the load map! Don't memoize them anywhere here, letChris Lattner2006-04-121-2/+0
* Added __builtin_ia32_storelv4si, __builtin_ia32_movqv4si,Evan Cheng2006-04-111-2/+21
* Fix SingleSource/UnitTests/Vector/sumarray-dblNate Begeman2006-04-111-4/+3
* Fix PR727, correctly handling large stack aligments on ppcNate Begeman2006-04-111-32/+28
* we have a shuffle instr, add an example.Chris Lattner2006-04-111-5/+6
* gcc lower SSE prefetch into generic prefetch intrinsic. Need to add supportEvan Cheng2006-04-111-8/+4
* Misc. intrinsics.Evan Cheng2006-04-111-13/+13
* Suppress debug label when not debug.Jim Laskey2006-04-111-1/+1
* movnt* and maskmovdqu intrinsicsEvan Cheng2006-04-112-16/+44
* Only get Tmp2 for cases where number of operands is > 1. Fixed return void.Evan Cheng2006-04-111-1/+1
* add some todosChris Lattner2006-04-111-0/+8
* Vector function results go into V2 according to GCC. The darwin ABI docChris Lattner2006-04-111-1/+10
* Add basic support for legalizing returns of vectorsChris Lattner2006-04-111-9/+36
* Move some return-handling code from lowerarguments to the ISD::RET handling s...Chris Lattner2006-04-111-20/+9
* Added support for _mm_move_ss and _mm_move_sd.Evan Cheng2006-04-113-2/+46
* Use existing information.Jim Laskey2006-04-102-10/+14
* Implement vec_shuffle.ll:test3Chris Lattner2006-04-101-2/+17
* Implement InstCombine/vec_shuffle.ll:test[12]Chris Lattner2006-04-101-0/+62
* Remove some bogus patterns; clean up.Evan Cheng2006-04-101-53/+20
* add a noteChris Lattner2006-04-101-0/+23
* Remove an entry that is now done.Evan Cheng2006-04-101-13/+0
* Added some missing shuffle patterns.Evan Cheng2006-04-101-5/+22
* Correct an entryEvan Cheng2006-04-101-2/+2
* movups / movupdEvan Cheng2006-04-101-6/+10
* Add a simple pass to make sure that all (non-library) calls to malloc and freeAndrew Lenharth2006-04-101-0/+92
* Missing breakEvan Cheng2006-04-101-0/+1
* Conditional move of vector types.Evan Cheng2006-04-102-37/+63
* New entriesEvan Cheng2006-04-101-0/+19
* Use movaps to do VR128 reg-to-reg copies for now. It's shorter and available ...Evan Cheng2006-04-101-1/+1
* properly mark vector selects as expanded to select_ccChris Lattner2006-04-081-0/+4
* Add VRRC select supportChris Lattner2006-04-083-2/+8
* Add code generator support for VSELECTChris Lattner2006-04-083-10/+22
* Disable switch lowering for targets based on the selection dag isel,Nate Begeman2006-04-085-28/+0
* Implement PowerPC/CodeGen/vec_splat.ll:spltish to use vsplish instead of aChris Lattner2006-04-081-0/+57
* Change the interface to the predicate that determines if vsplti* can be used.Chris Lattner2006-04-083-32/+28
* Initialize SDOperand values because the gcc 4.0.2 compiler complains aboutReid Spencer2006-04-081-2/+2
* Canonicalize vvector_shuffle(x,x) -> vvector_shuffle(x,undef) to enable patternsChris Lattner2006-04-082-2/+50
* Add constant replacement for insertelement/vectorshuffle constant exprsChris Lattner2006-04-081-0/+16
* Codegen shufflevector as VVECTOR_SHUFFLEChris Lattner2006-04-082-2/+25
* add a sanity check: LegalizeOp should return a value that is the same typeChris Lattner2006-04-081-0/+3
* use isValidOperands instead of duplicating checksChris Lattner2006-04-081-13/+24
* RegenerateChris Lattner2006-04-082-165/+143
* Use isValidOperands instead of duplicating or eliding checks.Chris Lattner2006-04-081-19/+8
* Use the isValidOperands helper instead of duplicating checking codeChris Lattner2006-04-081-16/+7
* Add methods to check insertelement/extractelement instructions for validity,Chris Lattner2006-04-081-6/+37