| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | Re-enable usage of the ARM base pointer. r113394 fixed the known failures. | Jim Grosbach | 2010-09-08 | 1 | -1/+1 | |
| | | | | | | | Re-running some nightly testers w/ it enabled to verify. llvm-svn: 113399 | |||||
| * | Fix errant fall-throughs causing the base pointer to be used when the frame | Jim Grosbach | 2010-09-08 | 1 | -3/+3 | |
| | | | | | | | pointer was intended. rdar://8401980 llvm-svn: 113394 | |||||
| * | Add intrinsic forms of mmx<->sse conversions. Notes: | Dale Johannesen | 2010-09-08 | 1 | -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. llvm-svn: 113388 | |||||
| * | Rewrite TargetMaterializeConstant. | Eric Christopher | 2010-09-08 | 1 | -7/+18 | |
| | | | | | llvm-svn: 113387 | |||||
| * | Remove dead code. | Jakob Stoklund Olesen | 2010-09-08 | 1 | -11/+0 | |
| | | | | | llvm-svn: 113386 | |||||
| * | Minor change. Fix comments and remove unused and redundant code | Bruno Cardoso Lopes | 2010-09-08 | 1 | -10/+3 | |
| | | | | | llvm-svn: 113378 | |||||
| * | ELF_STB_Local is 0 so setting and checking it must be done specially | Roman Divacky | 2010-09-08 | 2 | -3/+5 | |
| | | | | | llvm-svn: 113375 | |||||
| * | Clarify the ownership model of LLVMContext and Module. Namely, contexts own | Owen Anderson | 2010-09-08 | 4 | -0/+24 | |
| | | | | | | | | modules are instantiated in them. If the context is deleted, all of its owned modules are also deleted. llvm-svn: 113374 | |||||
| * | x86 vector shuffle lowering now relies only on target specific | Bruno Cardoso Lopes | 2010-09-08 | 2 | -6/+132 | |
| | | | | | | | | | | | | | | | | nodes to emit shuffles and don't do isel mask matching anymore. - Add the selection of the remaining shuffle opcode (movddup) - Introduce two new functions to "recognize" where we may get potential folds and add several comments to them explaining why they are not yet in the desidered shape. - Add more patterns to fallback the case where we select a specific shuffle opcode as if it could fold a load, but it can't, so remap to a valid instruction. - Add a couple of FIXMEs to address in the following days once there's a good solution to the current folding problem. llvm-svn: 113369 | |||||
| * | Be more careful about when to do dynamic stack realignment. Since we have an | Jim Grosbach | 2010-09-08 | 1 | -2/+9 | |
| | | | | | | | | option to disable base pointer usage, pay attention to it when deciding if we can realign (if no base pointer and VLAs, we can't). llvm-svn: 113366 | |||||
| * | Add missing assert | Jim Grosbach | 2010-09-08 | 1 | -1/+4 | |
| | | | | | llvm-svn: 113365 | |||||
| * | Unresolved weak symbols have value equal zero. | Roman Divacky | 2010-09-08 | 1 | -1/+1 | |
| | | | | | llvm-svn: 113358 | |||||
| * | Fix CellSPU vector shuffles, again. | Kalle Raiskila | 2010-09-08 | 1 | -7/+7 | |
| | | | | | | | Some cases of lowering to rotate were miscompiled. llvm-svn: 113355 | |||||
| * | add support for the commuted form of the test instruction, rdar://8018260. | Chris Lattner | 2010-09-08 | 1 | -0/+10 | |
| | | | | | llvm-svn: 113352 | |||||
| * | implement proper support for sysret{,l,q}, rdar://8403907 | Chris Lattner | 2010-09-08 | 3 | -2/+7 | |
| | | | | | llvm-svn: 113350 | |||||
| * | implement the iret suite of instructions properly, | Chris Lattner | 2010-09-08 | 3 | -3/+5 | |
| | | | | | | | fixing rdar://8403974 llvm-svn: 113349 | |||||
| * | add support for instruction prefixes on the same line as the instruction, | Chris Lattner | 2010-09-08 | 1 | -6/+17 | |
| | | | | | | | implementing rdar://8033482 and PR7254. llvm-svn: 113348 | |||||
| * | change the MC "ParseInstruction" interface to make it the | Chris Lattner | 2010-09-08 | 3 | -7/+9 | |
| | | | | | | | | implementation's job to check for and lex the EndOfStatement marker. llvm-svn: 113347 | |||||
| * | gas accepts xchg <mem>, <reg> as a synonym for xchg <reg>, <mem>. | Chris Lattner | 2010-09-08 | 1 | -0/+11 | |
| | | | | | | | Add this to the mc assembler, fixing PR8061 llvm-svn: 113346 | |||||
| * | ARM/Disassembler: Fix definitions incompatible(unsigned and uint32_t) to ↵ | NAKAMURA Takumi | 2010-09-08 | 1 | -2/+2 | |
| | | | | | | | Cygwin-1.5, following up to r113255. llvm-svn: 113345 | |||||
| * | fix the encoding of the "jump on *cx" family of instructions, | Chris Lattner | 2010-09-08 | 2 | -18/+22 | |
| | | | | | | | rdar://8061602 llvm-svn: 113343 | |||||
| * | remove trailing whitespace | Jim Grosbach | 2010-09-08 | 1 | -12/+12 | |
| | | | | | llvm-svn: 113338 | |||||
| * | remove obsolete comment | Jim Grosbach | 2010-09-08 | 1 | -1/+0 | |
| | | | | | llvm-svn: 113337 | |||||
| * | disable for the moment while tracking down a few Thumb2-O0 failure that look | Jim Grosbach | 2010-09-08 | 1 | -1/+1 | |
| | | | | | | | related. (attempt deux, complete w/ test update this time) llvm-svn: 113333 | |||||
| * | woops. need to update a test along with this. | Jim Grosbach | 2010-09-08 | 1 | -1/+1 | |
| | | | | | llvm-svn: 113332 | |||||
| * | disable temporarily while sorting out a few test failures in Thumb2-O0 tests. | Jim Grosbach | 2010-09-08 | 1 | -1/+1 | |
| | | | | | llvm-svn: 113331 | |||||
| * | Add a new experimental generalized dependence query interface to | Dan Gohman | 2010-09-08 | 2 | -0/+212 | |
| | | | | | | | | | AliasAnalysis, and some code for implementing the new query on top of existing implementations by making standard alias and getModRefInfo queries. llvm-svn: 113329 | |||||
| * | correct spill code to properly determine if dynamic stack realignment is | Jim Grosbach | 2010-09-08 | 1 | -2/+2 | |
| | | | | | | | | present in the function and thus whether aligned load/store instructions can be used. llvm-svn: 113323 | |||||
| * | VFP/NEON load/store multiple instructions are addrmode4, not 5. | Jim Grosbach | 2010-09-08 | 3 | -14/+14 | |
| | | | | | llvm-svn: 113322 | |||||
| * | Add a separate unrolling threshold when the current function is being ↵ | Owen Anderson | 2010-09-07 | 1 | -4/+20 | |
| | | | | | | | | | | | optimized for size. The threshold value of 50 is arbitrary, and I chose it simply by analogy to the inlining thresholds, where the baseline unrolling threshold is slightly smaller than the baseline inlining threshold. This could undoubtedly use some tuning. llvm-svn: 113306 | |||||
| * | Don't add <imp-def> operands during register rewriting. | Jakob Stoklund Olesen | 2010-09-07 | 1 | -16/+9 | |
| | | | | | | | | | | | | | | | LiveIntervals already adds <imp-def> operands for super-registers when a subreg def defines the whole register. Thus, it is not necessary to do it again when rewriting. In fact, the super-register imp-defs caused miscompilations because the late scheduler couldn't see that the super-register was read. We still add super-reg <imp-use,kill> operands when rewriting virtuals to physicals. llvm-svn: 113299 | |||||
| * | To shrink a t2LDM instruction to the 16-bit wide tLDM instruction, the base | Jim Grosbach | 2010-09-07 | 1 | -0/+12 | |
| | | | | | | | | | | | register must be one of the destination registers for the load. Otherwise, the tLDM instruction will write-back to the base register, which isn't what's desired (otherwise, we'd have a t2LDM_UPD instead). rdar://8394087 llvm-svn: 113297 | |||||
| * | grammar tweak | Jim Grosbach | 2010-09-07 | 1 | -1/+1 | |
| | | | | | llvm-svn: 113289 | |||||
| * | Factor out some x86 vector shuffle rewriting and add comments about the ↵ | Bruno Cardoso Lopes | 2010-09-07 | 1 | -29/+59 | |
| | | | | | | | direction the shuffle lowering is heading to llvm-svn: 113286 | |||||
| * | Fix PR7972, in which the PassRegistry was being leaked. As part of this, | Owen Anderson | 2010-09-07 | 1 | -35/+16 | |
| | | | | | | | | switch to using a ManagedStatic for the global PassRegistry instead of a ManagedCleanup, and fix a destruction ordering bug this exposed. llvm-svn: 113283 | |||||
| * | Move code around to prepare for moving some of the logic together to another ↵ | Bruno Cardoso Lopes | 2010-09-07 | 1 | -3/+3 | |
| | | | | | | | function llvm-svn: 113267 | |||||
| * | Add an MVT::x86mmx type. It will take the place of all current MMX vector types. | Bill Wendling | 2010-09-07 | 2 | -0/+4 | |
| | | | | | llvm-svn: 113261 | |||||
| * | Fix a serious performance regression introduced by r108687 on linux: | Chris Lattner | 2010-09-07 | 1 | -1/+6 | |
| | | | | | | | | | turning (fptrunc (sqrt (fpext x))) -> (sqrtf x) is great, but we have to delete the original sqrt as well. Not doing so causes us to do two sqrt's when building with -fmath-errno (the default on linux). llvm-svn: 113260 | |||||
| * | Remove a dead comment. | Evan Cheng | 2010-09-07 | 1 | -1/+0 | |
| | | | | | llvm-svn: 113259 | |||||
| * | hopefully fix a problem building on cygwin-1.5 | Chris Lattner | 2010-09-07 | 1 | -2/+2 | |
| | | | | | llvm-svn: 113255 | |||||
| * | Clean up some of the PassRegistry implementation, and pImpl-ize it to reduce ↵ | Owen Anderson | 2010-09-07 | 2 | -26/+66 | |
| | | | | | | | | | #include clutter and exposing internal details. llvm-svn: 113252 | |||||
| * | decouple MMX check from regular splat checks. Some refactoring is coming, ↵ | Bruno Cardoso Lopes | 2010-09-07 | 1 | -4/+8 | |
| | | | | | | | and MMX should be left alone to be easily removed after moving to intrinsics llvm-svn: 113247 | |||||
| * | Remove now useless check, because the code can be matched below, no need to ↵ | Bruno Cardoso Lopes | 2010-09-07 | 1 | -1/+1 | |
| | | | | | | | leave it for isel llvm-svn: 113242 | |||||
| * | Issue a #error if the host doesn't have an implementation for | Dan Gohman | 2010-09-07 | 1 | -0/+2 | |
| | | | | | | | GetMainExecutable yet. llvm-svn: 113240 | |||||
| * | Minor change. Since the checks are equivalent, use isMMX | Bruno Cardoso Lopes | 2010-09-07 | 1 | -1/+1 | |
| | | | | | llvm-svn: 113239 | |||||
| * | Create PTX backend. Patch by Che-Liang Chiou! | Nick Lewycky | 2010-09-07 | 13 | -0/+230 | |
| | | | | | llvm-svn: 113235 | |||||
| * | Add patterns for MMX that use the new intrinsics. | Dale Johannesen | 2010-09-07 | 2 | -16/+71 | |
| | | | | | | | | Enable palignr intrinsic. These may need adjustment for a new VT in due course. llvm-svn: 113233 | |||||
| * | Remove unused target specific node | Bruno Cardoso Lopes | 2010-09-07 | 2 | -10/+0 | |
| | | | | | llvm-svn: 113224 | |||||
| * | Don't leak the old operand when transforming "sldt" into "sldtw". | Benjamin Kramer | 2010-09-07 | 1 | -1/+3 | |
| | | | | | llvm-svn: 113200 | |||||
| * | Add completely hokey binary-and and binary-or operations to ConstantRange and | Nick Lewycky | 2010-09-07 | 2 | -0/+32 | |
| | | | | | | | teach LazyValueInfo to use them. llvm-svn: 113196 | |||||

