summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86
Commit message (Collapse)AuthorAge
...
* [DAGCombiner] Revert load slicing (r192471), until I figure out why it fails ↵Quentin Colombet2013-10-11
| | | | | | on ubuntu. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192474 91177308-0d34-0410-b5e6-96231b3b80d8
* [DAGCombiner] Slice a big load in two loads when the element are next to eachQuentin Colombet2013-10-11
| | | | | | | | | | | | | | | | | | | | | | | | | other in memory and the target has paired load and performs post-isel loads combining. E.g., this optimization will transform something like this: a = load i64* addr b = trunc i64 a to i32 c = lshr i64 a, 32 d = trunc i64 c to i32 into: b = load i32* addr1 d = load i32* addr2 Where addr1 = addr2 +/- sizeof(i32), if the target supports paired load and performs post-isel loads combining. One should overload TargetLowering::hasPairedLoad to provide this information. The default is false. <rdar://problem/14477220> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192471 91177308-0d34-0410-b5e6-96231b3b80d8
* Tests: Do not unnecessarily depend on kill commentsMatthias Braun2013-10-10
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192404 91177308-0d34-0410-b5e6-96231b3b80d8
* Disable function padding to get this test to pass on atom.Benjamin Kramer2013-10-10
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192348 91177308-0d34-0410-b5e6-96231b3b80d8
* AVX-512: Added VRCP28 and VRSQRT28 instructions and intrinsics.Elena Demikhovsky2013-10-09
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192283 91177308-0d34-0410-b5e6-96231b3b80d8
* Add in64BitMode/in32BitMode to the MMX/SSE2/AVX maskmovq/dq instructions. ↵Craig Topper2013-10-09
| | | | | | This way the asm parser will pick the right one based on the mode. Instruction selection already did the right thing based on the pointer size. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192266 91177308-0d34-0410-b5e6-96231b3b80d8
* Fix a typo in the mattr part of the run line.Craig Topper2013-10-08
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192174 91177308-0d34-0410-b5e6-96231b3b80d8
* Explicitly disable AVX on a bunch of tests so they won't fail on AVX ↵Craig Topper2013-10-08
| | | | | | machines post r192171. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192173 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove some instructions that existed to provide aliases to the assembler. ↵Craig Topper2013-10-08
| | | | | | Can be done with InstAlias instead. Unfortunately, this was causing printer to use 'vmovq' or 'vmovd' based on what was parsed. To cleanup the inconsistencies convert all 'vmovd' with 64-bit registers to 'vmovq', but provide an alias so that 'vmovd' will still parse. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192171 91177308-0d34-0410-b5e6-96231b3b80d8
* X86: Fix type check. Just because an integer type is illegal doesn't mean ↵Benjamin Kramer2013-10-07
| | | | | | | | | it's i64. Fixes PR17495, where an i24 triggered this code. It's intended to optimize i64 loads on 32 bit x86. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192123 91177308-0d34-0410-b5e6-96231b3b80d8
* Change objectsize intrinsic to accept different address spaces.Matt Arsenault2013-10-07
| | | | | | | Bitcasting everything to i8* won't work. Autoupgrade the old intrinsic declarations to use the new mangling. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192117 91177308-0d34-0410-b5e6-96231b3b80d8
* Add support for aliases with linkonce_odr.Rafael Espindola2013-10-06
| | | | | | This will be used to extend constructor aliases in clang. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192066 91177308-0d34-0410-b5e6-96231b3b80d8
* Force a CPU that doesn't have AVX, otherwise this test fails.Benjamin Kramer2013-10-06
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192065 91177308-0d34-0410-b5e6-96231b3b80d8
* X86: Don't fold spills into SSE operations if the stack is unaligned.Benjamin Kramer2013-10-06
| | | | | | | Regalloc can emit unaligned spills nowadays, but we can't fold the spills into SSE ops if we can't guarantee alignment. PR12250. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192064 91177308-0d34-0410-b5e6-96231b3b80d8
* AVX-512: added scalar convert instructions and intrinsics.Elena Demikhovsky2013-10-06
| | | | | | | Fixed load folding in VPERM2I instruction. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192063 91177308-0d34-0410-b5e6-96231b3b80d8
* AVX-512: fixed shuffle loweringElena Demikhovsky2013-10-06
| | | | | | | in case of BLEND and added VSHUFPS patterns. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192055 91177308-0d34-0410-b5e6-96231b3b80d8
* Emit a better error when running out of registers on inline asm.Benjamin Kramer2013-10-05
| | | | | | | | | The most likely case where this error happens is when the user specifies too many register operands. Don't make it look like an internal LLVM bug when we can see that the error is coming from an inline asm instruction. For other instructions we keep the "ran out of registers" error. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192041 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove unneeded TBM intrinsics. The arithmetic/logical operation patterns ↵Craig Topper2013-10-05
| | | | | | are sufficient. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192039 91177308-0d34-0410-b5e6-96231b3b80d8
* Add an additional pattern for BLCI since opt can turn (not (add x, 1)) into ↵Craig Topper2013-10-05
| | | | | | (sub -2, x). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192037 91177308-0d34-0410-b5e6-96231b3b80d8
* Convert test to FileCheck.Rafael Espindola2013-10-05
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192025 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove duplicated test cases that occurred when I applied the same patch ↵Craig Topper2013-10-03
| | | | | | file to my model twice. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191873 91177308-0d34-0410-b5e6-96231b3b80d8
* Add patterns for selecting TBM instructions from logical operations. Patch ↵Craig Topper2013-10-03
| | | | | | from Yunzhong Gao. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191871 91177308-0d34-0410-b5e6-96231b3b80d8
* AVX-512: fixed a bug in getLoadStoreRegOpcode() for AVX-512 targetElena Demikhovsky2013-10-02
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191818 91177308-0d34-0410-b5e6-96231b3b80d8
* Add test case for PR16785.Preston Gurd2013-10-01
| | | | | | | | | Thanks for Dimitry Andric, Rafael Espindola, and Benjamin Kramer for providing and progressively reducing the test case! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191782 91177308-0d34-0410-b5e6-96231b3b80d8
* AVX-512: Added X86vzmovl patternsElena Demikhovsky2013-10-01
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191733 91177308-0d34-0410-b5e6-96231b3b80d8
* TBAA: remove !tbaa from testing cases when they are not needed.Manman Ren2013-09-30
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191689 91177308-0d34-0410-b5e6-96231b3b80d8
* Adding intrinsics to the llvm backend for TBM instruction set.Yunzhong Gao2013-09-27
| | | | | | | | Phabricator code review is located here: http://llvm-reviews.chandlerc.com/D1750 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191539 91177308-0d34-0410-b5e6-96231b3b80d8
* Remove superfluous comment accidentally checked-in.Andrea Di Biagio2013-09-27
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191513 91177308-0d34-0410-b5e6-96231b3b80d8
* Re-apply the change from r191393 with fix for pr17380.Andrea Di Biagio2013-09-27
| | | | | | | | | | | This change fixes the problem reported in pr17380 and re-add the dagcombine transformation ensuring that the value types are always legal if the transformation is triggered after Legalization took place. Added the test case from pr17380. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191509 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert r191393 since it caused pr17380.Andrea Di Biagio2013-09-26
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191438 91177308-0d34-0410-b5e6-96231b3b80d8
* Test commit. Removed trailing whitespace.Josh Magee2013-09-25
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191402 91177308-0d34-0410-b5e6-96231b3b80d8
* Teach DAGCombiner how to canonicalize dags according to the ruleAndrea Di Biagio2013-09-25
| | | | | | | | | | | | | (shl (zext (shr A, X)), X) => (zext (shl (shr A, X), X)). The rule only triggers when there are no other uses of the zext to avoid materializing more instructions. This helps the DAGCombiner understand that the shl/shr sequence can then be converted into an and instruction. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191393 91177308-0d34-0410-b5e6-96231b3b80d8
* Add missing check to SETCC optimization.Eli Friedman2013-09-24
| | | | | | PR17338. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191337 91177308-0d34-0410-b5e6-96231b3b80d8
* [stackprotector] Forgot to add in PR number to test case.Michael Gottesman2013-09-24
| | | | git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191261 91177308-0d34-0410-b5e6-96231b3b80d8
* [stackprotector] Allow for copies from vreg -> vreg to be in a terminator ↵Michael Gottesman2013-09-24
| | | | | | | | | | | sequence. Sometimes a copy from a vreg -> vreg sneaks into the middle of a terminator sequence. It is safe to slice this into the stack protector success bb. This fixes PR16979. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191260 91177308-0d34-0410-b5e6-96231b3b80d8
* Selecting the address from a very long chain of GEPs can blow the stack.Bill Wendling2013-09-24
| | | | | | | | | | | The recursive nature of the address selection code can cause the stack to explode if there is a long chain of GEPs. Convert the recursive bit into a iterative method to avoid this. <rdar://problem/12445434> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191252 91177308-0d34-0410-b5e6-96231b3b80d8
* Add sha intrinsic testsBen Langmuir2013-09-23
| | | | | | | These should have been included with r190864, but I forgot to use svn add. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191208 91177308-0d34-0410-b5e6-96231b3b80d8
* ISelDAG: spot chain cycles involving MachineNodesTim Northover2013-09-22
| | | | | | | | | | | | | | | | | Previously, the DAGISel function WalkChainUsers was spotting that it had entered already-selected territory by whether a node was a MachineNode (amongst other things). Since it's fairly common practice to insert MachineNodes during ISelLowering, this was not the correct check. Looking around, it seems that other nodes get their NodeId set to -1 upon selection, so this makes sure the same thing happens to all MachineNodes and uses that characteristic to determine whether we should stop looking for a loop during selection. This should fix PR15840. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191165 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert "SelectionDAG: Teach the legalizer to split SETCC if VSELECT needs ↵Juergen Ributzka2013-09-21
| | | | | | | | splitting too." This reverts commit r191130. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191138 91177308-0d34-0410-b5e6-96231b3b80d8
* [X86] Emulate AVX 256bit MIN/MAX support by splitting the vector.Juergen Ributzka2013-09-21
| | | | | | | | | | | In AVX 256bit vectors are valid vectors and therefore the Type Legalizer doesn't split the VSELECT and SETCC nodes. AVX only supports MIN/MAX on 128bit vectors and this fix enables vector splitting for this special case in the X86 DAG Combiner. This fix is related to PR16695, PR17002, and <rdar://problem/14594431>. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191131 91177308-0d34-0410-b5e6-96231b3b80d8
* SelectionDAG: Teach the legalizer to split SETCC if VSELECT needs splitting too.Juergen Ributzka2013-09-21
| | | | | | | | | | | | | | | | | | The Type Legalizer recognizes that VSELECT needs to be split, because the type is to wide for the given target. The same does not always apply to SETCC, because less space is required to encode the result of a comparison. As a result VSELECT is split and SETCC is unrolled into scalar comparisons. This commit fixes the issue by checking for VSELECT-SETCC patterns in the DAG Combiner. If a matching pattern is found, then the result mask of SETCC is promoted to the expected vector mask for the given target. This mask has usually te same size as the VSELECT return type (except for Intel KNL). Now the type legalizer will split both VSELECT and SETCC. This allows the following X86 DAG Combine code to sucessfully detect the MIN/MAX pattern. This fixes PR16695, PR17002, and <rdar://problem/14594431>. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191130 91177308-0d34-0410-b5e6-96231b3b80d8
* PR16726: extend rol/ror matchingKai Nacke2013-09-19
| | | | | | | | | | | | | | | | | | | | | | C-like languages promote types like unsigned short to unsigned int before performing an arithmetic operation. Currently the rotate matcher in the DAGCombiner does not consider this situation. This commit extends the DAGCombiner in the way that the pattern (or (shl ([az]ext x), (*ext y)), (srl ([az]ext x), (*ext (sub 32, y)))) is folded into ([az]ext (rotl x, y)) The matching is restricted to aext and zext because in this cases the upper bits are either undefined or known. Test case is included. This fixes PR16726. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191049 91177308-0d34-0410-b5e6-96231b3b80d8
* Revert PR16726: extend rol/ror matchingKai Nacke2013-09-19
| | | | | | There is a buildbot failure. Need to investigate this. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191048 91177308-0d34-0410-b5e6-96231b3b80d8
* PR16726: extend rol/ror matchingKai Nacke2013-09-19
| | | | | | | | | | | | | | | | | | | | | | C-like languages promote types like unsigned short to unsigned int before performing an arithmetic operation. Currently the rotate matcher in the DAGCombiner does not consider this situation. This commit extends the DAGCombiner in the way that the pattern (or (shl ([az]ext x), (*ext y)), (srl ([az]ext x), (*ext (sub 32, y)))) is folded into ([az]ext (rotl x, y)) The matching is restricted to aext and zext because in this cases the upper bits are either undefined or known. Test case is included. This fixes PR16726. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191045 91177308-0d34-0410-b5e6-96231b3b80d8
* Add testcase to make sure we don't generate too many jumps for a une compare.Bill Wendling2013-09-19
| | | | | | | <rdar://problem/7859988> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191040 91177308-0d34-0410-b5e6-96231b3b80d8
* DAGCombiner: Don't fold vector muls with constants that look like a splat of ↵Benjamin Kramer2013-09-19
| | | | | | | | a power of 2 but differ in bit width. PR17283. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191000 91177308-0d34-0410-b5e6-96231b3b80d8
* X86: FrameIndex addressing modes do have a base register.Tim Northover2013-09-19
| | | | | | | | | | | | | | When selecting the DAG (add (WrapperRIP ...), (FrameIndex ...)), X86 code had spotted the FrameIndex possibility and was working out whether it could fold the WrapperRIP into this. The test for forming a %rip version is notionally whether we already have a base or index register (%rip precludes both), but we were forgetting to account for the register that would be inserted later to access the frame. rdar://problem/15024520 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190995 91177308-0d34-0410-b5e6-96231b3b80d8
* Attempt to fix llvm-ppc64-linux2 buildbot failure by addingPreston Gurd2013-09-18
| | | | | | | | -march=x86 to SLM test. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190958 91177308-0d34-0410-b5e6-96231b3b80d8
* Verify that llvm can generate the prefetchw instruction when the CPU isPreston Gurd2013-09-18
| | | | | | | | | | Atom Silvermont. Patch by Sriram Murali. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190957 91177308-0d34-0410-b5e6-96231b3b80d8
* Lift alignment restrictions for load/store folding on ↵Craig Topper2013-09-18
| | | | | | VINSERTF128/VEXTRACTF128. Fixes PR17268. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190916 91177308-0d34-0410-b5e6-96231b3b80d8
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-20 02:14:49 +0000