| Commit message (Expand) | Author | Age | Files | Lines |
* | Avoid zero extend bit test operands to pointer type if all the masks fit in | Evan Cheng | 2011-01-06 | 1 | -0/+30 |
* | Optimize: | Evan Cheng | 2011-01-05 | 1 | -0/+60 |
* | fix PR8900, a shuffle miscompilation. Patch by Nadav Rotem! | Chris Lattner | 2011-01-05 | 1 | -0/+13 |
* | Use pushq / popq instead of subq $8, %rsp / addq $8, %rsp to adjust stack in | Evan Cheng | 2011-01-03 | 7 | -170/+170 |
* | Try to reuse the value when lowering memset. | Benjamin Kramer | 2011-01-02 | 1 | -0/+9 |
* | Lower the i8 extension in memset to a multiply instead of a potentially long ... | Benjamin Kramer | 2011-01-02 | 1 | -0/+11 |
* | Fix darwin bots. | Rafael Espindola | 2011-01-01 | 1 | -1/+1 |
* | Add support for the 'H' modifier. | Rafael Espindola | 2011-01-01 | 1 | -0/+12 |
* | test/CodeGen/X86/negative-sin.ll: FileCheck-ize. | NAKAMURA Takumi | 2010-12-29 | 1 | -2/+2 |
* | test/CodeGen/X86/fp-in-intregs.ll: FileCheck-ize. | NAKAMURA Takumi | 2010-12-29 | 1 | -1/+2 |
* | DAGCombine add (sext i1), X into sub X, (zext i1) if sext from i1 is illegal.... | Benjamin Kramer | 2010-12-22 | 1 | -0/+12 |
* | X86: Lower a select directly to a setcc_carry if possible. | Benjamin Kramer | 2010-12-22 | 1 | -2/+19 |
* | Fix a bug in ReduceLoadWidth that wasn't handling extending | Chris Lattner | 2010-12-22 | 1 | -3/+21 |
* | Reapply 122353-122355 with fixes. 122354 was wrong; | Dale Johannesen | 2010-12-21 | 2 | -3/+13 |
* | Add some x86 specific dagcombines for conditional increments. | Benjamin Kramer | 2010-12-21 | 1 | -0/+89 |
* | Revert 122353-122355 for the moment, they broke stuff. | Dale Johannesen | 2010-12-21 | 2 | -13/+3 |
* | Add a new transform to DAGCombiner. | Dale Johannesen | 2010-12-21 | 1 | -0/+10 |
* | Get the type of a shift from the shift, not from its shift | Dale Johannesen | 2010-12-21 | 1 | -3/+3 |
* | Cosmetic changes. | Dale Johannesen | 2010-12-20 | 1 | -1/+1 |
* | now that addc/adde are gone, "ADDC" in the X86 backend uses EFLAGS results, | Chris Lattner | 2010-12-20 | 1 | -0/+19 |
* | We lower setb to sbb with the hope that the and will go away, when it | Chris Lattner | 2010-12-20 | 1 | -0/+9 |
* | Add comment for testcase for 122206 | Mon P Wang | 2010-12-20 | 1 | -1/+2 |
* | Prevents PerformShuffleCombine from creating a node with an illegal type afte... | Mon P Wang | 2010-12-19 | 1 | -4/+24 |
* | improve the setcc -> setcc_carry optimization to happen more | Chris Lattner | 2010-12-19 | 3 | -23/+34 |
* | now that generic vector types aren't selected onto MMX registers, these | Chris Lattner | 2010-12-19 | 38 | -38/+36 |
* | fix PR8642: if a critical edge has a PHI value that can trap, | Chris Lattner | 2010-12-19 | 1 | -0/+29 |
* | Just rename the functions, relying on matching a instruction that has the sam... | Benjamin Kramer | 2010-12-18 | 1 | -4/+4 |
* | Test more than just label names and make test work on non-x86 hosts. | Benjamin Kramer | 2010-12-18 | 1 | -1/+5 |
* | Add support for matching psign & plendvb to the x86 target | Nate Begeman | 2010-12-17 | 1 | -0/+26 |
* | Add a transform to DAG Combiner. This improves the | Dale Johannesen | 2010-12-17 | 1 | -0/+9 |
* | Teach machine cse to commute instructions. | Evan Cheng | 2010-12-15 | 1 | -0/+40 |
* | take care of some todos, transforming [us]mul_lohi into | Chris Lattner | 2010-12-15 | 1 | -0/+1 |
* | merge two tests | Chris Lattner | 2010-12-15 | 2 | -7/+10 |
* | Fix a minor bug in two-address pass. It was missing a commute opportunity. | Evan Cheng | 2010-12-14 | 1 | -5/+43 |
* | rename test | Chris Lattner | 2010-12-13 | 1 | -0/+0 |
* | Add a couple dag combines to transform mulhi/mullo into a wider multiply | Chris Lattner | 2010-12-13 | 2 | -12/+36 |
* | Formalize the notion that AVX and SSE are non-overlapping extensions from the... | Nate Begeman | 2010-12-10 | 1 | -1/+1 |
* | Rewrite the darwin tlv support to use a chain and return to copying | Eric Christopher | 2010-12-09 | 1 | -0/+16 |
* | Remove extraneous copy from DAG conversion for darwin tls. This was | Eric Christopher | 2010-12-09 | 1 | -0/+32 |
* | Move this test to tlv* to make it easier to notice versus linux tls | Eric Christopher | 2010-12-08 | 1 | -0/+0 |
* | If dbg_declare() or dbg_value() is not lowered by isel then emit DEBUG messag... | Devang Patel | 2010-12-06 | 1 | -24/+18 |
* | Revert previous two patches while I try to find out how to make both | Rafael Espindola | 2010-12-06 | 1 | -1/+1 |
* | Update test for the extra =. | Rafael Espindola | 2010-12-06 | 1 | -1/+1 |
* | Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags | Chris Lattner | 2010-12-05 | 1 | -0/+22 |
* | it turns out that when ".with.overflow" intrinsics were added to the X86 | Chris Lattner | 2010-12-05 | 1 | -1/+7 |
* | fix the rest of the linux miscompares :) | Chris Lattner | 2010-12-05 | 1 | -1/+1 |
* | generalize the previous check to handle -1 on either side of the | Chris Lattner | 2010-12-05 | 1 | -0/+24 |
* | relax this to handle linux defaulting to -static. | Chris Lattner | 2010-12-05 | 1 | -1/+1 |
* | Improve an integer select optimization in two ways: | Chris Lattner | 2010-12-05 | 1 | -0/+58 |
* | merge some tests into select.ll and make them more specific. | Chris Lattner | 2010-12-05 | 7 | -99/+88 |