| Commit message (Expand) | Author | Age | Files | Lines |
... | |
* | For something like | Evan Cheng | 2012-07-16 | 2 | -2/+50 |
* | Make ComputeDemandedBits return a deterministic result when computing an Asse... | Nadav Rotem | 2012-07-16 | 1 | -0/+12 |
* | Fix tests that failed on i686-win32 after r160248: | Alexey Samsonov | 2012-07-16 | 2 | -3/+4 |
* | Fix a bug in the 3-address conversion of LEA when one of the operands is an | Nadav Rotem | 2012-07-16 | 1 | -0/+16 |
* | This CL changes the function prologue and epilogue emitted on X86 when stack ... | Alexey Samsonov | 2012-07-16 | 3 | -24/+48 |
* | Teach getTargetVShiftNode about TargetConstant nodes. | Nadav Rotem | 2012-07-15 | 1 | -0/+9 |
* | llvm/test/CodeGen/X86/2012-07-15-broadcastfold.ll: Rewrite expressions to fit... | NAKAMURA Takumi | 2012-07-15 | 1 | -1/+3 |
* | Rename VBROADCASTSDrm into VBROADCASTSDYrm to match the naming convention. | Nadav Rotem | 2012-07-15 | 1 | -0/+21 |
* | AVX: Fix a bug in getTargetVShiftNode. The shift amount has to be a 128bit ve... | Nadav Rotem | 2012-07-14 | 1 | -0/+31 |
* | Add a dagcombine optimization to convert concat_vectors of undefs into a sing... | Nadav Rotem | 2012-07-14 | 1 | -0/+17 |
* | Restrict this to x86, hopefully fixing ARM buildbots. | Duncan Sands | 2012-07-13 | 1 | -1/+1 |
* | Give the rdrand instructions a SideEffect flag and a chain so MachineCSE and ... | Benjamin Kramer | 2012-07-12 | 1 | -0/+38 |
* | The LIT tests below do not specify the exact cpu model and fail on AVX2 machi... | Nadav Rotem | 2012-07-12 | 5 | -9/+9 |
* | llvm/test/CodeGen/X86/rdrand.ll: Relax expression corresponding to Win64 CC. | NAKAMURA Takumi | 2012-07-12 | 1 | -7/+7 |
* | Use %s instead of the explicit name, the latter doesn't work in out-of-tree b... | Benjamin Kramer | 2012-07-12 | 1 | -1/+1 |
* | Add intrinsics for Ivy Bridge's rdrand instruction. | Benjamin Kramer | 2012-07-12 | 1 | -0/+47 |
* | The result type of EXTRACT_VECTOR_ELT doesn't have to match the element type of | Duncan Sands | 2012-07-12 | 1 | -0/+20 |
* | Update GATHER instructions to support 2 read-write operands. Patch from mysel... | Craig Topper | 2012-07-12 | 1 | -0/+19 |
* | X86: Update to peephole optimization to move Movr0 before (Sub, Cmp) pair. | Manman Ren | 2012-07-11 | 1 | -0/+12 |
* | PR13326: Fix a subtle edge case in the udiv -> magic multiply generator. | Benjamin Kramer | 2012-07-11 | 1 | -0/+21 |
* | When ext-loading and trunc-storing vectors to memory, on x86 32bit systems, a... | Nadav Rotem | 2012-07-11 | 5 | -9/+26 |
* | Add newline. | Chad Rosier | 2012-07-10 | 1 | -1/+1 |
* | Add test case accidentally omitted from r160002. | Chad Rosier | 2012-07-10 | 1 | -0/+242 |
* | Add support for dynamic stack realignment in the presence of dynamic allocas on | Chad Rosier | 2012-07-10 | 3 | -5/+18 |
* | Improve the loading of load-anyext vectors by allowing the codegen to load | Nadav Rotem | 2012-07-10 | 3 | -12/+18 |
* | X86: implement functions to analyze & synthesize CMOV|SET|Jcc | Manman Ren | 2012-07-09 | 1 | -0/+17 |
* | X86: Fix optimizeCompare to correctly check safe condition. | Manman Ren | 2012-07-07 | 1 | -0/+18 |
* | X86: peephole optimization to remove cmp instruction | Manman Ren | 2012-07-06 | 1 | -0/+19 |
* | [fast-isel] Tell fast-isel to do nothing with the new donothing intrinsic. | Chad Rosier | 2012-07-06 | 1 | -0/+8 |
* | Attempt to fix windows buildbots. Patch by James Benton. | Duncan Sands | 2012-07-06 | 1 | -5/+1 |
* | test/CodeGen/X86/sext-setcc-self.ll: Mark it as XFAIL: cygwin,mingw32,win32. ... | NAKAMURA Takumi | 2012-07-06 | 1 | -0/+4 |
* | Use the right kind of booleans: we were emitting 0/1 booleans, instead of 0/-1 | Duncan Sands | 2012-07-05 | 1 | -0/+55 |
* | Ensure CopyToReg nodes are always glued to the call instruction. | Jakob Stoklund Olesen | 2012-07-04 | 2 | -5/+21 |
* | Add a testcase for pr13209. It is not a great test, but it still fails if | Rafael Espindola | 2012-07-04 | 1 | -0/+74 |
* | Add early if-conversion support to X86. | Jakob Stoklund Olesen | 2012-07-04 | 1 | -0/+39 |
* | test/CodeGen/X86/sincos.ll: FileCheck-ize. | NAKAMURA Takumi | 2012-07-03 | 1 | -4/+22 |
* | test/CodeGen/X86/fabs.ll: FileCheck-ize. | NAKAMURA Takumi | 2012-07-03 | 1 | -5/+23 |
* | test/CodeGen/X86/2007-09-05-InvalidAsm.ll: FileCheck-ize. | NAKAMURA Takumi | 2012-07-03 | 1 | -1/+2 |
* | test/CodeGen/X86/2004-03-30-Select-Max.ll: FileCheck-ize. | NAKAMURA Takumi | 2012-07-03 | 1 | -1/+2 |
* | Fix the remaining TCL-style quotes found in the testsuite. This is | Chandler Carruth | 2012-07-02 | 27 | -32/+32 |
* | Convert the uses of '|&' to use '2>&1 |' instead, which works on old | Chandler Carruth | 2012-07-02 | 25 | -26/+26 |
* | Convert all tests using TCL-style quoting to use shell-style quoting. | Chandler Carruth | 2012-07-02 | 70 | -95/+95 |
* | Optimization of shuffle node that can fit to the register form of VBROADCAST ... | Elena Demikhovsky | 2012-07-01 | 1 | -0/+96 |
* | Clear kill flags in InstrEmitter::EmitSubregNode(). | Jakob Stoklund Olesen | 2012-06-29 | 1 | -2/+37 |
* | In the initial exec mode we always do a load to find the address of a variable. | Rafael Espindola | 2012-06-29 | 1 | -5/+6 |
* | X86: add more GATHER intrinsics in LLVM | Manman Ren | 2012-06-29 | 1 | -10/+90 |
* | X86: add GATHER intrinsics (AVX2) in LLVM | Manman Ren | 2012-06-26 | 1 | -0/+80 |
* | Shuffle optimization for AVX/AVX2. | Elena Demikhovsky | 2012-06-26 | 1 | -0/+21 |
* | Enable the new LoopInfo algorithm by default. | Andrew Trick | 2012-06-26 | 1 | -4/+4 |
* | Make some ugly hacks for inline asm operands which name a specific register a... | Eli Friedman | 2012-06-25 | 1 | -3/+16 |