| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Use PMULDQ for v2i64 multiplies when SSE4.1 is available. And add | Dan Gohman | 2008-05-23 | 1 | -0/+1 |
| * | Fix typos and comments. | Evan Cheng | 2008-05-15 | 1 | -2/+2 |
| * | Make use of vector load and store operations to implement memcpy, memmove, an... | Evan Cheng | 2008-05-15 | 1 | -16/+45 |
| * | Change target-specific classes to use more precise static types. | Dan Gohman | 2008-05-14 | 1 | -7/+4 |
| * | Instead of a vector load, shuffle and then extract an element. Load the eleme... | Evan Cheng | 2008-05-13 | 1 | -21/+1 |
| * | Xform bitconvert(build_pair(load a, load b)) to a single load if the load loc... | Evan Cheng | 2008-05-12 | 1 | -19/+5 |
| * | Initial X86 codegen support for VSETCC. | Nate Begeman | 2008-05-12 | 1 | -0/+9 |
| * | Refactor isConsecutiveLoad from X86 to TargetLowering so DAG combiner can mak... | Evan Cheng | 2008-05-12 | 1 | -67/+24 |
| * | Fix a compile error on compilers that still want a return value | Dan Gohman | 2008-05-12 | 1 | -0/+1 |
| * | When transforming a vector_shuffle to a load, the base address must not be an... | Evan Cheng | 2008-05-10 | 1 | -0/+2 |
| * | For now, abort when an ISD::VAARG is encountered on x86-64, rather | Dan Gohman | 2008-05-10 | 1 | -3/+17 |
| * | If movl top bits are undef, let it be selected to movlps, etc. | Evan Cheng | 2008-05-10 | 1 | -2/+1 |
| * | Handle a few more cases of folding load i64 into xmm and zero top bits. | Evan Cheng | 2008-05-09 | 1 | -8/+60 |
| * | Handle vector move / load which zero the destination register top bits (i.e. ... | Evan Cheng | 2008-05-08 | 1 | -50/+106 |
| * | Improved generated code for atomic operators | Mon P Wang | 2008-05-05 | 1 | -16/+16 |
| * | Code clean up. No functionality change. | Evan Cheng | 2008-05-05 | 1 | -20/+21 |
| * | Added addition atomic instrinsics and, or, xor, min, and max. | Mon P Wang | 2008-05-05 | 1 | -8/+214 |
| * | Add General Dynamic TLS model for X86-64. Some parts looks really ugly (look ... | Anton Korobeynikov | 2008-05-04 | 1 | -9/+48 |
| * | Select vector shift with non-immediate i32 shift amount operand by first movi... | Evan Cheng | 2008-05-04 | 1 | -1/+90 |
| * | Tail call optimization improvements: | Arnold Schwaighofer | 2008-04-30 | 1 | -177/+20 |
| * | Fix the SVOffset values for loads and stores produced by | Dan Gohman | 2008-04-28 | 1 | -5/+6 |
| * | Properly lower vararg's FORMAL_ARGUMENTS node on win64 | Anton Korobeynikov | 2008-04-27 | 1 | -14/+38 |
| * | A few inline asm cleanups: | Chris Lattner | 2008-04-26 | 1 | -10/+11 |
| * | Extract the lower 64-bit if a MMX value is passed in a XMM register. | Evan Cheng | 2008-04-25 | 1 | -3/+9 |
| * | Special handling for MMX values being passed in either GPR64 or lower 64-bits... | Evan Cheng | 2008-04-25 | 1 | -2/+28 |
| * | MMX argument passing fixes: | Evan Cheng | 2008-04-25 | 1 | -7/+19 |
| * | Fix bug in x86 memcpy / memset lowering. If there are trailing bytes not hand... | Evan Cheng | 2008-04-25 | 1 | -11/+8 |
| * | Implement an x86-64 ABI detail of passing structs by hidden first | Dan Gohman | 2008-04-21 | 1 | -0/+34 |
| * | Switch to using Simplified ConstantFP::get API. | Chris Lattner | 2008-04-20 | 1 | -21/+16 |
| * | Fix the handling of va_copy on x86-64. As of llvm-gcc r49920 | Dan Gohman | 2008-04-18 | 1 | -14/+4 |
| * | Ongoing work on improving the instruction selection infrastructure: | Roman Levenstein | 2008-04-16 | 1 | -6/+6 |
| * | Add support for the form of the SSE41 extractps instruction that | Dan Gohman | 2008-04-16 | 1 | -2/+4 |
| * | Recreate the size SDNode instead of reusing the old one in the x86 | Dan Gohman | 2008-04-16 | 1 | -2/+2 |
| * | Fix const-correctness issues with the SrcValue handling in the | Dan Gohman | 2008-04-14 | 1 | -3/+3 |
| * | This patch corrects the handling of byval arguments for tailcall | Arnold Schwaighofer | 2008-04-12 | 1 | -29/+135 |
| * | Drop ISD::MEMSET, ISD::MEMMOVE, and ISD::MEMCPY, which are not Legal | Dan Gohman | 2008-04-12 | 1 | -163/+108 |
| * | Fix a bug that prevented x86-64 from using rep.movsq for | Dan Gohman | 2008-04-12 | 1 | -2/+2 |
| * | Make isVectorClearMaskLegal's operand list const. | Dan Gohman | 2008-04-09 | 1 | -3/+4 |
| * | Re-commit of the r48822, where the infinite looping problem discovered | Roman Levenstein | 2008-04-07 | 1 | -1/+1 |
| * | Favors pshufd over shufps when shuffling elements from one vector. pshufd is ... | Evan Cheng | 2008-04-05 | 1 | -41/+51 |
| * | Backing out 48222 temporarily. | Evan Cheng | 2008-04-03 | 1 | -1/+1 |
| * | Don't use __bzero for memset if the second argument isn't zero. | Dan Gohman | 2008-04-01 | 1 | -1/+2 |
| * | Speculatively micro-optimize memory-zeroing calls on Darwin 10. | Dan Gohman | 2008-04-01 | 1 | -5/+15 |
| * | Accept 'y' constraint (MMX) in inline asm. | Dale Johannesen | 2008-04-01 | 1 | -0/+1 |
| * | Fix a tokenfactor node to use the load chain rather than the | Dan Gohman | 2008-03-28 | 1 | -1/+1 |
| * | Use a linked data structure for the uses lists of an SDNode, just like | Roman Levenstein | 2008-03-26 | 1 | -1/+1 |
| * | - SSE4.1 extractfps extracts a f32 into a gr32 register. Very useful! Not. Fi... | Evan Cheng | 2008-03-24 | 1 | -3/+19 |
| * | Add convenient helper for win64 check. Simplify things slightly. | Anton Korobeynikov | 2008-03-22 | 1 | -1/+1 |
| * | Initial support for Win64 calling conventions. Still in early state. | Anton Korobeynikov | 2008-03-22 | 1 | -4/+8 |
| * | Introduce a new node for holding call argument | Duncan Sands | 2008-03-21 | 1 | -27/+18 |
