| Commit message (Collapse) | Author | Age | Files | Lines | ||
|---|---|---|---|---|---|---|
| ... | ||||||
| * | remove a dead prototype | Chris Lattner | 2006-04-20 | 1 | -4/+0 | |
| | | | | | llvm-svn: 27882 | |||||
| * | Make code match cvs commit message :) | Andrew Lenharth | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27881 | |||||
| * | If we can convert the return pointer type into an integer that IntPtrType | Andrew Lenharth | 2006-04-20 | 1 | -2/+4 | |
| | | | | | | | can be converted to losslessly, we can continue the conversion to a direct call. llvm-svn: 27880 | |||||
| * | can we cast between pointers and IntPtrType | Andrew Lenharth | 2006-04-20 | 1 | -0/+15 | |
| | | | | | llvm-svn: 27879 | |||||
| * | Add a missing =back to eliminate error. | Reid Spencer | 2006-04-20 | 1 | -0/+2 | |
| | | | | | llvm-svn: 27878 | |||||
| * | v16i8 splat with 2 punpcklbw and a single pshufd. | Evan Cheng | 2006-04-20 | 1 | -0/+26 | |
| | | | | | llvm-svn: 27877 | |||||
| * | Another shuffle test. For 4-wide shuffle, no more than 3 {p}shuf*. | Evan Cheng | 2006-04-20 | 1 | -0/+9 | |
| | | | | | llvm-svn: 27876 | |||||
| * | - Added support to turn "vector clear elements", e.g. pand V, <-1, -1, 0, -1> | Evan Cheng | 2006-04-20 | 2 | -77/+232 | |
| | | | | | | | | | to a vector shuffle. - VECTOR_SHUFFLE lowering change in preparation for more efficient codegen of vector shuffle with zero (or any splat) vector. llvm-svn: 27875 | |||||
| * | Turn a VAND into a VECTOR_SHUFFLE is applicable. | Evan Cheng | 2006-04-20 | 1 | -1/+64 | |
| | | | | | | | | | DAG combiner can turn a VAND V, <-1, 0, -1, -1>, i.e. vector clear elements, into a vector shuffle with a zero vector. It only does so when TLI tells it the xform is profitable. llvm-svn: 27874 | |||||
| * | Added a virtual method isVectorClearMaskLegal to TLI. It is similar to | Evan Cheng | 2006-04-20 | 1 | -0/+10 | |
| | | | | | | | | | isShuffleMaskLegal, used to determine if it makes sense to turn a "vector clear" (e.g. pand V, <0, -1, 0, -1> to a shuffle of the vector and a zero vector. llvm-svn: 27873 | |||||
| * | Added a test case for , e.g. xform pand <0, 0, -1, -1> to a shuffle. | Evan Cheng | 2006-04-20 | 1 | -0/+8 | |
| | | | | | llvm-svn: 27872 | |||||
| * | Added a movhlps, movlhps test case. | Evan Cheng | 2006-04-20 | 1 | -0/+19 | |
| | | | | | llvm-svn: 27871 | |||||
| * | Don't hardcode in 1.5 for the website, just use 'CVS'. | Chris Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27870 | |||||
| * | This is old, out of date, and isn't linked to by anything. | Chris Lattner | 2006-04-20 | 1 | -180/+0 | |
| | | | | | llvm-svn: 27869 | |||||
| * | Make sure that the new instructions selected have the right type. This fixes | Chris Lattner | 2006-04-20 | 1 | -5/+5 | |
| | | | | | | | CodeGen/PowerPC/2006-04-19-vmaddfp-crash.ll llvm-svn: 27868 | |||||
| * | New testcase for a codegen crash | Chris Lattner | 2006-04-20 | 1 | -0/+72 | |
| | | | | | llvm-svn: 27867 | |||||
| * | Changing domain name | Tanya Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27865 | |||||
| * | Implement folding of a bunch of binops with undef | Chris Lattner | 2006-04-20 | 1 | -0/+46 | |
| | | | | | llvm-svn: 27863 | |||||
| * | Update llvmgcc4 tarball names | Chris Lattner | 2006-04-20 | 1 | -6/+9 | |
| | | | | | llvm-svn: 27861 | |||||
| * | Removed listing of llvm releases after 1.4, and said "1.4 and newer" | Tanya Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27860 | |||||
| * | Made warning red. | Tanya Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27859 | |||||
| * | Document is out of date.. added warning and link to llvm-config. | Tanya Lattner | 2006-04-20 | 1 | -0/+2 | |
| | | | | | llvm-svn: 27858 | |||||
| * | Fixed up comment on xfail for llvmgcc version. | Tanya Lattner | 2006-04-20 | 1 | -2/+2 | |
| | | | | | llvm-svn: 27857 | |||||
| * | Added note about being able to XFAIL based on llvmgcc version. | Tanya Lattner | 2006-04-20 | 1 | -2/+2 | |
| | | | | | llvm-svn: 27856 | |||||
| * | Removed cvs mirror comment | Tanya Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27855 | |||||
| * | Minor fixes for the release. | Tanya Lattner | 2006-04-20 | 1 | -22/+9 | |
| | | | | | llvm-svn: 27854 | |||||
| * | This has been fixed! Thanks Reid. | Chris Lattner | 2006-04-20 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27853 | |||||
| * | Yeah that's right! | Chris Lattner | 2006-04-20 | 1 | -2/+2 | |
| | | | | | llvm-svn: 27852 | |||||
| * | Fixes from Tanya | Chris Lattner | 2006-04-20 | 1 | -5/+6 | |
| | | | | | llvm-svn: 27851 | |||||
| * | Add in missing #defines for _OpenBSD_ systems. | Reid Spencer | 2006-04-20 | 1 | -0/+12 | |
| | | | | | llvm-svn: 27850 | |||||
| * | Handle v2i64 BUILD_VECTOR custom lowering correctly. v2i64 is a legal type, | Evan Cheng | 2006-04-20 | 1 | -1/+16 | |
| | | | | | | | | but i64 is not. If possible, change a i64 op to a f64 (e.g. load, constant) and then cast it back. llvm-svn: 27849 | |||||
| * | Allow OpenBSD to be recognized as a UNIX platform. | Reid Spencer | 2006-04-19 | 2 | -29/+35 | |
| | | | | | llvm-svn: 27848 | |||||
| * | isSplatMask() bug: first element can be an undef. | Evan Cheng | 2006-04-19 | 1 | -6/+18 | |
| | | | | | llvm-svn: 27847 | |||||
| * | Simplify some code | Chris Lattner | 2006-04-19 | 1 | -5/+1 | |
| | | | | | llvm-svn: 27846 | |||||
| * | - Added support to do aribitrary 4 wide shuffle with no more than three | Evan Cheng | 2006-04-19 | 1 | -7/+54 | |
| | | | | | | | | instructions. - Fixed a commute vector_shuff bug. llvm-svn: 27845 | |||||
| * | Prefer {p}unpack* and mov*dup over {p}shuf* as well. | Evan Cheng | 2006-04-19 | 1 | -3/+13 | |
| | | | | | llvm-svn: 27844 | |||||
| * | Renamed AddedCost to AddedComplexity. | Evan Cheng | 2006-04-19 | 2 | -6/+6 | |
| | | | | | llvm-svn: 27843 | |||||
| * | - Renamed AddedCost to AddedComplexity. | Evan Cheng | 2006-04-19 | 1 | -11/+18 | |
| | | | | | | | - Added more movhlps and movlhps patterns. llvm-svn: 27842 | |||||
| * | Rename AddedCost to AddedComplexity. | Evan Cheng | 2006-04-19 | 2 | -13/+15 | |
| | | | | | llvm-svn: 27841 | |||||
| * | Commute vector_shuffle to match more movlhps, movlp{s|d} cases. | Evan Cheng | 2006-04-19 | 2 | -63/+59 | |
| | | | | | llvm-svn: 27840 | |||||
| * | Final piece to get relinked .o files buildable universal on Darwin. | Chris Lattner | 2006-04-19 | 1 | -2/+6 | |
| | | | | | llvm-svn: 27839 | |||||
| * | Regenerate | Chris Lattner | 2006-04-19 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27838 | |||||
| * | When on darwin, compiler_flags need to be percolated down to the 'gcc -r' | Chris Lattner | 2006-04-19 | 1 | -1/+1 | |
| | | | | | | | command line so that relinked .o files can be built universal. llvm-svn: 27837 | |||||
| * | More mov{h|l}p{d|s} patterns. | Evan Cheng | 2006-04-19 | 1 | -21/+26 | |
| | | | | | llvm-svn: 27836 | |||||
| * | - More mov{h|l}ps patterns. | Evan Cheng | 2006-04-19 | 1 | -2/+25 | |
| | | | | | | | | - Increase cost (complexity) of patterns which match mov{h|l}ps ops. These are preferred over shufps in most cases. llvm-svn: 27835 | |||||
| * | Allow "let AddedCost = n in" to increase pattern complexity. | Evan Cheng | 2006-04-19 | 4 | -8/+26 | |
| | | | | | llvm-svn: 27834 | |||||
| * | Alpha too! | Chris Lattner | 2006-04-19 | 1 | -1/+1 | |
| | | | | | llvm-svn: 27833 | |||||
| * | add a note | Chris Lattner | 2006-04-19 | 1 | -0/+31 | |
| | | | | | llvm-svn: 27832 | |||||
| * | Another simple case type merge case to try | Andrew Lenharth | 2006-04-19 | 1 | -0/+24 | |
| | | | | | llvm-svn: 27831 | |||||
| * | deal with memchr | Andrew Lenharth | 2006-04-19 | 1 | -0/+7 | |
| | | | | | llvm-svn: 27830 | |||||
 |
index : bcm5719-llvm | |
| Project Ortega BCM5719 LLVM | Raptor Computing Systems |
| summaryrefslogtreecommitdiffstats |
|