| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| ... | |
| * | Make this test harder, always check generic x86 and SSE-enabled x86. | Chris Lattner | 2006-03-31 | 1 | -1/+10 |
| * | Implement PromoteOp for VEXTRACT_VECTOR_ELT. Thsi fixes | Chris Lattner | 2006-03-31 | 1 | -42/+54 |
| * | Scalarized vector stores need not be legal, e.g. if the vector element type | Chris Lattner | 2006-03-31 | 1 | -0/+3 |
| * | Fix build breakage. | Jeff Cohen | 2006-03-31 | 1 | -0/+1 |
| * | note to self: *save* file, then check it in | Chris Lattner | 2006-03-31 | 1 | -1/+1 |
| * | Implement an item from the readme, folding vcmp/vcmp. instructions with | Chris Lattner | 2006-03-31 | 2 | -9/+29 |
| * | new testcase | Chris Lattner | 2006-03-31 | 1 | -0/+21 |
| * | compactify some more instruction definitions | Chris Lattner | 2006-03-31 | 1 | -61/+15 |
| * | Compactify comparisons. | Chris Lattner | 2006-03-31 | 1 | -104/+34 |
| * | Allow bits init values to be used in patterns, turn them into ints. | Chris Lattner | 2006-03-31 | 1 | -0/+19 |
| * | Lower vector compares to VCMP nodes, just like we lower vector comparison | Chris Lattner | 2006-03-31 | 4 | -43/+72 |
| * | These are done | Chris Lattner | 2006-03-31 | 1 | -5/+0 |
| * | Final bugfix for PR724. GCC won't inline varargs functions, so use one to | Chris Lattner | 2006-03-31 | 1 | -17/+9 |
| * | Add a new method to verify intrinsic function prototypes. | Chris Lattner | 2006-03-31 | 1 | -2/+60 |
| * | When emitting code for the verifier, instead of emitting each case statement | Chris Lattner | 2006-03-31 | 1 | -9/+42 |
| * | Make sure to pass enough values to phi nodes when we are dealing with | Chris Lattner | 2006-03-31 | 1 | -2/+10 |
| * | Significantly improve handling of vectors that are live across basic blocks, | Chris Lattner | 2006-03-31 | 3 | -52/+101 |
| * | Was returning the wrong type. | Chris Lattner | 2006-03-31 | 1 | -4/+5 |
| * | Mark INSERT_VECTOR_ELT as expand | Chris Lattner | 2006-03-31 | 1 | -0/+1 |
| * | Expand all INSERT_VECTOR_ELT (obviously bad) for now. | Evan Cheng | 2006-03-31 | 1 | -0/+1 |
| * | Expand INSERT_VECTOR_ELT to store vec, sp; store elt, sp+k; vec = load sp; | Evan Cheng | 2006-03-31 | 1 | -1/+24 |
| * | Modify the TargetLowering::getPackedTypeBreakdown method to also return the | Chris Lattner | 2006-03-31 | 2 | -7/+13 |
| * | Typo | Evan Cheng | 2006-03-31 | 1 | -2/+2 |
| * | Ok for vector_shuffle mask to contain undef elements. | Evan Cheng | 2006-03-31 | 1 | -56/+120 |
| * | Implement TargetLowering::getPackedTypeBreakdown | Chris Lattner | 2006-03-31 | 1 | -0/+41 |
| * | Add a method useful for decimating vectors. | Chris Lattner | 2006-03-31 | 1 | -0/+10 |
| * | Add the rest of the vmul instructions and the vmulsum* instructions. | Chris Lattner | 2006-03-30 | 1 | -1/+15 |
| * | fix incorrect prototypes | Chris Lattner | 2006-03-30 | 1 | -12/+12 |
| * | Use a new tblgen feature to significantly shrinkify instruction definitions that | Chris Lattner | 2006-03-30 | 1 | -108/+46 |
| * | Add a bunch of new instructions for intrinsics. | Chris Lattner | 2006-03-30 | 1 | -6/+87 |
| * | regenerate | Chris Lattner | 2006-03-30 | 3 | -1663/+1208 |
| * | Implement Regression/TableGen/DagDefSubst.ll | Chris Lattner | 2006-03-30 | 4 | -41/+45 |
| * | Dag operator should be able to be template params. | Chris Lattner | 2006-03-30 | 1 | -0/+15 |
| * | Fix Transforms/InstCombine/2006-03-30-ExtractElement.ll | Chris Lattner | 2006-03-30 | 1 | -3/+7 |
| * | new testcase that crashes instcombine | Chris Lattner | 2006-03-30 | 1 | -0/+7 |
| * | Make sure all possible shuffles are matched. | Evan Cheng | 2006-03-30 | 2 | -30/+89 |
| * | Add vector multiply, multiply sum, pack, unpack, and lvsl/lvsr intrinsics. | Chris Lattner | 2006-03-30 | 1 | -0/+91 |
| * | More logical ops patterns | Evan Cheng | 2006-03-30 | 1 | -0/+106 |
| * | Add support for _mm_cmp{cc}_ss and _mm_cmp{cc}_ps intrinsics | Evan Cheng | 2006-03-30 | 2 | -115/+39 |
| * | Add 128-bit pmovmskb intrinsic support. | Evan Cheng | 2006-03-30 | 2 | -7/+14 |
| * | Change SSE pack operation definitions to fit what the intrinsics expected. | Evan Cheng | 2006-03-29 | 2 | -23/+23 |
| * | Add SSE2 integer pack with saturation intrinsics. | Evan Cheng | 2006-03-29 | 1 | -0/+10 |
| * | - Added some SSE2 128-bit packed integer ops. | Evan Cheng | 2006-03-29 | 3 | -25/+314 |
| * | Add a pshufhw test case. | Evan Cheng | 2006-03-29 | 1 | -0/+25 |
| * | Need to special case splat after all. Make the second operand of splat | Evan Cheng | 2006-03-29 | 2 | -15/+18 |
| * | Use unpcklpd for v2f64 splat. | Evan Cheng | 2006-03-29 | 1 | -1/+1 |
| * | Floating point logical operation patterns should match bit_convert. Or else | Evan Cheng | 2006-03-29 | 1 | -29/+53 |
| * | Add more SSE intrinsics | Evan Cheng | 2006-03-29 | 1 | -94/+118 |
| * | - More shuffle related bug fixes. | Evan Cheng | 2006-03-29 | 2 | -47/+30 |
| * | Another entry about shuffles. | Evan Cheng | 2006-03-29 | 1 | -0/+6 |
