| Commit message (Expand) | Author | Age |
|---|
| * | Add a warning | Chris Lattner | 2006-04-18 |
| * | Use vmladduhm to do v8i16 multiplies which is faster and simpler than doing | Chris Lattner | 2006-04-18 |
| * | Implement v16i8 multiply with this code: | Chris Lattner | 2006-04-18 |
| * | Add tests for v8i16 and v16i8 | Chris Lattner | 2006-04-18 |
| * | Correct comments | Evan Cheng | 2006-04-18 |
| * | Lower v8i16 multiply into this code: | Chris Lattner | 2006-04-18 |
| * | Custom lower v4i32 multiplies into a cute sequence, instead of having legalize | Chris Lattner | 2006-04-18 |
| * | new testcase | Chris Lattner | 2006-04-18 |
| * | Another entry | Evan Cheng | 2006-04-18 |
| * | Fix a build failure on Vladimir's tester. | Chris Lattner | 2006-04-18 |
| * | Another entry. | Evan Cheng | 2006-04-18 |
| * | Use movss to insert_vector_elt(v, s, 0). | Evan Cheng | 2006-04-17 |
| * | Turn x86 unaligned load/store intrinsics into aligned load/store instructions | Chris Lattner | 2006-04-17 |
| * | Fix handling of calls in functions that use vectors. This fixes a crash on | Chris Lattner | 2006-04-17 |
| * | Use two pinsrw to insert an element into v4i32 / v4f32 vector. | Evan Cheng | 2006-04-17 |
| * | remove done item | Chris Lattner | 2006-04-17 |
| * | Don't diddle VRSAVE if no registers need to be added/removed from it. This | Chris Lattner | 2006-04-17 |
| * | New testcase, shouldn't touch vrsave | Chris Lattner | 2006-04-17 |
| * | Add a MachineInstr::eraseFromParent convenience method. | Chris Lattner | 2006-04-17 |
| * | Add some convenience methods. | Chris Lattner | 2006-04-17 |
| * | Encoding bug | Evan Cheng | 2006-04-17 |
| * | Vectors that are known live-in and live-out are clearly already marked in | Chris Lattner | 2006-04-17 |
| * | Prefer to allocate V2-V5 before V0,V1. This lets us generate code like this: | Chris Lattner | 2006-04-17 |
| * | Move some knowledge about registers out of the code emitter into the register... | Chris Lattner | 2006-04-17 |
| * | Use a small table instead of macros to do this conversion. | Chris Lattner | 2006-04-17 |
| * | Implement v8i16, v16i8 splat using unpckl + pshufd. | Evan Cheng | 2006-04-17 |
| * | implement returns of a vector, testcase here: CodeGen/X86/vec_return.ll | Chris Lattner | 2006-04-17 |
| * | New testcase | Chris Lattner | 2006-04-17 |
| * | Codegen insertelement with constant insertion points as scalar_to_vector | Chris Lattner | 2006-04-17 |
| * | Make sure to check splats of every constant we can, handle splat(31) by | Chris Lattner | 2006-04-17 |
| * | Incorrect foldMemoryOperand entries | Evan Cheng | 2006-04-17 |
| * | Errors in patterns preventing load folding | Evan Cheng | 2006-04-17 |
| * | Add checks for __OpenBSD__. | Jeff Cohen | 2006-04-17 |
| * | Teach the ppc backend to use rol and vsldoi to generate splatted constants. | Chris Lattner | 2006-04-17 |
| * | Some more cases that can be generated with two instructions | Chris Lattner | 2006-04-17 |
| * | add a note | Chris Lattner | 2006-04-17 |
| * | FP SETOLT, SETOLT, SETUGE, SETUGT conditions were implemented incorrectly | Evan Cheng | 2006-04-17 |
| * | Make some code more general, adding support for constant formation of several | Chris Lattner | 2006-04-17 |
| * | New testcases | Chris Lattner | 2006-04-17 |
| * | Learn how to make odd splatted constants in range [17,29]. This implements | Chris Lattner | 2006-04-17 |
| * | new testcase | Chris Lattner | 2006-04-17 |
| * | Pull some code out into a helper function. | Chris Lattner | 2006-04-17 |
| * | New testcase | Chris Lattner | 2006-04-17 |
| * | Implement a TODO: for any shuffle that can be viewed as a v4[if]32 shuffle, | Chris Lattner | 2006-04-17 |
| * | new testcase, these shuffles can be implemented with discrete instructions, | Chris Lattner | 2006-04-17 |
| * | Regenerate with adjusted costs | Chris Lattner | 2006-04-17 |
| * | Encode a cost of zero as a cost of 1. | Chris Lattner | 2006-04-17 |
| * | Regenerate with correct offset | Chris Lattner | 2006-04-17 |
| * | Really, I can count! | Chris Lattner | 2006-04-17 |
| * | Increase the opcodes by one each to disambiguate COPY from VMRGHW. | Chris Lattner | 2006-04-17 |
