| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | ADDS{D|S}rr_Int and MULS{D|S}rr_Int are not commutable. The users of these in... | Evan Cheng | 2009-02-26 | 1 | -4/+4 |
| * | Modify the intrinsics pattern to separate out the "return" types from the | Bill Wendling | 2008-11-13 | 1 | -285/+286 |
| * | Removed pinsrd and pinsrq intrinsics because the code generator does not support | Mon P Wang | 2008-10-15 | 1 | -6/+0 |
| * | Fix SSE4.1 roundss, roundsd. While the instructions have | Dale Johannesen | 2008-10-10 | 1 | -2/+2 |
| * | "The original bug was a complaint that _mm_srli_si128 mis-compiled when passed | Bill Wendling | 2008-10-02 | 1 | -0/+6 |
| * | SSE codegen for vsetcc nodes | Nate Begeman | 2008-07-17 | 1 | -0/+3 |
| * | Horizontal-add instructions are not commutative. | Evan Cheng | 2008-06-16 | 1 | -8/+11 |
| * | - Add "Commutative" property to intrinsics. This allows tblgen to generate th... | Evan Cheng | 2008-06-16 | 1 | -87/+129 |
| * | Eliminate x86.sse2.punpckh.qdq and x86.sse2.punpckl.qdq. | Evan Cheng | 2008-05-24 | 1 | -11/+0 |
| * | Eliminate x86.sse2.movs.d, x86.sse2.shuf.pd, x86.sse2.unpckh.pd, and x86.sse2... | Evan Cheng | 2008-05-24 | 1 | -12/+0 |
| * | Remove x86.sse2.loadh.pd and x86.sse2.loadl.pd. These will be lowered into lo... | Evan Cheng | 2008-05-24 | 1 | -6/+0 |
| * | Add separate intrinsics for MMX / SSE shifts with i32 integer operands. This ... | Evan Cheng | 2008-05-03 | 1 | -6/+59 |
| * | Undo 48570. Correctly match mmx shift instructions with an immediate operand. | Evan Cheng | 2008-03-21 | 1 | -24/+0 |
| * | Add intrinsics to match mmx shift builtin's with immediate operand. | Evan Cheng | 2008-03-19 | 1 | -0/+24 |
| * | __builtin_ia32_movntdqa reads memory | Nate Begeman | 2008-03-16 | 1 | -1/+1 |
| * | Missed one. | Dale Johannesen | 2008-02-05 | 1 | -3/+3 |
| * | Do not unconditionally redefine vec_ext_v16qi and | Dale Johannesen | 2008-02-04 | 1 | -2/+2 |
| * | SSE 4.1 Intrinsics and detection | Nate Begeman | 2008-02-03 | 1 | -0/+150 |
| * | Fix sse2.psrl.w and sse2.psrl.q definitions. | Evan Cheng | 2008-01-09 | 1 | -2/+2 |
| * | remove attribution from a variety of miscellaneous files. | Chris Lattner | 2007-12-29 | 1 | -2/+2 |
| * | Add a few more missing gcc builtin's. | Evan Cheng | 2007-12-21 | 1 | -8/+8 |
| * | Type specification didn't match gcc's. | Evan Cheng | 2007-12-20 | 1 | -1/+1 |
| * | Remove int_x86_sse2_movl_dq. It's replaced with a string compare. | Evan Cheng | 2007-12-18 | 1 | -2/+0 |
| * | These have matching builtin's in 4.2. | Evan Cheng | 2007-12-18 | 1 | -2/+2 |
| * | Bring back int_x86_sse2_movl_dq intrinsic for backward compatibility. Make sure | Evan Cheng | 2007-12-17 | 1 | -0/+2 |
| * | __builtin_ia32_movqv4si is now expanded to a shuffle. | Evan Cheng | 2007-12-15 | 1 | -2/+0 |
| * | All MMX shift instructions took a <2 x i32> vector as the shift amount parame... | Anders Carlsson | 2007-12-14 | 1 | -8/+8 |
| * | Add missing SSE builtins: CVTPD2PI, CVTPS2PI, | Dale Johannesen | 2007-10-30 | 1 | -0/+13 |
| * | Fix argument types for PSLLQ, PSRLQ. | Dale Johannesen | 2007-10-30 | 1 | -2/+2 |
| * | There is no {rsqrt,rcp}{p,s}d. | Dan Gohman | 2007-09-21 | 1 | -12/+0 |
| * | Adding SSSE3 intrinsics. | Bill Wendling | 2007-08-10 | 1 | -2/+116 |
| * | Add missing SSE builtins: | Bill Wendling | 2007-07-23 | 1 | -0/+14 |
| * | add missing mmx intrinsic | Chris Lattner | 2007-05-16 | 1 | -0/+4 |
| * | Add the final MMX instructions. Correct a few wrong patterns. | Bill Wendling | 2007-04-24 | 1 | -0/+4 |
| * | Add support for our first SSSE3 instruction "pmulhrsw". | Bill Wendling | 2007-04-10 | 1 | -0/+10 |
| * | Adding more MMX instructions. | Bill Wendling | 2007-04-03 | 1 | -0/+41 |
| * | Add FEMMS and ADDQ. Renamed MMX recipes to prepend the MMX_ to them. | Bill Wendling | 2007-04-03 | 1 | -1/+3 |
| * | Add support for integer comparison builtins. | Bill Wendling | 2007-03-27 | 1 | -0/+23 |
| * | This is dead. DEAD I tells you!! | Bill Wendling | 2007-03-23 | 1 | -3/+0 |
| * | PR1260: | Bill Wendling | 2007-03-23 | 1 | -4/+20 |
| * | We generate a shufflevector instruction, so we don't need the builtin | Bill Wendling | 2007-03-22 | 1 | -7/+0 |
| * | Support added for shifts and unpacking MMX instructions. | Bill Wendling | 2007-03-22 | 1 | -0/+38 |
| * | Multiplication support for MMX. | Bill Wendling | 2007-03-15 | 1 | -0/+8 |
| * | Adding more arithmetic operators to MMX. This is an almost exact copy of | Bill Wendling | 2007-03-10 | 1 | -0/+16 |
| * | Added "padd*" support for MMX. Added MMX move stuff to X86InstrInfo so that | Bill Wendling | 2007-03-08 | 1 | -0/+17 |
| * | Add the emms intrinsic for MMX support. | Bill Wendling | 2007-03-05 | 1 | -0/+9 |
| * | Convert the intrinsic function definitions to use llvm_i32_ty instead of | Reid Spencer | 2006-12-31 | 1 | -44/+44 |
| * | Added X86 SSE2 intrinsics which can be represented as vector_shuffles. This is | Evan Cheng | 2006-04-24 | 1 | -1/+29 |
| * | Last few SSE3 intrinsics. | Evan Cheng | 2006-04-14 | 1 | -0/+26 |
| * | Misc. SSE2 intrinsics: clflush, lfench, mfence | Evan Cheng | 2006-04-14 | 1 | -0/+6 |
