2015-10-20 |
Igor Breger | AVX512: Implemented encoding and intrinsics for VPBROAD... |
blob | commitdiff | raw |
2015-10-08 |
Igor Breger | AVX512: vpextrb/w/d/q and vpinsrb/w/d/q implementation. |
blob | commitdiff | raw | diff to current |
2015-10-04 |
Igor Breger | AVX512: Implemented encoding and intrinsics for VPERMIL... |
blob | commitdiff | raw | diff to current |
2015-09-22 |
Stephen Canon | Don't raise inexact when lowering ceil, floor, round... |
blob | commitdiff | raw | diff to current |
2015-09-20 |
Igor Breger | AVX512: Implement instructions encoding, lowering and... |
blob | commitdiff | raw | diff to current |
2015-09-02 |
Asaf Badouh | [X86][AVX512VLBW] add support in byte shift and SAD |
blob | commitdiff | raw | diff to current |
2015-09-02 |
Igor Breger | AVX512: Implemented encoding and intrinsics for vshufps/d. |
blob | commitdiff | raw | diff to current |
2015-08-31 |
Igor Breger | AVX512: Implemented encoding and intrinsics for vpalignr |
blob | commitdiff | raw | diff to current |
2015-08-20 |
Ahmed Bougacha | [X86] Look for scalar through one bitcast when lowering... |
blob | commitdiff | raw | diff to current |
2015-08-20 |
Ahmed Bougacha | [X86] Replace avx2 broadcast intrinsics with native IR. |
blob | commitdiff | raw | diff to current |
2015-08-20 |
Marina Yatsina | [X86] Fix bug in COMISD and COMISS definition in td... |
blob | commitdiff | raw | diff to current |
2015-07-28 |
Sanjay Patel | fix invalid load folding with SSE/AVX FP logical instru... |
blob | commitdiff | raw | diff to current |
2015-07-26 |
Igor Breger | Implemented encoding and intrinsics of the following... |
blob | commitdiff | raw | diff to current |
2015-07-24 |
Igor Breger | AVX-512: Implemented encoding , DAG lowering and intrin... |
blob | commitdiff | raw | diff to current |
2015-07-23 |
Igor Breger | AVX : Fix ISA disabling in case AVX512VL , some instruc... |
blob | commitdiff | raw | diff to current |
2015-07-19 |
Elena Demikhovsky | AVX-512: Floating point conversions for SKX - DAG Lowering. |
blob | commitdiff | raw | diff to current |
2015-07-15 |
Igor Breger | AVX : Fix ISA disabling in case AVX512VL , some instruc... |
blob | commitdiff | raw | diff to current |
2015-07-12 |
Simon Pilgrim | [X86][SSE] (V)PMINSB is commutable. |
blob | commitdiff | raw | diff to current |
2015-07-06 |
Simon Pilgrim | [X86][SSE4A] Shuffle lowering using SSE4A EXTRQ/INSERTQ... |
blob | commitdiff | raw | diff to current |
2015-07-06 |
Simon Pilgrim | [X86][SSE] Use the general SMAX/SMIN/UMAX/UMIN opcodes... |
blob | commitdiff | raw | diff to current |
2015-06-24 |
Ahmed Bougacha | [X86] Don't generate vbroadcasti128 for v4i64 splats... |
blob | commitdiff | raw | diff to current |
2015-06-16 |
Simon Pilgrim | [X86][SSE] Vectorize v2i32 to v2f64 conversions |
blob | commitdiff | raw | diff to current |
2015-06-03 |
Simon Pilgrim | [X86] Removed (unused) FSRL x86 operation |
blob | commitdiff | raw | diff to current |
2015-05-30 |
Chandler Carruth | [x86] Implement a faster vector population count based... |
blob | commitdiff | raw | diff to current |
2015-05-27 |
Elena Demikhovsky | AVX-512: Implemented all forms of sign-extend and zero... |
blob | commitdiff | raw | diff to current |
2015-05-21 |
Elena Demikhovsky | AVX-512: Enabled SSE intrinsics on AVX-512. |
blob | commitdiff | raw | diff to current |
2015-05-07 |
Sanjay Patel | Use intrinsic pattern to make a simpler match |
blob | commitdiff | raw | diff to current |
2015-05-07 |
Sanjay Patel | [x86] eliminate unnecessary shuffling/moves with unary... |
blob | commitdiff | raw | diff to current |
2015-04-28 |
Sanjay Patel | [x86] remove RCPPS and RSQRTPS intrinsic instruction... |
blob | commitdiff | raw | diff to current |
2015-04-27 |
Sanjay Patel | remove obsolete pattern matches for scalar SSE ops |
blob | commitdiff | raw | diff to current |
2015-04-22 |
Sanjay Patel | [x86] Add store-folded memop patterns for vcvtps2ph |
blob | commitdiff | raw | diff to current |
2015-04-22 |
Andrea Di Biagio | [X86][AVX] Fix failure due to a missing ISel pattern... |
blob | commitdiff | raw | diff to current |
2015-04-21 |
Simon Pilgrim | [X86][SSE] Provide execution domains for scalar floatin... |
blob | commitdiff | raw | diff to current |
2015-04-02 |
Sanjay Patel | [X86, AVX] adjust tablegen patterns to generate better... |
blob | commitdiff | raw | diff to current |
2015-03-31 |
Sanjay Patel | typo; NFC |
blob | commitdiff | raw | diff to current |
2015-03-31 |
Sanjay Patel | [X86, AVX] fix zero-extending integer operand load... |
blob | commitdiff | raw | diff to current |
2015-03-31 |
Ahmed Bougacha | [X86] Generate MOVNT for all vector types. |
blob | commitdiff | raw | diff to current |
2015-03-12 |
Sanjay Patel | [X86, AVX2] Replace inserti128 and extracti128 intrinsi... |
blob | commitdiff | raw | diff to current |
2015-03-11 |
Juergen Ributzka | Add the "vbroadcasti128" instruction back. |
blob | commitdiff | raw | diff to current |
2015-03-11 |
Elena Demikhovsky | AVX-512: Added SKX forms of shift instructions. |
blob | commitdiff | raw | diff to current |
2015-03-05 |
Ahmed Bougacha | [X86] Remove stale comment. NFC. |
blob | commitdiff | raw | diff to current |
2015-03-04 |
Juergen Ributzka | Remove 'llvm.x86.avx2.vbroadcasti128' intrinsic. |
blob | commitdiff | raw | diff to current |
2015-03-01 |
Elena Demikhovsky | AVX-512: Added mask and rounding mode for scalar arithm... |
blob | commitdiff | raw | diff to current |
2015-02-28 |
Craig Topper | [X86] Remove the blendpd/blendps/pblendw/pblendd intrin... |
blob | commitdiff | raw | diff to current |
2015-02-23 |
Elena Demikhovsky | restructured X86 scalar unary operation templates |
blob | commitdiff | raw | diff to current |
2015-02-22 |
Craig Topper | [X86] Add some missing redundant MMX and SSE encodings... |
blob | commitdiff | raw | diff to current |
2015-02-20 |
Sanjay Patel | canonicalize a v2f64 blendi of 2 registers |
blob | commitdiff | raw | diff to current |
2015-02-18 |
Craig Topper | [X86] Remove AVX2 and SSE2 pslldq and psrldq intrinsics... |
blob | commitdiff | raw | diff to current |
2015-02-17 |
Sanjay Patel | prevent folding a scalar FP load into a packed logical... |
blob | commitdiff | raw | diff to current |
2015-02-16 |
Simon Pilgrim | [X86][SSE] Add SSE MOVQ instructions to SSEPackedInt... |
blob | commitdiff | raw | diff to current |
2015-02-16 |
Craig Topper | [X86] Remove the multiply by 8 that goes into the shift... |
blob | commitdiff | raw | diff to current |
2015-02-16 |
Craig Topper | [X86] Remove x86.avx2.psll.dq.bs and x86.avx2.psrl... |
blob | commitdiff | raw | diff to current |
2015-02-15 |
Simon Pilgrim | [X86][AVX2] vpslldq/vpsrldq byte shifts for AVX2 |
blob | commitdiff | raw | diff to current |
2015-02-13 |
Sanjay Patel | [SSE/AVX] Use multiclasses to reduce the mass of scalar... |
blob | commitdiff | raw | diff to current |
2015-02-13 |
Craig Topper | [X86] Remove int_x86_sse2_psll_dq_bs and int_x86_sse2_p... |
blob | commitdiff | raw | diff to current |
2015-02-09 |
Craig Topper | [X86] Remove 256-bit and 512-bit memop pattern fragment... |
blob | commitdiff | raw | diff to current |
2015-02-08 |
Craig Topper | [X86] Remove the remaining uses of memop from AVX and... |
blob | commitdiff | raw | diff to current |
2015-02-05 |
Craig Topper | [X86] Add xrstors/xsavec/xsaves/clflushopt/clwb/pcommit... |
blob | commitdiff | raw | diff to current |
2015-02-04 |
Chandler Carruth | [x86] Give movss and movsd execution domains in the... |
blob | commitdiff | raw | diff to current |
2015-02-04 |
Chandler Carruth | [x86] Add missing patterns for andps, orps, xorps,... |
blob | commitdiff | raw | diff to current |
2015-02-03 |
Sanjay Patel | Merge consecutive 16-byte loads into one 32-byte load... |
blob | commitdiff | raw | diff to current |
2015-01-26 |
Simon Pilgrim | [X86][SSE] Float comparisons can sometimes be safely... |
blob | commitdiff | raw | diff to current |
2015-01-26 |
Simon Pilgrim | [X86][PCLMUL] Enable commutation for PCLMUL instructions |
blob | commitdiff | raw | diff to current |
2015-01-26 |
Sanjay Patel | Model sqrtsd as a binary operation with one source... |
blob | commitdiff | raw | diff to current |
2015-01-25 |
Craig Topper | [X86] Give scalar VRNDSCALE instructions priority in... |
blob | commitdiff | raw | diff to current |
2015-01-25 |
Craig Topper | Remove tab characters. NFC |
blob | commitdiff | raw | diff to current |
2015-01-25 |
Craig Topper | [X86] Replace i32i8imm on SSE/AVX instructions with... |
blob | commitdiff | raw | diff to current |
2015-01-25 |
Craig Topper | [X86] Use u8imm in several places that used i32i8imm... |
blob | commitdiff | raw | diff to current |
2015-01-25 |
Craig Topper | Remove tab characters. NFC. |
blob | commitdiff | raw | diff to current |
2015-01-21 |
Simon Pilgrim | [X86][SSE] Added support for SSE3 lane duplication... |
blob | commitdiff | raw | diff to current |
2015-01-21 |
Ahmed Bougacha | [X86] Declare SSE4.1/AVX2 vector extloads covered by... |
blob | commitdiff | raw | diff to current |
2015-01-21 |
Craig Topper | [X86] Convert all the i8imm used by SSE and AVX instruc... |
blob | commitdiff | raw | diff to current |
2015-01-21 |
Craig Topper | [x86] Add assembly parser bounds checking to the immedi... |
blob | commitdiff | raw | diff to current |
2015-01-20 |
Craig Topper | [x86] Add some mayLoad/hasSideEffects flags. Remove... |
blob | commitdiff | raw | diff to current |
2015-01-11 |
Simon Pilgrim | [X86][SSE] Minor fix to VPBLENDW AVX2 commutation. |
blob | commitdiff | raw | diff to current |
2014-12-27 |
Craig Topper | [x86] Prevent llvm.x86.cmp.ps/pd/ss/sd from being selec... |
blob | commitdiff | raw | diff to current |
2014-12-19 |
Elena Demikhovsky | Masked load and store codegen - fixed 128-bit vectors |
blob | commitdiff | raw | diff to current |
2014-12-19 |
Sanjay Patel | Model sqrtss as a binary operation with one source... |
blob | commitdiff | raw | diff to current |
2014-12-18 |
Robert Khasanov | [AVX512] Enable FP arithmetic lowering for AVX512VL... |
blob | commitdiff | raw | diff to current |
2014-12-18 |
Craig Topper | [X86] Don't use PS prefix on LDMXCSR/STMXCSR. |
blob | commitdiff | raw | diff to current |
2014-12-16 |
Robert Khasanov | [AVX512] Enable integer arithmetic lowering for AVX512B... |
blob | commitdiff | raw | diff to current |
2014-12-16 |
Sanjay Patel | combine consecutive subvector 16-byte loads into one... |
blob | commitdiff | raw | diff to current |
2014-12-12 |
Robert Khasanov | [AVX512] Enabling bit logic lowering |
blob | commitdiff | raw | diff to current |
2014-12-12 |
Robert Khasanov | [AVX512] Enabling MIN/MAX lowering. |
blob | commitdiff | raw | diff to current |
2014-12-11 |
Ahmed Bougacha | [X86] Add a temporary testcase for PR21876/r223996. |
blob | commitdiff | raw | diff to current |
2014-12-11 |
Ahmed Bougacha | [X86] Add back AVX2 VR256 PMOVX patterns. |
blob | commitdiff | raw | diff to current |
2014-12-10 |
Sanjay Patel | Match new shuffle codegen for MOVHPD patterns |
blob | commitdiff | raw | diff to current |
2014-12-06 |
Ahmed Bougacha | [X86] Refactor PMOV[SZ]Xrm to add missing AVX2 patterns. |
blob | commitdiff | raw | diff to current |
2014-12-04 |
Elena Demikhovsky | Masked Load / Store Intrinsics - the CodeGen part. |
blob | commitdiff | raw | diff to current |
2014-12-04 |
Michael Liao | [X86] Clean up whitespace as well as minor coding style |
blob | commitdiff | raw | diff to current |
2014-12-02 |
Simon Pilgrim | [X86][SSE] Keep 4i32 vector insertions in integer domai... |
blob | commitdiff | raw | diff to current |
2014-11-28 |
Duncan P. N. Exon... | Revert "Masked Vector Load and Store Intrinsics." |
blob | commitdiff | raw | diff to current |
2014-11-26 |
Craig Topper | Replace neverHasSideEffects=1 with hasSideEffects=0... |
blob | commitdiff | raw | diff to current |
2014-11-23 |
Elena Demikhovsky | Masked Vector Load and Store Intrinsics. |
blob | commitdiff | raw | diff to current |
2014-11-04 |
Simon Pilgrim | [X86][SSE] Enable commutation for SSE immediate blend... |
blob | commitdiff | raw | diff to current |
2014-10-17 |
Andrea Di Biagio | [X86] Fix missed selection of non-temporal store of... |
blob | commitdiff | raw | diff to current |
2014-10-06 |
Benjamin Kramer | X86: Drop the isConvertibleTo3Addr bit from shufps... |
blob | commitdiff | raw | diff to current |
2014-10-03 |
Chandler Carruth | [x86] Add a really preposterous number of patterns... |
blob | commitdiff | raw | diff to current |
2014-10-03 |
Chandler Carruth | [x86] Adjust the patterns for lowering X86vzmovl nodes... |
blob | commitdiff | raw | diff to current |
2014-10-03 |
Chandler Carruth | [x86] Teach the new vector shuffle lowering to aggressi... |
blob | commitdiff | raw | diff to current |
next |