2014-07-18 |
Tim Northover | AArch64: support f16 extend/trunc operations. |
tree | commitdiff |
2014-07-18 |
Tim Northover | X86: support fpext/fptrunc operations to and from 16... |
tree | commitdiff |
2014-07-18 |
Tim Northover | ARM: support legalisation of "fptrunc ... to half"... |
tree | commitdiff |
2014-07-18 |
Tim Northover | CodeGen: soften f16 type by default instead of marking... |
tree | commitdiff |
2014-07-18 |
Tilmann Scheller | [ARM] Add earlyclobber constraint to pre/post-indexed... |
tree | commitdiff |
2014-07-18 |
Tim Northover | R600: rename misleading fp16 test. |
tree | commitdiff |
2014-07-18 |
Tim Northover | R600: support f16 -> f64 conversion intrinsic. |
tree | commitdiff |
2014-07-18 |
Tim Northover | NVPTX: support direct f16 <-> f64 conversions via intri... |
tree | commitdiff |
2014-07-18 |
Jim Grosbach | X86: Constant fold converting vector setcc results... |
tree | commitdiff |
2014-07-18 |
Jim Grosbach | AArch64: Constant fold converting vector setcc results... |
tree | commitdiff |
2014-07-18 |
Michael J. Spencer | Revert "[x86] Fold extract_vector_elt of a load into... |
tree | commitdiff |
2014-07-17 |
Justin Holewinski | [NVPTX] Improve handling of FP fusion |
tree | commitdiff |
2014-07-17 |
Zinovy Nis | [BUG] Due to a typo introduced in r199933 and r200027... |
tree | commitdiff |
2014-07-17 |
Justin Holewinski | [NVPTX] Add missing .v4 qualifier on vector store instr... |
tree | commitdiff |
2014-07-17 |
Justin Holewinski | [NVPTX] Flag surface/texture query instructions with... |
tree | commitdiff |
2014-07-17 |
Justin Holewinski | [NVPTX] Add more surface/texture intrinsics, including... |
tree | commitdiff |
2014-07-17 |
Tim Northover | ARM: support direct f16 <-> f64 conversions |
tree | commitdiff |
2014-07-17 |
Tim Northover | CodeGen: generate single libcall for fptrunc -> f16... |
tree | commitdiff |
2014-07-17 |
Tim Northover | X86: support double extension of f16 type. |
tree | commitdiff |
2014-07-17 |
Tim Northover | CodeGen: extend f16 conversions to permit types > float. |
tree | commitdiff |
2014-07-17 |
Yi Kong | Port memory barriers intrinsics to AArch64 |
tree | commitdiff |
2014-07-16 |
Sanjay Patel | Fixed formatting, removed bug reference, renamed testcase |
tree | commitdiff |
2014-07-16 |
Juergen Ributzka | [FastISel] Local values shouldn't be alive across an... |
tree | commitdiff |
2014-07-16 |
Sanjay Patel | trivial fix for PR20314 |
tree | commitdiff |
2014-07-16 |
Justin Holewinski | [NVPTX] Honor alignment on vector loads/stores |
tree | commitdiff |
2014-07-16 |
Justin Holewinski | [NVPTX] Rename registers %fl -> %fd and %rl -> %rd |
tree | commitdiff |
2014-07-16 |
Tim Northover | Convert test to CHECK-LABEL |
tree | commitdiff |
2014-07-16 |
Andrea Di Biagio | [X86] Add a check for 'isMOVHLPSMask' within method... |
tree | commitdiff |
2014-07-15 |
Matt Arsenault | R600/SI: Allow using f32 rcp / rsq when denormals not... |
tree | commitdiff |
2014-07-15 |
Matt Arsenault | R600/SI: Fix select on i1 |
tree | commitdiff |
2014-07-15 |
Matt Arsenault | R600/SI: Implement less wrong f32 fdiv |
tree | commitdiff |
2014-07-15 |
Chris Bieneman | [RegisterCoalescer] Add new subtarget hook allowing... |
tree | commitdiff |
2014-07-15 |
Cameron McInally | Revert r213070. It's breaking the build in MCELFStreame... |
tree | commitdiff |
2014-07-15 |
Jan Vesely | R600: Implement zero undef variants of ctlz/cttz |
tree | commitdiff |
2014-07-15 |
Cameron McInally | Add x86 patterns to match a specific add-with-carry. |
tree | commitdiff |
2014-07-15 |
Andrea Di Biagio | [DAGCombiner] Add more rules to fold shuffles. |
tree | commitdiff |
2014-07-15 |
Tim Northover | AArch64: fall back to generic code for out of range... |
tree | commitdiff |
2014-07-15 |
David Majnemer | Some targets don't prefix private symbols with dot |
tree | commitdiff |
2014-07-15 |
David Majnemer | Specify a more specific triple for constant-pool-remat... |
tree | commitdiff |
2014-07-15 |
David Majnemer | Relax tests expecting to see CPI symbols |
tree | commitdiff |
2014-07-15 |
David Majnemer | CodeGen: Handle ConstantVector and undef in WinCOFF... |
tree | commitdiff |
2014-07-15 |
Matt Arsenault | R600: Add dag combine for copy of an illegal type. |
tree | commitdiff |
2014-07-15 |
Andrea Di Biagio | Improve test 'CodeGen/X86/combine-vec-shuffle-3.ll'. |
tree | commitdiff |
2014-07-15 |
Andrea Di Biagio | [DAGCombiner] Avoid calling method 'isShuffleMaskLegal... |
tree | commitdiff |
2014-07-14 |
Matt Arsenault | R600: Add denormal handling subtarget features. |
tree | commitdiff |
2014-07-14 |
Matt Arsenault | R600/SI: Default to no single precision denormals. |
tree | commitdiff |
2014-07-14 |
David Majnemer | CodeGen: Stick constant pool entries in COMDAT sections... |
tree | commitdiff |
2014-07-14 |
Andrea Di Biagio | [DAGCombiner] Add more rules to combine shuffle vector... |
tree | commitdiff |
2014-07-14 |
Bill Wendling | Unify the lowering of arguments during SjLj prepare. |
tree | commitdiff |
2014-07-14 |
Saleem Abdulrasool | X86: correct 64-bit atomics on 32-bit |
tree | commitdiff |
2014-07-14 |
Tim Northover | X86: remove temporary atomicrmw used during lowering. |
tree | commitdiff |
2014-07-14 |
Daniel Sanders | [mips] For the FP64A ABI, odd-numbered double-precision... |
tree | commitdiff |
2014-07-14 |
Daniel Sanders | [mips] Use MFHC1 when it is available (MIPS32r2 and... |
tree | commitdiff |
2014-07-14 |
Tim Northover | AArch64: remove unnecessary pseudo-instruction. |
tree | commitdiff |
2014-07-14 |
Sasa Stankovic | [mips] Expand BuildPairF64 to a spill and reload when... |
tree | commitdiff |
2014-07-14 |
Bill Wendling | Support lowering of empty aggregates. |
tree | commitdiff |
2014-07-13 |
Andrea Di Biagio | [DAGCombiner] Fix a crash caused by a missing check... |
tree | commitdiff |
2014-07-13 |
Matt Arsenault | R600: Run more tests with promote alloca disabled. |
tree | commitdiff |
2014-07-13 |
Matt Arsenault | R600: Run private-memory test with and without alloca... |
tree | commitdiff |
2014-07-12 |
Saleem Abdulrasool | AArch64: add support for llvm.aarch64.hint intrinsic |
tree | commitdiff |
2014-07-12 |
Matt Arsenault | R600: Add missing tests for some intrinsics |
tree | commitdiff |
2014-07-11 |
Ulrich Weigand | [PowerPC] Fix invalid displacement created by LocalStac... |
tree | commitdiff |
2014-07-11 |
Marek Olsak | R600/SI: Use i32 vectors for resources and samplers |
tree | commitdiff |
2014-07-11 |
Marek Olsak | R600/SI: add sample and image intrinsics exposing all... |
tree | commitdiff |
2014-07-11 |
Oliver Stannard | ARM: Allow __fp16 as a function arg or return type... |
tree | commitdiff |
2014-07-11 |
Quentin Colombet | [X86] Fix the inversion of low and high bits for the... |
tree | commitdiff |
2014-07-10 |
Jan Vesely | R600: Implement float to long/ulong |
tree | commitdiff |
2014-07-10 |
Zoran Jovanovic | [mips] Emit two CFI offset directives per double precis... |
tree | commitdiff |
2014-07-10 |
Andrea Di Biagio | Extend the test coverage in combine-vec-shuffle-2.ll... |
tree | commitdiff |
2014-07-10 |
Matt Arsenault | Revert "Revert r212640, "Add trunc (select c, a, b... |
tree | commitdiff |
2014-07-10 |
Andrea Di Biagio | [DAG] Further improve the logic in DAGCombiner that... |
tree | commitdiff |
2014-07-10 |
Akira Hatanaka | [X86] Mark pseudo instruction TEST8ri_NOEREX as hasSIde... |
tree | commitdiff |
2014-07-10 |
Zoran Jovanovic | [mips] Added FPXX modeless calling convention. |
tree | commitdiff |
2014-07-10 |
Tim Northover | AArch64: correctly fast-isel i8 & i16 multiplies |
tree | commitdiff |
2014-07-10 |
Daniel Sanders | [mips] Add support for -modd-spreg/-mno-odd-spreg |
tree | commitdiff |
2014-07-10 |
Chandler Carruth | [x86,SDAG] Introduce any- and sign-extend-vector-inreg... |
tree | commitdiff |
2014-07-10 |
NAKAMURA Takumi | llvm/test/CodeGen/X86/shift-parts.ll: FileCheck-ize... |
tree | commitdiff |
2014-07-10 |
NAKAMURA Takumi | Revert r212640, "Add trunc (select c, a, b) -> select... |
tree | commitdiff |
2014-07-10 |
Chandler Carruth | [x86] Add another combine that is particularly useful... |
tree | commitdiff |
2014-07-10 |
Daniel Sanders | Make it possible for ints/floats to return different... |
tree | commitdiff |
2014-07-10 |
Chandler Carruth | [x86] Expand the target DAG combining for PSHUFD nodes... |
tree | commitdiff |
2014-07-10 |
Chandler Carruth | [x86] Tweak the v16i8 single input special case lowerin... |
tree | commitdiff |
2014-07-10 |
Chandler Carruth | [x86] Initial improvements to the new shuffle lowering... |
tree | commitdiff |
2014-07-10 |
Hao Liu | [AArch64]Fix an assertion failure in DAG Combiner about... |
tree | commitdiff |
2014-07-10 |
Matt Arsenault | R600/SI: Add support for llvm.convert.{to|from}.fp16 |
tree | commitdiff |
2014-07-09 |
David Blaikie | Recommit r212203: Don't try to construct debug LexicalS... |
tree | commitdiff |
2014-07-09 |
Matt Arsenault | Add trunc (select c, a, b) -> select c (trunc a), ... |
tree | commitdiff |
2014-07-09 |
Jim Grosbach | AArch64: Better codegen for storing to __fp16. |
tree | commitdiff |
2014-07-09 |
Chandler Carruth | [x86] Fix a bug in my new zext-vector-inreg DAG tricker... |
tree | commitdiff |
2014-07-09 |
Benjamin Kramer | X86: When lowering v8i32 himuls use the correct shuffle... |
tree | commitdiff |
2014-07-09 |
Chandler Carruth | [x86] Add a ZERO_EXTEND_VECTOR_INREG DAG node and use... |
tree | commitdiff |
2014-07-09 |
Daniel Sanders | [mips][mips64r6] Correct select patterns that have... |
tree | commitdiff |
2014-07-09 |
Daniel Sanders | [mips][mips64r6] Correct cond names in the cmp.cond... |
tree | commitdiff |
2014-07-09 |
Daniel Sanders | [mips][mips64r6] Use JALR for indirect branches instead... |
tree | commitdiff |
2014-07-09 |
Daniel Sanders | [mips][mips64r6] Use JALR for returns instead of JR... |
tree | commitdiff |
2014-07-09 |
Chandler Carruth | [x86] Re-apply a variant of the x86 side of r212324... |
tree | commitdiff |
2014-07-08 |
Jim Grosbach | AArch64: Better codegen for loading from __fp16. |
tree | commitdiff |
2014-07-08 |
Andrea Di Biagio | [DAG] Teach how to combine a pair of shuffles into... |
tree | commitdiff |
2014-07-08 |
Vladimir Medic | Mips.abiflags is a new implicitly generated section... |
tree | commitdiff |
2014-07-08 |
Chandler Carruth | [x86,SDAG] Sink the logic for folding shuffles of splat... |
tree | commitdiff |
next |