Age | Commit message (Expand) | Author | Files | Lines |
2014-12-10 | ScheduleDAGInstrs: Consider sub-registers when computing vreg def dependenciesmi-sched-experimental | Tom Stellard | 1 | -1/+2 |
2014-12-10 | MachineRegisterInfo: Add SubIdx argument to hasOneDef() | Tom Stellard | 2 | -6/+23 |
2014-11-25 | TargetRegisterInfo: Add target query subRegWriteClobbersSuperReg() | Tom Stellard | 1 | -0/+13 |
2014-11-25 | XXX: Load clustering fix. | Tom Stellard | 1 | -10/+41 |
2014-11-24 | R600/SI: Remove unused register class | Tom Stellard | 1 | -7/+0 |
2014-11-24 | XXX: Maystore = 0 on MUBUF loads | Tom Stellard | 1 | -1/+1 |
2014-11-24 | XXX: Sched improvements | Tom Stellard | 1 | -1/+3 |
2014-11-24 | R600/SI: Define a schedule model and enable the generic machine scheduler | Tom Stellard | 8 | -25/+217 |
2014-11-24 | Added comment about llvm_execute_on_thread waiting for thread to complete. | Yaron Keren | 1 | -1/+2 |
2014-11-24 | [mips][microMIPS] Implement LBU16, LHU16, LW16, SB16, SH16 and SW16 instructions | Jozef Kolek | 7 | -0/+209 |
2014-11-24 | [mips][microMIPS] Implement 16-bit instructions registers including ZERO inst... | Jozef Kolek | 3 | -0/+41 |
2014-11-24 | [Mips] Update MIPS relocations list | Simon Atanasyan | 1 | -0/+28 |
2014-11-24 | Replace a comment that says 'unreachable' with llvm_unreachable in TableGen A... | Craig Topper | 1 | -1/+1 |
2014-11-24 | Removing a variable that is initialized but never read. The original author h... | Aaron Ballman | 1 | -6/+2 |
2014-11-24 | [mips][microMIPS] Implement disassembler support for 16-bit instructions | Jozef Kolek | 4 | -14/+147 |
2014-11-24 | [X86] Improved target specific combine on VSELECT dag nodes. | Andrea Di Biagio | 3 | -153/+192 |
2014-11-24 | InstCombine: Don't assume DataLayout is always available | David Majnemer | 2 | -1/+22 |
2014-11-24 | Support: Add *cast_or_null<> for pointer wrappers | Duncan P. N. Exon Smith | 2 | -0/+130 |
2014-11-24 | Detect best type for some static index tables instead of just using uint32_t ... | Craig Topper | 1 | -15/+24 |
2014-11-23 | Converted back to Unix format (after my last commit 222632) | Elena Demikhovsky | 1 | -3241/+3241 |
2014-11-23 | [X86] Fixes bug in build_vector v4x32 lowering | Michael Kuperstein | 2 | -3/+23 |
2014-11-23 | Add missing override keywords. | Craig Topper | 1 | -2/+2 |
2014-11-23 | Tablegen output formatting fixes. | Craig Topper | 1 | -2/+4 |
2014-11-23 | Masked Vector Load and Store Intrinsics. | Elena Demikhovsky | 32 | -3154/+4418 |
2014-11-23 | R600: Fix extloads of i1 on R600/Evergreen | Matt Arsenault | 2 | -13/+33 |
2014-11-23 | R600: Fix assert on copy of an i1 on pre-SI | Matt Arsenault | 1 | -1/+2 |
2014-11-23 | R600/SI: Add additional tests for i1 loads | Matt Arsenault | 1 | -1/+22 |
2014-11-23 | R600/SI: Fix broken check lines and modernize prefixes | Matt Arsenault | 2 | -48/+50 |
2014-11-23 | R600/SI: Fix missing -verify-machineinstrs on a test | Matt Arsenault | 1 | -1/+1 |
2014-11-22 | InstCombine: Propagate exact for (sdiv X, Pow2) -> (udiv X, Pow2) | David Majnemer | 2 | -2/+15 |
2014-11-22 | InstCombine: Propagate exact for (sdiv X, Y) -> (udiv X, Y) | David Majnemer | 2 | -1/+13 |
2014-11-22 | InstCombine: Propagate exact for (sdiv -X, C) -> (sdiv X, -C) | David Majnemer | 2 | -4/+15 |
2014-11-22 | Tidied up target triple OS detection. NFC | Simon Pilgrim | 6 | -14/+25 |
2014-11-22 | Reduce size of some tables in tablegen register info output. | Craig Topper | 2 | -50/+54 |
2014-11-22 | InstCombine: Propagate exact in (udiv (lshr X,C1),C2) -> (udiv x,C1<<C2) | David Majnemer | 2 | -2/+16 |
2014-11-22 | [x86] Teach the vector shuffle yet another step of canonicalization. | Chandler Carruth | 1 | -2/+13 |
2014-11-22 | InstCombine: Propagate NSW/NUW for X*(1<<Y) -> X<<Y | David Majnemer | 2 | -4/+33 |
2014-11-22 | InstCombine: Propagate NSW for -X * -Y -> X * Y | David Majnemer | 2 | -3/+19 |
2014-11-22 | InstSimplify: Simplify (sub 0, X) -> X if it's NUW | David Majnemer | 2 | -11/+10 |
2014-11-22 | InstCombine: Silence a parenthesis warning | David Majnemer | 1 | -1/+1 |
2014-11-22 | [x86] Add some tests for a common unpack pattern of vector shuffle that | Chandler Carruth | 3 | -0/+72 |
2014-11-22 | InstCombine: Preserve nsw when folding X*(2^C) -> X << C | David Majnemer | 3 | -5/+7 |
2014-11-22 | InstCombine: Preserve nsw/nuw for ((X << C2)*C1) -> (X * (C1 << C2)) | David Majnemer | 2 | -3/+28 |
2014-11-22 | InstCombine: Preserve nsw for (mul %V, -1) -> (sub 0, %V) | David Majnemer | 2 | -2/+14 |
2014-11-21 | [InstCombine] Re-commit of r218721 (Optimize icmp-select-icmp sequence) | Gerolf Hoflehner | 9 | -11/+428 |
2014-11-21 | Fix transformation of add with pc argument to adr for non-immediate | Joerg Sonnenberger | 2 | -7/+33 |
2014-11-21 | [asan] remove old experimental code | Kostya Serebryany | 2 | -61/+0 |
2014-11-21 | R600/SI: Add a failing test case for offset order in ds_read2 instructions | Tom Stellard | 1 | -0/+44 |
2014-11-21 | R600/SI: Add an s_mov_b32 to patterns which use the M0RegClass | Tom Stellard | 2 | -24/+8 |
2014-11-21 | R600/SI: Emit s_mov_b32 m0, -1 before every DS instruction | Tom Stellard | 7 | -41/+30 |