Log - c9623db884ec044249c85366e9bc94e47d5cc48a - toolchain/llvm-project

941a705 MachineFunction: Return reference for getFrameInfo(); NFC by Matthias Braun · 9 years ago
fe26775 AMDGPU: Remove analyzeImmediate by Matt Arsenault · 9 years ago
7968c34 AMDGPU: Unify MOVRELSOffset and MOVRELDOffset by Nicolai Haehnle · 9 years ago
1322b6f AMDGPU: Improve offset folding for register indexing by Matt Arsenault · 9 years ago
a4b746d AMDGPU/SI: Remove address space query functions from AMDGPUDAGToDAGISel by Tom Stellard · 9 years ago
4a105d7 AMDGPU/R600: Add PatFrags for selecting the correct vtx id for loads by Tom Stellard · 9 years ago
17a0ec54 AMDGPU/SI: Remove hack for selecting < 32-bit loads to MUBUF instructions by Tom Stellard · 9 years ago
43e92fe AMDGPU: Cleanup subtarget handling. by Matt Arsenault · 9 years ago
180e0d5 AMDGPU: Fix gcc warnings by Matt Arsenault · 9 years ago
7b4ef06 Delete more dead code. by Rafael Espindola · 9 years ago
4897588 Delete some dead code. by Rafael Espindola · 9 years ago
fd92154 Reformat blank lines. by NAKAMURA Takumi · 9 years ago
fe1202c Untabify. by NAKAMURA Takumi · 9 years ago
a609259 AMDGPU: Fix MUBUF offset bugs affecting llvm.amdgcn.buffer.* intrinsics by Nicolai Haehnle · 9 years ago
bdc4956 Pass DebugLoc and SDLoc by const ref. by Benjamin Kramer · 9 years ago
26a2ab7 AMDGPU/SI: Make sure to emit TargetConstant nodes when matching ds_*permute by Tom Stellard · 9 years ago
7757c59 AMDGPU: Fix flat atomics by Matt Arsenault · 9 years ago
8870181 AMDGPU: Fix i64 global cmpxchg by Matt Arsenault · 9 years ago
f97de00 AMDGPU/R600: Implement memory loads from constant AS by Jan Vesely · 9 years ago
95927c0 SDAG: Implement Select instead of SelectImpl in AMDGPUDAGToDAGISel by Justin Bogner · 9 years ago
0a81921 Fixed unused but set variable warning by Simon Pilgrim · 9 years ago
b012699 SDAG: Rename Select->SelectImpl and repurpose Select as returning void by Justin Bogner · 9 years ago
2b957b5 AMDGPU: Make i64 loads/stores promote to v2i32 by Matt Arsenault · 10 years ago
92b24f3 AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions by Tom Stellard · 10 years ago
99c1452 AMDGPU: Implement addrspacecast by Matt Arsenault · 10 years ago
7e8de01 AMDGPU: sext_inreg (srl x, K), vt -> bfe x, K, vt.Size by Matt Arsenault · 10 years ago
05b127d [StructurizeCFG] Annotate branches that were treated as uniform by Nicolai Haehnle · 10 years ago
a9dbdca AMDGPU: Add atomic_inc + atomic_dec intrinsics by Matt Arsenault · 10 years ago
43b7b5b AMDGPU/SI: Implement atomic load/store for i32 and i64 by Jan Vesely · 10 years ago
b8a3720 Fix sequence point warning. NFC. by Vasileios Kalintiris · 10 years ago
f43c2a0 AMDGPU: Insert moves of frame index to value operands by Matt Arsenault · 10 years ago
cb38a6b AMDGPU: Remove SignBitIsZero for mubuf scratch offsets by Matt Arsenault · 10 years ago
3003ba0 AMDGPU: use ComplexPattern for offsets in llvm.amdgcn.buffer.load/store.format by Nicolai Haehnle · 10 years ago
8226fc4 AMDGPU: Simplify boolean conditional return statements by Matt Arsenault · 10 years ago
cd09961 AMDGPU: Check cheaper condition before SignBitIsZero by Matt Arsenault · 10 years ago
d275921 AMDGPU: Cleanup includes and random macros by Matt Arsenault · 10 years ago
bc4497b AMDGPU/SI: Detect uniform branches and emit s_cbranch instructions by Tom Stellard · 10 years ago
7e7d983 Refactor backend diagnostics for unsupported features by Oliver Stannard · 10 years ago
02fa1c8 Revert r259035, it introduces a cyclic library dependency by Oliver Stannard · 10 years ago
b4b092e Add backend dignostic printer for unsupported features by Oliver Stannard · 10 years ago
628a7a0 Revert r258951 (and r258950), "Refactor backend diagnostics for unsupported features" by NAKAMURA Takumi · 10 years ago
1e67a9f Refactor backend diagnostics for unsupported features by Oliver Stannard · 10 years ago
7836f89 AMDGPU: Fix old comments that mention AMDIL by Matt Arsenault · 10 years ago
b41574a AMDGPU/SI: Use flat for global load/store when targeting HSA by Changpeng Fang · 10 years ago
4b0d24c Revert "AMDGPU/SI: Use flat for global load/store when targeting HSA" by Rafael Espindola · 10 years ago
9b8a9be AMDGPU/SI: Use flat for global load/store when targeting HSA by Changpeng Fang · 10 years ago
592d068 AMDGPU: Error on addrspacecasts that aren't actually implemented by Matt Arsenault · 10 years ago
38b7cbe AMDGPU/SI: Remove REGISTER_STORE/REGISTER_LOAD code which is now dead by Tom Stellard · 10 years ago
26f8f3d AMDGPU: Rework how private buffer passed for HSA by Matt Arsenault · 10 years ago
ac234b6 AMDGPU: Rename enums to be consistent with HSA code object terminology by Matt Arsenault · 10 years ago
0e3d389 AMDGPU: Remove SIPrepareScratchRegs by Matt Arsenault · 10 years ago
61cb6fa AMDGPU: Remove dead code by Matt Arsenault · 10 years ago
d9d659a AMDGPU: Alphabetize includes by Matt Arsenault · 10 years ago
f1aebbf AMDGPU: Stop assuming vreg for build_vector by Matt Arsenault · 10 years ago
4bf43d4 AMDGPU: Handle i64->v2i32 loads/stores in PreprocessISelDAG by Matt Arsenault · 10 years ago
0a7d0ad Untabify. by NAKAMURA Takumi · 10 years ago
a9cb538 Reformat blank lines. by NAKAMURA Takumi · 10 years ago
8496503 Reformat comment lines. by NAKAMURA Takumi · 10 years ago
966a94f AMDGPU: Handle sub of constant for DS offset folding by Matt Arsenault · 10 years ago
e40c8a2 PseudoSourceValue: Replace global manager with a manager in a machine function. by Alex Lorenz · 10 years ago
217361c AMDGPU/SI: Add support for 32-bit immediate SMRD offsets on CI by Tom Stellard · 10 years ago
dee26a2 AMDGPU/SI: Use ComplexPatterns for SMRD addressing modes by Tom Stellard · 10 years ago
70580f8 AMDGPU/SI: Add VI patterns to select FLAT instructions for global memory ops by Tom Stellard · 10 years ago
78655fc AMDPGU/SI: Negative offsets aren't allowed in MUBUF's vaddr operand by Tom Stellard · 10 years ago
65c6940 Add allnodes() iterator range to SelectionDAG. NFC. by Pete Cooper · 10 years ago
db5a11f AMDGPU/SI: Select mad patterns to v_mac_f32 by Tom Stellard · 10 years ago
706f930 AMDGPU/SI: Add debugging subtarget feature for DS offsets by Matt Arsenault · 10 years ago
45bb48e R600 -> AMDGPU rename by Tom Stellard · 10 years ago[Renamed from llvm/lib/Target/R600/AMDGPUISelDAGToDAG.cpp]
381a94a R600/SI: Remove explicit m0 operand from DS instructions by Tom Stellard · 10 years ago
842a51b Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes" by Sergey Dmitrouk · 11 years ago
48e93f7 Revert "[DebugInfo] Add debug locations to constant SD nodes" by Daniel Jasper · 11 years ago
adb4c69 [DebugInfo] Add debug locations to constant SD nodes by Sergey Dmitrouk · 11 years ago
619c4e5 Reduce dyn_cast<> to isa<> or cast<> where possible. by Benjamin Kramer · 11 years ago
9b72868 R600/SI: Custom-select 32-bit S_BFE from bitwise opcodes by Marek Olsak · 11 years ago
1f9939f R600/SI: Add slc, glc, and tfe to non-atomic _ADDR64 instructions by Tom Stellard · 11 years ago
044f1d1 R600/SI: Use complex operand folding for div_scale by Matt Arsenault · 11 years ago
94b7231 R600/SI: Store immediate offsets > 12-bits in soffset by Tom Stellard · 11 years ago
c53861a R600/SI: Add soffset operand to mubuf addr64 instruction by Tom Stellard · 11 years ago
096b8c1 R600: Don't promote i64 stores to v2i32 during DAG legalization by Tom Stellard · 11 years ago
7792e32 Reuse a bunch of cached subtargets and remove getSubtarget calls by Eric Christopher · 11 years ago
20f6c07 R600/SI: Move i64 -> v2i32 load promotion into AMDGPUDAGToDAGISel::Select() by Tom Stellard · 11 years ago
95292bb R600/SI: Use external symbols for scratch buffer by Tom Stellard · 11 years ago
8058069 R600/SI: Don't store scratch buffer frame index in MUBUF offset field by Tom Stellard · 11 years ago
b655052 R600/SI: Use RegisterOperands to specify which operands can accept immediates by Tom Stellard · 11 years ago
45c0b3a R600/SI: Remove VReg_32 register class by Tom Stellard · 11 years ago
4831ce5 R600/SI: Add class intrinsic by Matt Arsenault · 11 years ago
794c8c0 R600/SI: Set the ATC bit on all resource descriptors for the HSA runtime by Tom Stellard · 11 years ago
1cffa4c R600/SI: Get rid of FCLAMP_SI pseudo by Matt Arsenault · 11 years ago
f3cd451 R600/SI: Move all rsrc building functions to SIISelLowering by Matt Arsenault · 11 years ago
485defe R600/SI: Remove SI_ADDR64_RSRC by Matt Arsenault · 11 years ago
83a535f R600/SI: Remove SI_BUFFER_RSRC pseudo by Matt Arsenault · 11 years ago
c8d7920 R600/SI: Fix bug where immediates were being used in DS addr operands by Tom Stellard · 11 years ago
1a74aff R600/SI: Also try to use 0 base for misaligned 8-byte DS loads. by Matt Arsenault · 11 years ago
e775f5f R600/SI: Use DS offsets for constant addresses by Matt Arsenault · 11 years ago
3457a84 R600/SI: Legalize CopyToReg during instruction selection by Tom Stellard · 11 years ago
272c50a R600/SI: Update VOP3b to not include obsolete operands by Matt Arsenault · 11 years ago
7980fc8 R600/SI: Add support for global atomic add by Tom Stellard · 11 years ago
744b99b R600/SI: Enable selecting SALU inside branches by Tom Stellard · 11 years ago
9f73851 Revert "R600/SI: Add support for global atomic add" by Tom Stellard · 11 years ago
2355a77 R600/SI: Add support for global atomic add by Tom Stellard · 11 years ago