Log - 7a8317c09ae041b5058a78028836cd94e22651b4 - toolchain/llvm-project

4c1ecde AMDGPU: Change DivergenceAnalysis for function arguments by Matt Arsenault · 9 years ago
f021fab [IR] Make getParamAttributes take argument numbers, not ArgNo+1 by Reid Kleckner · 9 years ago
478b819 [AMDGPU] Unroll more to eliminate phis and conditions by Stanislav Mekhanoshin · 9 years ago
baf31ac [AMDGPU] Boost unroll threshold for loops reading local memory by Stanislav Mekhanoshin · 9 years ago
1a14bfa [AMDGPU] Get address space mapping by target triple environment by Yaxun Liu · 9 years ago
1be9b9f AMDGPU/SI: Disable unrolling in the loop vectorizer if the loop is not vectorized. by Changpeng Fang · 9 years ago
f0a88db LoadStoreVectorizer: Split even sized illegal chains properly by Matt Arsenault · 9 years ago
d2c8a33 AMDGPU: Remove SI_fs_constant and SI_fs_interp intrinsics by Matt Arsenault · 9 years ago
81db531 [AMDGPU] Bump -amdgpu-unroll-threshold-private to 2000 by Stanislav Mekhanoshin · 9 years ago
d9cd736 AMDGPU: Don't unroll for private with dynamic allocas by Matt Arsenault · 9 years ago
f29602d [AMDGPU] Unroll preferences improvements by Stanislav Mekhanoshin · 9 years ago
41c1499 AMDGPU: Fix atomic_inc/atomic_dec + ds_swizzle not being divergent by Matt Arsenault · 9 years ago
2c96c43 [X86] updating TTI costs for arithmetic instructions on X86\SLM arch. by Mohammed Agabaria · 9 years ago
f45ea4b AMDGPU: llvm.amdgcn.interp.mov is a source of divergence by Nicolai Haehnle · 9 years ago
1c38681 Add new target hooks for LoadStoreVectorizer by Volkan Keles · 9 years ago
0994bd5 AMDGPU: Implement getLoadStoreVecRegBitWidth by Matt Arsenault · 9 years ago
8885910 AMDGPU: Remove llvm.SI.tid intrinsic by Matt Arsenault · 9 years ago
119d3d8 AMDGPU: llvm.SI.fs.constant is a source of divergence by Nicolai Haehnle · 10 years ago
b0c9748 AMDGPU/SI: add llvm.amdgcn.ps.live intrinsic by Nicolai Haehnle · 10 years ago
df3a20c AMDGPU: Add a shader calling convention by Nicolai Haehnle · 10 years ago
8c8fcb2 AMDGPU: Cost model for basic integer operations by Matt Arsenault · 10 years ago
9651813 AMDGPU: Partially implement getArithmeticInstrCost for FP ops by Matt Arsenault · 10 years ago
59767ce AMDGPU: TTI: Make insertelement free. by Matt Arsenault · 10 years ago
ad63638 AMDGPU/SI: Add llvm.amdgcn.buffer.atomic.* intrinsics by Nicolai Haehnle · 10 years ago
79cad85 AMDGPU: mark atomic instructions as sources of divergence by Nicolai Haehnle · 10 years ago
74127fe8 AMDGPU: mark llvm.amdgcn.image.atomic.* as a source of divergence by Nicolai Haehnle · 10 years ago
bc4497b AMDGPU/SI: Detect uniform branches and emit s_cbranch instructions by Tom Stellard · 10 years ago
fe26def AMDGPU: Fix not handling new workitem intrinsics in DivergenceAnalysis by Matt Arsenault · 10 years ago
4339b3f AMDGPU: Fix getRegisterBitWidth for vectors by Matt Arsenault · 10 years ago
ffc1a5a AMDGPU/SI: Fix implemenation of isSourceOfDivergence() for graphics shaders by Tom Stellard · 10 years ago
e05ff15 AMDGPU: Override getCFInstrCost by Matt Arsenault · 10 years ago
dbe374b AMDGPU/SI: Implement AMDGPUTargetTransformInfo::isSourceOfDivergence() by Tom Stellard · 10 years ago
e830f54 AMDGPU: Report extractelement as free in cost model by Matt Arsenault · 10 years ago
45bb48e R600 -> AMDGPU rename by Tom Stellard · 10 years ago[Renamed from llvm/lib/Target/R600/AMDGPUTargetTransformInfo.cpp]
062c744 [X86] Disable loop unrolling in loop vectorization pass when VF is 1. by Wei Mi · 11 years ago
a28d91d DataLayout is mandatory, update the API to reflect it with references. by Mehdi Amini · 11 years ago
eea3f70 R600/SI: Fix bug in TTI loop unrolling preferences by Tom Stellard · 11 years ago
ab5cb36 [multiversion] Remove the function parameter from the unrolling by Chandler Carruth · 11 years ago
93dcdc4 [PM] Switch the TargetMachine interface from accepting a pass manager by Chandler Carruth · 11 years ago
705b185 [PM] Change the core design of the TTI analysis to use a polymorphic by Chandler Carruth · 11 years ago
a41cf01 Fix broken doxygen annotations, NFC by Jingyue Wu · 11 years ago
d85ffb1 Add a new pass FunctionTargetTransformInfo. This pass serves as a by Eric Christopher · 11 years ago
b653de1 Rename getMaximumUnrollFactor -> getMaxInterleaveFactor; also rename option names controlling this variable. by Sanjay Patel · 11 years ago
d913448 Remove the TargetMachine forwards for TargetSubtargetInfo based by Eric Christopher · 11 years ago
c824458 R600/SI: Allow partial unrolling and increase thresholds. by Matt Arsenault · 11 years ago
1c407fb Revert accidentally committed r213459 by Matt Arsenault · 11 years ago
b38677e XXX - Increase unroll threshold by Matt Arsenault · 11 years ago
a93441f R600: Implement a few simple TTI queries. by Matt Arsenault · 11 years ago
3dd43fc R600: Implement TTI:getPopcntSupport by Matt Arsenault · 11 years ago
ac6e39c Use range for by Matt Arsenault · 11 years ago
5e2b0f5 R600: Short circuit alloca check if address space isn't private. by Matt Arsenault · 11 years ago
5656db4 [C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. R600 edition by Craig Topper · 12 years ago
062a2ba [C++] Use 'nullptr'. Target edition. by Craig Topper · 12 years ago
84e68b2 [Modules] Fix potential ODR violations by sinking the DEBUG_TYPE by Chandler Carruth · 12 years ago
5e1e431 Fix tabs by Matt Arsenault · 12 years ago
aee3ca6 [TTI] There is actually no realistic way to pop TTI implementations off by Chandler Carruth · 12 years ago
7315602 Switch all uses of LLVM_OVERRIDE to just use 'override' directly. by Craig Topper · 12 years ago
77dfe45 Switch all uses of LLVM_FINAL to just use 'final', and remove the macro. by Craig Topper · 12 years ago
fd0d86c R600: Don't unconditionally unroll loops with private memory accesses by Tom Stellard · 12 years ago
3e752e7 Add final and owerride keywords to TargetTransformInfo's subclasses. by Juergen Ributzka · 12 years ago
8cce9bd R600: Unconditionally unroll loops that contain GEPs with alloca pointers by Tom Stellard · 12 years ago
8a8cd2b Re-sort all of the includes with ./utils/sort_includes.py so that by Chandler Carruth · 12 years ago
8b1e021 SimplifyCFG: Use parallel-and and parallel-or mode to consolidate branch conditions by Tom Stellard · 12 years ago