This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 38ece52d643 [CostModel][X86] Add explicit fcmp costs for pre-SSE42 targets new 21d100aff8a [CostModel][X86] Add explicit vector select costs
The 1 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "adds" were already present in the repository and have only been added to this reference.
Summary of changes: lib/Target/X86/X86TargetTransformInfo.cpp | 41 ++++ test/Analysis/CostModel/X86/fshl.ll | 269 ++++++++++++--------- test/Analysis/CostModel/X86/fshr.ll | 269 ++++++++++++--------- test/Analysis/CostModel/X86/reduce-smax-widen.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-smax.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-smin-widen.ll | 96 ++++---- test/Analysis/CostModel/X86/reduce-smin.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-umax-widen.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-umax.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-umin-widen.ll | 100 ++++---- test/Analysis/CostModel/X86/reduce-umin.ll | 100 ++++---- test/Analysis/CostModel/X86/vselect-cost.ll | 221 ++++++++++++----- .../LoopVectorize/X86/imprecise-through-phis.ll | 135 ++++++----- .../LoopVectorize/X86/vector-scalar-select-cost.ll | 2 +- test/Transforms/SLPVectorizer/X86/crash_cmpop.ll | 124 +++++++--- .../SLPVectorizer/X86/horizontal-minmax.ll | 90 +++---- 16 files changed, 1109 insertions(+), 838 deletions(-)