This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 999a657 [AMDGPU] Implement f16 fcopysign and fcopysign(f32, f64) new f53524b [NVPTX] Added support for half-precision floating point.
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/NVPTX/InstPrinter/NVPTXInstPrinter.cpp | 9 +- lib/Target/NVPTX/NVPTX.h | 3 +- lib/Target/NVPTX/NVPTXAsmPrinter.cpp | 21 +- lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp | 71 +- lib/Target/NVPTX/NVPTXISelDAGToDAG.h | 1 + lib/Target/NVPTX/NVPTXISelLowering.cpp | 88 +- lib/Target/NVPTX/NVPTXISelLowering.h | 1 + lib/Target/NVPTX/NVPTXInstrInfo.cpp | 3 + lib/Target/NVPTX/NVPTXInstrInfo.td | 222 ++++- lib/Target/NVPTX/NVPTXIntrinsics.td | 50 +- lib/Target/NVPTX/NVPTXMCExpr.cpp | 7 + lib/Target/NVPTX/NVPTXMCExpr.h | 10 +- lib/Target/NVPTX/NVPTXRegisterInfo.cpp | 48 +- lib/Target/NVPTX/NVPTXRegisterInfo.td | 2 + lib/Target/NVPTX/NVPTXSubtarget.cpp | 9 + lib/Target/NVPTX/NVPTXSubtarget.h | 2 + test/CodeGen/NVPTX/f16-instructions.ll | 1034 +++++++++++++++++++++ test/CodeGen/NVPTX/half.ll | 8 +- 18 files changed, 1487 insertions(+), 102 deletions(-) create mode 100644 test/CodeGen/NVPTX/f16-instructions.ll