forked from OSchip/llvm-project
1705968102
replacement of multiple values. This is slightly more efficient than doing multiple ReplaceAllUsesOfValueWith calls, and theoretically could be optimized even further. However, an important property of this new function is that it handles the case where the source value set and destination value set overlap. This makes it feasible for isel to use SelectNodeTo in many very common cases, which is advantageous because SelectNodeTo avoids a temporary node and it doesn't require CSEMap updates for users of values that don't change position. Revamp MorphNodeTo, which is what does all the work of SelectNodeTo, to handle operand lists more efficiently, and to correctly handle a number of corner cases to which its new wider use exposes it. This commit also includes a change to the encoding of post-isel opcodes in SDNodes; now instead of being sandwiched between the target-independent pre-isel opcodes and the target-dependent pre-isel opcodes, post-isel opcodes are now represented as negative values. This makes it possible to test if an opcode is pre-isel or post-isel without having to know the size of the current target's post-isel instruction set. These changes speed up llc overall by 3% and reduce memory usage by 10% on the InstructionCombining.cpp testcase with -fast and -regalloc=local. llvm-svn: 53728 |
||
|---|---|---|
| .. | ||
| Alpha.h | ||
| Alpha.td | ||
| AlphaAsmPrinter.cpp | ||
| AlphaBranchSelector.cpp | ||
| AlphaCodeEmitter.cpp | ||
| AlphaISelDAGToDAG.cpp | ||
| AlphaISelLowering.cpp | ||
| AlphaISelLowering.h | ||
| AlphaInstrFormats.td | ||
| AlphaInstrInfo.cpp | ||
| AlphaInstrInfo.h | ||
| AlphaInstrInfo.td | ||
| AlphaJITInfo.cpp | ||
| AlphaJITInfo.h | ||
| AlphaLLRP.cpp | ||
| AlphaRegisterInfo.cpp | ||
| AlphaRegisterInfo.h | ||
| AlphaRegisterInfo.td | ||
| AlphaRelocations.h | ||
| AlphaSchedule.td | ||
| AlphaSubtarget.cpp | ||
| AlphaSubtarget.h | ||
| AlphaTargetAsmInfo.cpp | ||
| AlphaTargetAsmInfo.h | ||
| AlphaTargetMachine.cpp | ||
| AlphaTargetMachine.h | ||
| Makefile | ||
| README.txt | ||
README.txt
*** add gcc builtins for alpha instructions *** custom expand byteswap into nifty extract/insert/mask byte/word/longword/quadword low/high sequences *** see if any of the extract/insert/mask operations can be added *** match more interesting things for cmovlbc cmovlbs (move if low bit clear/set) *** lower srem and urem remq(i,j): i - (j * divq(i,j)) if j != 0 remqu(i,j): i - (j * divqu(i,j)) if j != 0 reml(i,j): i - (j * divl(i,j)) if j != 0 remlu(i,j): i - (j * divlu(i,j)) if j != 0 *** add crazy vector instructions (MVI): (MIN|MAX)(U|S)(B8|W4) min and max, signed and unsigned, byte and word PKWB, UNPKBW pack/unpack word to byte PKLB UNPKBL pack/unpack long to byte PERR pixel error (sum accross bytes of bytewise abs(i8v8 a - i8v8 b)) cmpbytes bytewise cmpeq of i8v8 a and i8v8 b (not part of MVI extentions) this has some good examples for other operations that can be synthesised well from these rather meager vector ops (such as saturating add). http://www.alphalinux.org/docs/MVI-full.html