mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-10-31 09:11:13 +00:00
78432feff8
Evan Cheng. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@24384 91177308-0d34-0410-b5e6-96231b3b80d8 |
||
---|---|---|
.. | ||
.cvsignore | ||
Makefile | ||
README.txt | ||
X86.h | ||
X86.td | ||
X86AsmPrinter.cpp | ||
X86AsmPrinter.h | ||
X86ATTAsmPrinter.cpp | ||
X86ATTAsmPrinter.h | ||
X86CodeEmitter.cpp | ||
X86ELFWriter.cpp | ||
X86FloatingPoint.cpp | ||
X86InstrBuilder.h | ||
X86InstrInfo.cpp | ||
X86InstrInfo.h | ||
X86InstrInfo.td | ||
X86IntelAsmPrinter.cpp | ||
X86IntelAsmPrinter.h | ||
X86ISelDAGToDAG.cpp | ||
X86ISelLowering.cpp | ||
X86ISelLowering.h | ||
X86ISelPattern.cpp | ||
X86JITInfo.cpp | ||
X86JITInfo.h | ||
X86PeepholeOpt.cpp | ||
X86RegisterInfo.cpp | ||
X86RegisterInfo.h | ||
X86RegisterInfo.td | ||
X86Relocations.h | ||
X86Subtarget.cpp | ||
X86Subtarget.h | ||
X86TargetMachine.cpp | ||
X86TargetMachine.h |
//===---------------------------------------------------------------------===// // Random ideas for the X86 backend. //===---------------------------------------------------------------------===// Add a MUL2U and MUL2S nodes to represent a multiply that returns both the Hi and Lo parts (combination of MUL and MULH[SU] into one node). Add this to X86, & make the dag combiner produce it when needed. This will eliminate one imul from the code generated for: long long test(long long X, long long Y) { return X*Y; } by using the EAX result from the mul. We should add a similar node for DIVREM. //===---------------------------------------------------------------------===// This should be one DIV/IDIV instruction, not a libcall: unsigned test(unsigned long long X, unsigned Y) { return X/Y; } This can be done trivially with a custom legalizer. What about overflow though? http://gcc.gnu.org/bugzilla/show_bug.cgi?id=14224 //===---------------------------------------------------------------------===// Need to add support for rotate instructions. //===---------------------------------------------------------------------===// Some targets (e.g. athlons) prefer freep to fstp ST(0): http://gcc.gnu.org/ml/gcc-patches/2004-04/msg00659.html //===---------------------------------------------------------------------===// This should use faddi on chips where it is profitable: double foo(double P, int *I) { return P+*I; } //===---------------------------------------------------------------------===// The FP stackifier needs to be global. Also, it should handle simple permutates to reduce number of shuffle instructions, e.g. turning: fld P -> fld Q fld Q fld P fxch or: fxch -> fucomi fucomi jl X jg X //===---------------------------------------------------------------------===// Improvements to the multiply -> shift/add algorithm: http://gcc.gnu.org/ml/gcc-patches/2004-08/msg01590.html //===---------------------------------------------------------------------===// Improve code like this (occurs fairly frequently, e.g. in LLVM): long long foo(int x) { return 1LL << x; } http://gcc.gnu.org/ml/gcc-patches/2004-09/msg01109.html http://gcc.gnu.org/ml/gcc-patches/2004-09/msg01128.html http://gcc.gnu.org/ml/gcc-patches/2004-09/msg01136.html Another useful one would be ~0ULL >> X and ~0ULL << X. //===---------------------------------------------------------------------===// Should support emission of the bswap instruction, probably by adding a new DAG node for byte swapping. Also useful on PPC which has byte-swapping loads.