Changes in directory llvm/lib/Target/X86:
README.txt updated: 1.14 -> 1.15 --- Log message: Put some of my random notes somewhere public --- Diffs of the changes: (+70 -0) README.txt | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 70 insertions(+) Index: llvm/lib/Target/X86/README.txt diff -u /dev/null llvm/lib/Target/X86/README.txt:1.15 --- /dev/null Sun Oct 23 14:52:52 2005 +++ llvm/lib/Target/X86/README.txt Sun Oct 23 14:52:42 2005 @@ -0,0 +1,70 @@ +//===---------------------------------------------------------------------===// +// 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. + _______________________________________________ llvm-commits mailing list llvm-commits@cs.uiuc.edu http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits