llvm-6502/lib/Target/X86
2005-11-21 07:16:34 +00:00
..
.cvsignore ignore generated files 2004-11-21 00:01:54 +00:00
Makefile initial step at adding a dag-to-dag isel for X86 backend. Patch contributed 2005-11-16 01:54:32 +00:00
README.txt add a note that Nate mentioned last week 2005-10-23 21:44:59 +00:00
X86.h Separate X86ISelLowering stuff out from the X86ISelPattern.cpp file. Patch 2005-11-15 00:40:23 +00:00
X86.td Get closer to fully working scalar FP in SSE regs. This gets singlesource 2005-07-15 00:38:55 +00:00
X86AsmPrinter.cpp convert the rest of this over to use SwitchSection 2005-11-21 07:16:34 +00:00
X86AsmPrinter.h Start using the AsmPrinter shared SwitchSection code. This allows the X86 2005-11-21 07:11:11 +00:00
X86ATTAsmPrinter.cpp convert the rest of this over to use SwitchSection 2005-11-21 07:16:34 +00:00
X86ATTAsmPrinter.h Add support for printing the sse scalar comparison instruction mnemonics. 2005-07-14 22:52:25 +00:00
X86CodeEmitter.cpp Refactor things a bit to allow the ELF code emitter to run the X86 machine code emitter 2005-07-11 05:17:48 +00:00
X86ELFWriter.cpp Refactor things a bit to allow the ELF code emitter to run the X86 machine code emitter 2005-07-11 05:17:48 +00:00
X86FloatingPoint.cpp Adjust to new livevars interface 2005-08-23 23:41:14 +00:00
X86InstrBuilder.h * Remove trailing whitespace 2005-04-21 23:38:14 +00:00
X86InstrInfo.cpp Properly split f32 and f64 into separate register classes for scalar sse fp 2005-10-14 22:06:00 +00:00
X86InstrInfo.h Eliminate tabs and trailing spaces. 2005-07-27 05:53:44 +00:00
X86InstrInfo.td encode rdtsc correctly 2005-11-20 22:13:18 +00:00
X86IntelAsmPrinter.cpp convert the rest of this over to use SwitchSection 2005-11-21 07:16:34 +00:00
X86IntelAsmPrinter.h Add support for printing the sse scalar comparison instruction mnemonics. 2005-07-14 22:52:25 +00:00
X86ISelDAGToDAG.cpp Add load and other support to the dag-dag isel. Patch contributed by Evan 2005-11-19 02:11:08 +00:00
X86ISelLowering.cpp Lower READCYCLECOUNTER correctly, preserving the chain result 2005-11-20 22:57:19 +00:00
X86ISelLowering.h The second patch of X86 support for read cycle counter. 2005-11-20 21:41:10 +00:00
X86ISelPattern.cpp The second patch of X86 support for read cycle counter. 2005-11-20 21:41:10 +00:00
X86JITInfo.cpp update interface 2005-07-22 20:49:37 +00:00
X86JITInfo.h turn off GOT on archs that didn't use it (not that it appeard to harm them much with it on) 2005-07-29 23:32:02 +00:00
X86PeepholeOpt.cpp Eliminate all remaining tabs and trailing spaces. 2005-07-27 06:12:32 +00:00
X86RegisterInfo.cpp Properly split f32 and f64 into separate register classes for scalar sse fp 2005-10-14 22:06:00 +00:00
X86RegisterInfo.h Pass extra regclasses into spilling code 2005-09-30 01:29:42 +00:00
X86RegisterInfo.td Properly split f32 and f64 into separate register classes for scalar sse fp 2005-10-14 22:06:00 +00:00
X86Relocations.h * Remove trailing whitespace 2005-04-21 23:38:14 +00:00
X86Subtarget.cpp 1. Use SubtargetFeatures in llc/lli. 2005-09-01 21:38:21 +00:00
X86Subtarget.h 1. Use SubtargetFeatures in llc/lli. 2005-09-01 21:38:21 +00:00
X86TargetMachine.cpp initial step at adding a dag-to-dag isel for X86 backend. Patch contributed 2005-11-16 01:54:32 +00:00
X86TargetMachine.h Add a new option to indicate we want the code generator to emit code quickly,not spending tons of time microoptimizing it. This is useful for an -O0style of build. 2005-11-08 02:11:51 +00:00

//===---------------------------------------------------------------------===//
// 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.