1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-29 23:12:55 +01:00
Commit Graph

27 Commits

Author SHA1 Message Date
Evan Cheng
e458553c73 Bye bye HACKTROCITY.
llvm-svn: 24935
2005-12-22 02:26:21 +00:00
Evan Cheng
0226113ed5 * Added lowering hook for external weak global address. It inserts a load
for Darwin.
* Added lowering hook for ISD::RET. It inserts CopyToRegs for the return
  value (or store / fld / copy to ST(0) for floating point value). This
  eliminate the need to write C++ code to handle RET with variable number
  of operands.

llvm-svn: 24888
2005-12-21 02:39:21 +00:00
Evan Cheng
ace8f1fafa SSE2 floating point load / store patterns. SSE2 fp to int conversion patterns.
llvm-svn: 24886
2005-12-20 22:59:51 +00:00
Evan Cheng
5d90b26707 Added support for cmp, test, and conditional move instructions.
llvm-svn: 24756
2005-12-17 01:24:02 +00:00
Nate Begeman
811a41a87c Support multiple ValueTypes per RegisterClass, needed for upcoming vector
work.  This change has no effect on generated code.

llvm-svn: 24563
2005-12-01 04:51:06 +00:00
Nate Begeman
3b6c2df603 Properly split f32 and f64 into separate register classes for scalar sse fp
fixing a bunch of nasty hackery

llvm-svn: 23735
2005-10-14 22:06:00 +00:00
Chris Lattner
2ac3fd08d2 Split RegisterClass 'Methods' into MethodProtos and MethodBodies
llvm-svn: 22929
2005-08-19 19:13:20 +00:00
Chris Lattner
f86654ffde Put register classes into namespaces
llvm-svn: 22925
2005-08-19 18:51:57 +00:00
Nate Begeman
e5314eb2c2 First round of support for doing scalar FP using the SSE2 ISA extension and
XMM registers.  There are many known deficiencies and fixmes, which will be
addressed ASAP.  The major benefit of this work is that it will allow the
LLVM register allocator to allocate FP registers across basic blocks.

The x86 backend will still default to x87 style FP.  To enable this work,
you must pass -enable-sse-scalar-fp and either -sse2 or -sse3 to llc.

An example before and after would be for:
double foo(double *P) { double Sum = 0; int i; for (i = 0; i < 1000; ++i)
                        Sum += P[i]; return Sum; }

The inner loop looks like the following:
x87:
.LBB_foo_1:     # no_exit
        fldl (%esp)
        faddl (%eax,%ecx,8)
        fstpl (%esp)
        incl %ecx
        cmpl $1000, %ecx
        #FP_REG_KILL
        jne .LBB_foo_1  # no_exit

SSE2:
        addsd (%eax,%ecx,8), %xmm0
        incl %ecx
        cmpl $1000, %ecx
        #FP_REG_KILL
        jne .LBB_foo_1  # no_exit

llvm-svn: 22340
2005-07-06 18:59:04 +00:00
Nate Begeman
032a94775d Initial set of .td file changes necessary to get scalar fp in xmm registers
working.  The instruction selector changes will hopefully be coming later
this week once they are debugged.  This is necessary to support the darwin
x86 FP model, and is recommended by intel as the replacement for x87.  As
a bonus, the register allocator knows how to deal with these registers
across basic blocks, unliky the FP stackifier.  This leads to significantly
better codegen in several cases.

llvm-svn: 22300
2005-06-27 21:20:31 +00:00
Chris Lattner
b438f5251f Minor optimization to allocate R8 registers in a better order.
llvm-svn: 19289
2005-01-05 16:09:16 +00:00
Chris Lattner
316f923a9c Spill/restore X86 floating point stack registers with 64-bits of precision
instead of 80-bits of precision.  This fixes PR467.

This change speeds up fldry on X86 with LLC from 7.32s on apoc to 4.68s.

llvm-svn: 18433
2004-12-02 18:17:31 +00:00
Alkis Evlogimenos
3f8f30bcb8 The real x87 floating point registers should not be allocatable. They
are only used by the stackifier when transforming FPn register
allocations to the real stack file x87 registers.

llvm-svn: 16472
2004-09-21 21:22:11 +00:00
Misha Brukman
9e5af08ef9 Fit long lines into 80 cols via creative space elimination
llvm-svn: 16353
2004-09-15 01:40:18 +00:00
Chris Lattner
aee36bb527 Revamp the Register class, and allow the use of the RegisterGroup class to
specify aliases directly in register definitions.

Patch contributed by Jason Eckhardt!

llvm-svn: 16330
2004-09-14 04:17:02 +00:00
Chris Lattner
28c7ae5697 Nuke commented out stuff
llvm-svn: 16017
2004-08-24 08:18:27 +00:00
Chris Lattner
64d3bc5e85 Switch from bytes to bits for alignment for consistency
llvm-svn: 15974
2004-08-21 20:14:13 +00:00
Chris Lattner
c40aa40525 give FP stack registers names
llvm-svn: 15394
2004-08-01 08:12:13 +00:00
Alkis Evlogimenos
10f4523e9a Improve allocation order:
1) For 8-bit registers try to use first the ones that are parts of the
   same register (AL then AH). This way we only alias 2 16/32-bit
   registers after allocating 4 8-bit variables.

2) Move EBX as the last register to allocate. This will cause less
   spills to happen since we will have 8-bit registers available up to
   register excaustion (assuming we use the allocation order). It
   would be nice if we could push all of the 8-bit aliased registers
   towards the end but we much prefer to keep callee saved register to
   the end to avoid saving them on entry and exit of the function.

For example this gives a slight reduction of spills with linear scan
on 164.gzip.

Before:

11221 asm-printer           - Number of machine instrs printed
  975 spiller               - Number of loads added
  675 spiller               - Number of stores added
  398 spiller               - Number of register spills

After:

11182 asm-printer           - Number of machine instrs printed
  952 spiller               - Number of loads added
  652 spiller               - Number of stores added
  386 spiller               - Number of register spills

llvm-svn: 11996
2004-02-29 09:17:01 +00:00
John Criswell
de34542f41 Added LLVM copyright header.
llvm-svn: 9321
2003-10-21 15:17:13 +00:00
Misha Brukman
caed7aad11 Converted tabs to spaces.
llvm-svn: 7728
2003-08-11 15:38:50 +00:00
Chris Lattner
a263312e82 This register is never used, disable it.
llvm-svn: 7661
2003-08-07 04:49:16 +00:00
Chris Lattner
cd1aec5a9d Rename register classes to be upper case to make it obvious that they are X86
specific in the tree patterns

llvm-svn: 7578
2003-08-04 20:58:29 +00:00
Chris Lattner
0d7b042206 transition to using let instead of set
llvm-svn: 7564
2003-08-04 04:59:56 +00:00
Chris Lattner
e9a18e0f9f Specify custom name for registers to get the ()'s in the name.
llvm-svn: 7547
2003-08-03 22:12:47 +00:00
Chris Lattner
6b3f365906 The RegisterInfo class is obsolete
llvm-svn: 7522
2003-08-03 18:18:48 +00:00
Chris Lattner
f4bfcad4ea Initial checkin of X86 Register File description
llvm-svn: 7509
2003-08-03 15:47:25 +00:00