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

1 files changed, 6 insertions, 0 deletions

diff --git a/llvm/lib/Target/TargetMachine.cpp b/llvm/lib/Target/TargetMachine.cpp
index f4b9039f482..90f10c1fccb 100644
--- a/llvm/lib/Target/TargetMachine.cpp
+++ b/llvm/lib/Target/TargetMachine.cpp
@@ -27,6 +27,7 @@ namespace llvm {
   bool NoExcessFPPrecision;
   int  PatternISelTriState;
   bool UnsafeFPMath;
+  bool PICEnabled;
 };
 namespace {
   cl::opt<bool, true> PrintCode("print-machineinstrs",
@@ -52,6 +53,11 @@ namespace {
                cl::desc("Enable optimizations that may decrease FP precision"),
                cl::location(UnsafeFPMath),
                cl::init(false));
+  cl::opt<bool, true>
+  EnablePIC("enable-pic",
+               cl::desc("Enable generation of position independant code"),
+               cl::location(PICEnabled),
+               cl::init(false));
 };
 
 //---------------------------------------------------------------------------