llvm-svn: 12587

llvm-svn: 12579

llvm-svn: 12578

the X86 does not support a full set of fp cmove instructions, so we can't always
fold the condition into the select.  :(  Yuck.

llvm-svn: 12577

llvm-svn: 12576

llvm-svn: 12575

that require the asmwriter to be extended (printing implicit uses before the
explicit operands)

llvm-svn: 12574

using our broad selection of movcc instructions.  :)

llvm-svn: 12560

llvm-svn: 12554

folding compares into the select yet.

llvm-svn: 12553

we never generated them

Make indentation a bit more consistent

llvm-svn: 12549

an incoming value from a block, the selector would evaluate the constant
at the TOP of the block instead of at the end of the block.  This made the
live range for the constant span the entire block, increasing register
pressure needlessly.

llvm-svn: 12542

llvm-svn: 12541

llvm-svn: 12500

folding load instructions into other instructions across free instruction
boundaries.  Perhaps this will also fix the other strange failures?

llvm-svn: 12494

llvm-svn: 12424

MachineBasicBlock::iterator take a MachineInstr*.

llvm-svn: 12392

instruction to make the API more flexible.

llvm-svn: 12386

llvm-svn: 12357

Intrinsic::va*.  This avoid conflicting with macros in the stdlib.h file.

llvm-svn: 12356

llvm-svn: 12336

llvm-svn: 12289

instructions.

llvm-svn: 12258

llvm-svn: 12254

llvm-svn: 12253

llvm-svn: 12252

llvm-svn: 12251

testcase like this:

int %test(int* %P, int %A) {
        %Pv = load int* %P
        %B = add int %A, %Pv
        ret int %B
}

We now generate:
test:
        mov %ECX, DWORD PTR [%ESP + 4]
        mov %EAX, DWORD PTR [%ESP + 8]
        add %EAX, DWORD PTR [%ECX]
        ret

Instead of:
test:
        mov %EAX, DWORD PTR [%ESP + 4]
        mov %ECX, DWORD PTR [%ESP + 8]
        mov %EAX, DWORD PTR [%EAX]
        add %EAX, %ECX
        ret

... saving one instruction, and often a register.  Note that there are a lot
of other instructions that could use this, but they aren't handled.  I'm not
really interested in adding them, but mul/div and all of the FP instructions
could be supported as well if someone wanted to add them.

llvm-svn: 12204

llvm-svn: 12203

llvm-svn: 12190

llvm-svn: 12122

llvm-svn: 12120

llvm-svn: 12064

(16) into certain areas of the SPARC V9 back-end. I'm fairly sure the US IIIi's
dcache has 32-byte lines, so I'm not sure where the 16 came from. However, in
the interest of not breaking things any more than they already are, I'm going
to leave the constant alone.

llvm-svn: 12043

of generating this code:

        mov %EAX, 4
        mov DWORD PTR [%ESP], %EAX
        mov %AX, 123
        movsx %EAX, %AX
        mov DWORD PTR [%ESP + 4], %EAX
        call Y

we now generate:
        mov DWORD PTR [%ESP], 4
        mov DWORD PTR [%ESP + 4], 123
        call Y

Which hurts the eyes less.  :)

Considering that register pressure around call sites is already high (with all
of the callee clobber registers n stuff), this may help a lot.

llvm-svn: 12028

to function calls, we would emit dead code, like this:

int Y(int, short, double);
int X() {
  Y(4, 123, 4);
}

--- Old
X:
        sub %ESP, 20
        mov %EAX, 4
        mov DWORD PTR [%ESP], %EAX
***     mov %AX, 123
        mov %AX, 123
        movsx %EAX, %AX
        mov DWORD PTR [%ESP + 4], %EAX
        fld QWORD PTR [.CPIX_0]
        fstp QWORD PTR [%ESP + 8]
        call Y
        mov %EAX, 0
        # IMPLICIT_USE %EAX %ESP
        add %ESP, 20
        ret

Now we emit:
X:
        sub %ESP, 20
        mov %EAX, 4
        mov DWORD PTR [%ESP], %EAX
        mov %AX, 123
        movsx %EAX, %AX
        mov DWORD PTR [%ESP + 4], %EAX
        fld QWORD PTR [.CPIX_0]
        fstp QWORD PTR [%ESP + 8]
        call Y
        mov %EAX, 0
        # IMPLICIT_USE %EAX %ESP
        add %ESP, 20
        ret

Next up, eliminate the mov AX and movsx entirely!

llvm-svn: 12026

llvm-svn: 11998

operand size is correctly specified.

llvm-svn: 11997

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

their names more decriptive. A name consists of the base name, a
default operand size followed by a character per operand with an
optional special size. For example:

ADD8rr -> add, 8-bit register, 8-bit register

IMUL16rmi -> imul, 16-bit register, 16-bit memory, 16-bit immediate

IMUL16rmi8 -> imul, 16-bit register, 16-bit memory, 8-bit immediate

MOVSX32rm16 -> movsx, 32-bit register, 16-bit memory

llvm-svn: 11995