Skip to content
  1. Mar 09, 2004
  3. Mar 08, 2004
    • Chris Lattner's avatar
      Implement folding explicit load instructions into binary operations. For a · 653e662a
      Chris Lattner authored 
      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
      653e662a
    • Chris Lattner's avatar
      Rearrange and refactor some code. No functionality changes. · 1dd6afe6
      Chris Lattner authored 
      llvm-svn: 12203
      1dd6afe6
  5. Mar 07, 2004
  7. Mar 04, 2004
  9. Mar 02, 2004
  11. Mar 01, 2004
    • Brian Gaeke's avatar
      TargetCacheInfo has been removed; its only uses were to propagate a constant · 427cec13
      Brian Gaeke authored 
      (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
      427cec13
    • Chris Lattner's avatar
      Handle passing constant integers to functions much more efficiently. Instead · 1f4642c4
      Chris Lattner authored 
      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
      1f4642c4
    • Chris Lattner's avatar
      Fix a minor code-quality issue. When passing 8 and 16-bit integer constants · 5c7d3cda
      Chris Lattner authored 
      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
      5c7d3cda
  13. Feb 29, 2004
  15. Feb 28, 2004
  17. Feb 27, 2004
  19. Feb 26, 2004
  21. Feb 25, 2004
    • Chris Lattner's avatar
      Fix failures in 099.go due to the cfgsimplify pass creating switch instructions · 64c9b223
      Chris Lattner authored 
      where there did not used to be any before

llvm-svn: 11829
      64c9b223
    • Chris Lattner's avatar
      Teach the instruction selector how to transform 'array' GEP computations into X86 · 309327a4
      Chris Lattner authored 
      scaled indexes.  This allows us to compile GEP's like this:

int* %test([10 x { int, { int } }]* %X, int %Idx) {
        %Idx = cast int %Idx to long
        %X = getelementptr [10 x { int, { int } }]* %X, long 0, long %Idx, ubyte 1, ubyte 0
        ret int* %X
}

Into a single address computation:

test:
        mov %EAX, DWORD PTR [%ESP + 4]
        mov %ECX, DWORD PTR [%ESP + 8]
        lea %EAX, DWORD PTR [%EAX + 8*%ECX + 4]
        ret

Before it generated:
test:
        mov %EAX, DWORD PTR [%ESP + 4]
        mov %ECX, DWORD PTR [%ESP + 8]
        shl %ECX, 3
        add %EAX, %ECX
        lea %EAX, DWORD PTR [%EAX + 4]
        ret

This is useful for things like int/float/double arrays, as the indexing can be folded into
the loads&stores, reducing register pressure and decreasing the pressure on the decode unit.
With these changes, I expect our performance on 256.bzip2 and gzip to improve a lot.  On
bzip2 for example, we go from this:

10665 asm-printer           - Number of machine instrs printed
   40 ra-local              - Number of loads/stores folded into instructions
 1708 ra-local              - Number of loads added
 1532 ra-local              - Number of stores added
 1354 twoaddressinstruction - Number of instructions added
 1354 twoaddressinstruction - Number of two-address instructions
 2794 x86-peephole          - Number of peephole optimization performed

to this:
9873 asm-printer           - Number of machine instrs printed
  41 ra-local              - Number of loads/stores folded into instructions
1710 ra-local              - Number of loads added
1521 ra-local              - Number of stores added
 789 twoaddressinstruction - Number of instructions added
 789 twoaddressinstruction - Number of two-address instructions
2142 x86-peephole          - Number of peephole optimization performed

... and these types of instructions are often in tight loops.

Linear scan is also helped, but not as much.  It goes from:

8787 asm-printer           - Number of machine instrs printed
2389 liveintervals         - Number of identity moves eliminated after coalescing
2288 liveintervals         - Number of interval joins performed
3522 liveintervals         - Number of intervals after coalescing
5810 liveintervals         - Number of original intervals
 700 spiller               - Number of loads added
 487 spiller               - Number of stores added
 303 spiller               - Number of register spills
1354 twoaddressinstruction - Number of instructions added
1354 twoaddressinstruction - Number of two-address instructions
 363 x86-peephole          - Number of peephole optimization performed

to:

7982 asm-printer           - Number of machine instrs printed
1759 liveintervals         - Number of identity moves eliminated after coalescing
1658 liveintervals         - Number of interval joins performed
3282 liveintervals         - Number of intervals after coalescing
4940 liveintervals         - Number of original intervals
 635 spiller               - Number of loads added
 452 spiller               - Number of stores added
 288 spiller               - Number of register spills
 789 twoaddressinstruction - Number of instructions added
 789 twoaddressinstruction - Number of two-address instructions
 258 x86-peephole          - Number of peephole optimization performed

Though I'm not complaining about the drop in the number of intervals.  :)

llvm-svn: 11820
      309327a4