Re: Some platform-specific MemSet research

Martijn van Oosterhout wrote:
> On Tue, Jan 24, 2006 at 05:24:28PM -0500, Seneca Cunningham wrote:
>
>>After reading the post on -patches proposing that MemSet be changed to
>>use long instead of int32 on the grounds that a pair of x86-64 linux
>>boxes took less time to execute the long code 64*10^6 times[1], I took a
>>look at how the testcode performed on AIX with gcc. While the switch to
>>long did result in a minor performance improvement, dropping the
>>MemSetLoop in favour of the native memset resulted in the tests taking
>>~25% the time as the MemSetLoop-like int loop. The 32-bit linux system I
>>ran the expanded tests on showed that for the buffer size range that
>>postgres can use the looping MemSet instead of memset (size <= 1024
>>bytes), MemSet generally had better performance.
>
>
> Could you please check the asm output to see what's going on. We've had
> tests like these produce odd results in the past because the compiler
> optimised away stuff that didn't have any effect. Since every memset
> after the first is a no-op, you want to make sure it's still actually
> doing the work...

Well, on both linux and AIX, all 30 of the 64000000 iterations loops
from the source exist (10 int, 10 long, 10 memset). According to my
understanding of the assembler, memset itself is only called for values
>= 64 bytes on both platforms and the memset is called in each iteration.

The assembler for the 64 byte loops, with prepended line number, first
loop MemSetLoop int-variant, second loop memset, third loop MemSetLoop
long-variant:

64-bit AIX:

419 addi 3,1,112
420 li 4,0
421 bl .gettimeofday
422 nop
423 lis 10,0x3d0
424 cmpld 6,26,16
425 li 11,0
426 ori 10,10,36864
427 L..41:
428 bge 6,L..42
429 mr 9,26
430 li 0,0
431 L..44:
432 stw 0,0(9)
433 addi 9,9,4
434 cmpld 7,16,9
435 bgt 7,L..44
436 L..42:
437 addi 0,11,1
438 extsw 11,0
439 cmpw 7,11,10
440 bne+ 7,L..41
441 li 4,0
442 mr 3,22
443 lis 25,0x3d0
444 li 28,0
445 bl .gettimeofday
446 nop
447 li 4,64
448 addi 5,1,112
449 ld 3,LC..9(2)
450 mr 6,22
451 ori 25,25,36864
452 bl .print_time
453 addi 3,1,112
454 li 4,0
455 bl .gettimeofday
456 nop
457 L..46:
458 mr 3,26
459 li 4,0
460 li 5,64
461 bl .memset
462 nop
463 addi 0,28,1
464 extsw 28,0
465 cmpw 7,28,25
466 bne+ 7,L..46
467 li 4,0
468 mr 3,22
469 bl .gettimeofday
470 nop
471 li 4,64
472 addi 5,1,112
473 ld 3,LC..11(2)
474 mr 6,22
475 bl .print_time
476 addi 3,1,112
477 li 4,0
478 bl .gettimeofday
479 nop
480 lis 10,0x3d0
481 cmpld 6,26,16
482 li 11,0
483 ori 10,10,36864
484 L..48:
485 bge 6,L..49
486 mr 9,26
487 li 0,0
488 L..51:
489 std 0,0(9)
490 addi 9,9,8
491 cmpld 7,9,16
492 blt 7,L..51
493 L..49:
494 addi 0,11,1
495 extsw 11,0
496 cmpw 7,11,10
497 bne+ 7,L..48
498 li 4,0
499 mr 3,22
500 bl .gettimeofday
501 nop
502 li 4,64
503 addi 5,1,112
504 ld 3,LC..13(2)
505 mr 6,22
506 bl .print_time

32-bit Linux:

387 popl %ecx
388 popl %edi
389 pushl $0
390 leal -20(%ebp), %edx
391 pushl %edx
392 call gettimeofday
393 xorl %edx, %edx
394 addl $16, %esp
395 .L41:
396 movl -4160(%ebp), %eax
397 cmpl %eax, -4144(%ebp)
398 jae .L42
399 movl -4144(%ebp), %eax
400 .L44:
401 movl $0, (%eax)
402 addl $4, %eax
403 cmpl %eax, -4160(%ebp)
404 ja .L44
405 .L42:
406 incl %edx
407 cmpl $64000000, %edx
408 jne .L41
409 subl $8, %esp
410 pushl $0
411 leal -28(%ebp), %edx
412 pushl %edx
413 call gettimeofday
414 leal -28(%ebp), %eax
415 movl %eax, (%esp)
416 leal -20(%ebp), %ecx
417 movl $64, %edx
418 movl $.LC5, %eax
419 call print_time
420 popl %eax
421 popl %edx
422 pushl $0
423 leal -20(%ebp), %edx
424 pushl %edx
425 call gettimeofday
426 xorl %edi, %edi
427 addl $16, %esp
428 .L46:
429 pushl %eax
430 pushl $64
431 pushl $0
432 movl -4144(%ebp), %ecx
433 pushl %ecx
434 call memset
435 incl %edi
436 addl $16, %esp
437 cmpl $64000000, %edi
438 jne .L46
439 subl $8, %esp
440 pushl $0
441 leal -28(%ebp), %eax
442 pushl %eax
443 call gettimeofday
444 leal -28(%ebp), %edx
445 movl %edx, (%esp)
446 leal -20(%ebp), %ecx
447 movl $64, %edx
448 movl $.LC6, %eax
449 call print_time
450 popl %eax
451 popl %edx
452 pushl $0
453 leal -20(%ebp), %eax
454 pushl %eax
455 call gettimeofday
456 xorl %edx, %edx
457 addl $16, %esp
458 .L48:
459 movl -4160(%ebp), %eax
460 cmpl %eax, -4144(%ebp)
461 jae .L49
462 movl -4144(%ebp), %eax
463 .L51:
464 movl $0, (%eax)
465 addl $4, %eax
466 cmpl -4160(%ebp), %eax
467 jb .L51
468 .L49:
469 incl %edx
470 cmpl $64000000, %edx
471 jne .L48
472 subl $8, %esp
473 pushl $0
474 leal -28(%ebp), %edx
475 pushl %edx
476 call gettimeofday
477 leal -28(%ebp), %eax
478 movl %eax, (%esp)
479 leal -20(%ebp), %ecx
480 movl $64, %edx
481 movl $.LC7, %eax
482 call print_time

--
Seneca Cunningham
scunning(at)ca(dot)afilias(dot)info