Re: Swap should be better done native?

Ulf Zibis Thu, 01 Apr 2010 05:26:40 -0700

Am 31.03.2010 22:54, schrieb Martin Buchholz:

On Wed, Mar 31, 2010 at 13:41, Ulf Zibis<ulf.zi...@gmx.de>  wrote:

You remember on UTF-8 twiddling:


Am 16.03.2010 22:51, schrieb Ulf Zibis:

Am 16.03.2010 21:57, schrieb Martin Buchholz:

On Tue, Mar 16, 2010 at 12:48, Ulf Zibis<ulf.zi...@gmx.de>    wrote:

  8-bit shift + compare would allow HotSpot to compile to smart 1-byte
immediate op-codes.
In encodeBufferLoop() you could use putChar(), putInt() instead put().
Should perform better.

I'm not convinced.  You would need to assemble bytes into an
int, and then break them apart into bytes on the other side?

Some time ago, I disassembled such code. I could see, that the int was
copied directly to memory by one 32-bit move instruction.
In case of using put(byte), I saw 4 8-bit move instructions.

Ulf, I'd like to understand this better.

How are you generating the machine code
(pointer to docs?)?

I must prepare it. Takes some time.

Now you can see, that putInt(int) is done at once, so faster as 4 put(byte).

Leider versteh ich dass immer noch nicht.


Thanks for some little German. :-D

Ich weiss auch noch nicht,
how to generate disassembled code.


Sorry about my flippancy/ignorance.
I started here: http://wikis.sun.com/display/HotSpotInternals/PrintAssembly

On Windows I use a hsdis-i386.dll compiled by Andreas Schösser andprovided from Volker Simonis <volker.simo...@gmail.com>.

How can 4 put(byte) be converted into one put(int)?

See the following code snippets ...

===================================================
Codesnippet from EUC_TW$Encoder:
            dst.put(SS2);
            dst.put((byte)(0xa0 | p));
            dst.put((byte)(db >> 8));
            dst.put((byte)db);

becomes (124 bytes):
  0x00b94ab2: mov    %edx,%ebx          ;*invokevirtual put

; -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ab4: mov    0x14(%ebx),%ecx    ;*getfield position

; -java.nio.Buffer::nextputin...@1 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ab7: mov    0x18(%ebx),%edx    ;*getfield limit

; -java.nio.Buffer::nextputin...@5 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94aba: cmp    %edx,%ecx
  0x00b94abc: jge    0x00b94b79         ;*if_icmplt

; -java.nio.Buffer::nextputin...@8 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ac2: mov    %ebx,0x14(%esp)
  0x00b94ac6: mov    %ebx,%esi
  0x00b94ac8: mov    0x8(%esi),%ebp
  0x00b94acb: mov    0xc(%esi),%edi
  0x00b94ace: mov    0x8(%esp),%eax

0x00b94ad2: or $0xa0,%eax ;*ior ; -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@107 (line 267)

  0x00b94ad8: mov    %eax,0x8(%esp)
  0x00b94adc: mov    %ebp,%eax
  0x00b94ade: mov    %ecx,%ebx
  0x00b94ae0: inc    %ebx               ;*iadd

; -java.nio.Buffer::nextputin...@26 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ae1: mov    %ebx,0x14(%esi)    ;*putfield position

; -java.nio.Buffer::nextputin...@27 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ae4: add    %ecx,%eax
  0x00b94ae6: movb   $0x8e,(%eax)       ;*invokevirtual putByte

; -java.nio.DirectByteBuffer::p...@12 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@97 (line 266)

  0x00b94ae9: cmp    %edx,%ebx
  0x00b94aeb: jge    0x00b94b8d         ;*if_icmplt

; -java.nio.Buffer::nextputin...@8 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@109 (line 267)

  0x00b94af1: mov    0x8(%esp),%ebx
  0x00b94af5: mov    %bl,0x1(%eax)      ;*invokevirtual putByte

; -java.nio.DirectByteBuffer::p...@12 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@109 (line 267)

  0x00b94af8: mov    %ecx,%ebx
  0x00b94afa: add    $0x2,%ebx          ;*iadd

; -java.nio.Buffer::nextputin...@26 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@109 (line 267)

  0x00b94afd: mov    %ebx,0x14(%esi)    ;*putfield position

; -java.nio.Buffer::nextputin...@27 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@109 (line 267)

  0x00b94b00: cmp    %edx,%ebx
  0x00b94b02: jge    0x00b94b9d         ;*if_icmplt

; -java.nio.Buffer::nextputin...@8 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@119 (line 268)

  0x00b94b08: mov    0x18(%esp),%ebx
  0x00b94b0c: mov    %bl,0x2(%eax)      ;*invokevirtual putByte

; -java.nio.DirectByteBuffer::p...@12 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@119 (line 268)

  0x00b94b0f: mov    %ecx,%ebx
  0x00b94b11: add    $0x3,%ebx          ;*iadd

; -java.nio.Buffer::nextputin...@26 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@119 (line 268)

  0x00b94b14: mov    %esi,%ebp
  0x00b94b16: mov    %ebx,0x14(%ebp)    ;*putfield position

; -java.nio.Buffer::nextputin...@27 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@119 (line 268)

  0x00b94b19: cmp    %edx,%ebx
  0x00b94b1b: jge    0x00b94ba9         ;*if_icmplt

; -java.nio.Buffer::nextputin...@8 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@126 (line 269)

  0x00b94b21: mov    0x4(%esp),%edx
  0x00b94b25: mov    %dl,0x3(%eax)      ;*invokevirtual putByte

; -java.nio.DirectByteBuffer::p...@12 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@126 (line 269)

  0x00b94b28: add    $0x4,%ecx
  0x00b94b2b: mov    %ecx,0x14(%ebp)    ;*putfield position

; -java.nio.Buffer::nextputin...@27 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); -sun.nio.cs.ext.E_30_d_n_codeToBuffer0::enc...@126 (line 269)


===================================================
Alternative 1 codesnippet:
            dst.putInt((SS2 << 24) | (0xa0 << 16) | (p << 16) | db);

becomes (63 bytes):
  0x00b95d51: shl    $0x10,%ebx
  0x00b95d54: or     %edi,%ebx

0x00b95d56: or $0x8ea00000,%ebx ;*ior ; -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@93 (line 265)0x00b95d5c: cmp $0x282c61d8,%ebp ;{oop('java/nio/DirectByteBuffer')}

  0x00b95d62: jne    0x00b95dcd         ;*invokevirtual putInt

; -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d64: mov    0x18(%edx),%edi
  0x00b95d67: mov    0x14(%edx),%ecx    ;*getfield position

; -java.nio.Buffer::nextputin...@5 (line 518); -java.nio.DirectByteBuffer::put...@4 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d6a: sub    %ecx,%edi
  0x00b95d6c: cmp    $0x4,%edi
  0x00b95d6f: jl     0x00b95de1         ;*if_icmpge

; -java.nio.Buffer::nextputin...@10 (line 518); -java.nio.DirectByteBuffer::put...@4 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d71: movzbl 0x26(%edx),%eax
  0x00b95d75: test   %eax,%eax
  0x00b95d77: jne    0x00b95d7b         ;*ifeq

; -java.nio.DirectByteBuffer::put...@17 (line 664); -java.nio.DirectByteBuffer::put...@11 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d79: bswap  %ebx               ;*invokevirtual putInt

; -java.nio.DirectByteBuffer::put...@30 (line 664); -java.nio.DirectByteBuffer::put...@11 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d7b: mov    %edx,%esi
  0x00b95d7d: mov    0x8(%esi),%ebp
  0x00b95d80: mov    0xc(%esi),%edi     ;*getfield address

; -java.nio.DirectByteBuffer::i...@1 (line 225); -java.nio.DirectByteBuffer::put...@7 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d83: mov    %ecx,%eax
  0x00b95d85: add    $0x4,%eax
  0x00b95d88: mov    %eax,0x14(%edx)    ;*putfield position

; -java.nio.Buffer::nextputin...@33 (line 521); -java.nio.DirectByteBuffer::put...@4 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)

  0x00b95d8b: mov    %ebp,%eax
  0x00b95d8d: mov    %ebx,(%eax,%ecx,1)  ;*invokevirtual putInt

; -java.nio.DirectByteBuffer::put...@30 (line 664); -java.nio.DirectByteBuffer::put...@11 (line 676); -sun.nio.cs.ext.E_31_d_n_codeToBuffer1::enc...@94 (line 265)


===================================================
On big endian machines, additionally the swapping becomes omitted.

===================================================
Alternative 2 codesnippet:
            bb[0] = SS2;
            bb[1] = (byte)(0xa0 | p);
            bb[2] = (byte)(db >> 8);
            bb[3] = (byte)db;
            dst.put(bb, 0, 4);

becomes (149 bytes):
  0x00b95f68: mov    0x30(%esp),%ebp    ;*invokevirtual put

; -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f6c: mov    %ebp,0x30(%esp)
  0x00b95f70: add    $0xfffffffc,%ecx
  0x00b95f73: or     $0x4,%ecx
  0x00b95f76: test   %ecx,%ecx
  0x00b95f78: jl     0x00b96120         ;*ifge

; -java.nio.Buffer::checkbou...@13 (line 551); - java.nio.ByteBuffer::p...@4(line 803); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f7e: mov    0x14(%ebp),%ecx    ;*getfield position

; -java.nio.Buffer::remain...@5 (line 383); - java.nio.ByteBuffer::p...@9(line 804); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f81: mov    0x18(%ebp),%ebx    ;*getfield limit

; -java.nio.Buffer::remain...@1 (line 383); - java.nio.ByteBuffer::p...@9(line 804); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f84: mov    %ebx,%ebp
  0x00b95f86: sub    %ecx,%ebp
  0x00b95f88: cmp    $0x4,%ebp
  0x00b95f8b: jl     0x00b9612d         ;*if_icmple

; - java.nio.ByteBuffer::p...@12(line 804); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f91: cmp    %ebx,%ecx
  0x00b95f93: jge    0x00b96139         ;*if_icmplt

; -java.nio.Buffer::nextputin...@8 (line 512); -java.nio.DirectByteBuffer::p...@5 (line 271); - java.nio.ByteBuffer::p...@43(line 808); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95f99: mov    %eax,0x18(%esp)
  0x00b95f9d: mov    %edx,0x14(%esp)
  0x00b95fa1: mov    0x30(%esp),%esi
  0x00b95fa5: mov    0x8(%esi),%ebp
  0x00b95fa8: mov    0xc(%esi),%edi
  0x00b95fab: mov    %ecx,%edx
  0x00b95fad: inc    %edx               ;*iadd

; -java.nio.Buffer::nextputin...@26 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); - java.nio.ByteBuffer::p...@43(line 808); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95fae: mov    %edx,0x14(%esi)    ;*putfield position

; -java.nio.Buffer::nextputin...@27 (line 514); -java.nio.DirectByteBuffer::p...@5 (line 271); - java.nio.ByteBuffer::p...@43(line 808); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95fb1: mov    %ebp,%eax
  0x00b95fb3: add    %ecx,%eax
  0x00b95fb5: movb   $0x8e,(%eax)       ;*invokevirtual putByte

; -java.nio.DirectByteBuffer::p...@12 (line 271); - java.nio.ByteBuffer::p...@43(line 808); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95fb8: cmp    %ebx,%edx
  0x00b95fba: jge    0x00b96155         ;*if_icmplt

  0x00b95fc0: mov    0x8(%esp),%edx
  0x00b95fc4: mov    %dl,0x1(%eax)      ;*invokevirtual putByte

  0x00b95fc7: mov    %ecx,%ebp
  0x00b95fc9: add    $0x2,%ebp          ;*iadd

  0x00b95fcc: mov    %ebp,0x14(%esi)    ;*putfield position

  0x00b95fcf: cmp    %ebx,%ebp
  0x00b95fd1: jge    0x00b96142         ;*if_icmplt

  0x00b95fd7: mov    0x18(%esp),%edx
  0x00b95fdb: mov    %dl,0x2(%eax)      ;*invokevirtual putByte

  0x00b95fde: mov    %ecx,%ebp
  0x00b95fe0: add    $0x3,%ebp          ;*iadd

  0x00b95fe3: mov    %ebp,0x14(%esi)    ;*putfield position

  0x00b95fe6: cmp    %ebx,%ebp
  0x00b95fe8: jge    0x00b96161         ;*aload_0

; - java.nio.ByteBuffer::p...@38(line 808); -java.nio.DirectByteBuffer::p...@117 (line 349); -sun.nio.cs.ext.E_30_d_n_codeToBuffer01::enc...@136 (line 272)

  0x00b95fee: mov    0x4(%esp),%ebx
  0x00b95ff2: mov    %bl,0x3(%eax)      ;*invokevirtual putByte

  0x00b95ff5: add    $0x4,%ecx
  0x00b95ff8: mov    %esi,%ebp
  0x00b95ffa: mov    %ecx,0x14(%ebp)    ;*putfield position


===================================================

I believe, alternative 2 could become much better from HotSpot side(enable -XX:+DoEscapeAnalysis didn't work here).


-Ulf

Re: Swap should be better done native?

Reply via email to