83

Вопрос по performance, instructions, intel, assembly, c – Производительность цикла кода C [продолжение]

Error: User Rate Limit Exceeded

Error: User Rate Limit Exceeded


Error: User Rate Limit Exceeded

for(int i=0; i<size; i+=16) {
    y1 = _mm_load_ps(output[i]);
    …
    y4 = _mm_load_ps(output[i+12]);

    for(k=0; k<ksize; k++){
        for(l=0; l<ksize; l++){
            w  = _mm_set_ps1(weight[i+k+l]);

            x1 = _mm_load_ps(input[i+k+l]);
            y1 = _mm_add_ps(y1,_mm_mul_ps(w,x1));
            …
            x4 = _mm_load_ps(input[i+k+l+12]);
            y4 = _mm_add_ps(y4,_mm_mul_ps(w,x4));
        }
    }
    _mm_store_ps(&output[i],y1);
    …
    _mm_store_ps(&output[i+12],y4);
    }

Error: User Rate Limit Exceeded

Error: User Rate Limit Exceeded

schedule

Error: User Rate Limit ExceededmovssError: User Rate Limit ExceededshufpsError: User Rate Limit ExceededmulpsError: User Rate Limit Exceeded

Error: User Rate Limit ExceededmovapsError: User Rate Limit ExceededaddpsError: User Rate Limit ExceededmulpsError: User Rate Limit Exceeded

Error: User Rate Limit Exceeded


Error: User Rate Limit Exceeded

…
Block x: 
  movapsx  (%rax,%rcx,4), %xmm0
  movapsx  0x10(%rax,%rcx,4), %xmm1
  movapsx  0x20(%rax,%rcx,4), %xmm2
  movapsx  0x30(%rax,%rcx,4), %xmm3
  movssl  (%rdx,%rcx,4), %xmm4
  inc %rcx
  shufps $0x0, %xmm4, %xmm4               {fill weight vector}
  cmp $0x32, %rcx 
  mulps %xmm4, %xmm0 
  mulps %xmm4, %xmm1
  mulps %xmm4, %xmm2 
  mulps %xmm3, %xmm4
  addps %xmm0, %xmm5 
  addps %xmm1, %xmm6 
  addps %xmm2, %xmm7 
  addps %xmm4, %xmm8 
  jl 0x401ad6 <Block x> 
…
  • Error: User Rate Limit Exceededlinkedin.com/in/vtsymbal

    от
  • Error: User Rate Limit Exceeded

    от
  • Error: User Rate Limit Exceededoff-coreError: User Rate Limit Exceeded

    от Ricky
  • Error: User Rate Limit Exceededsoftware.intel.com/sites/products/collateral/hpc/vtune/…

    от
  • Error: User Rate Limit ExceededshufpsError: User Rate Limit Exceeded

    от Mysticial
  • Error: User Rate Limit ExceededshufpsError: User Rate Limit ExceededmultpsError: User Rate Limit Exceeded

    от Ricky
  • Error: User Rate Limit Exceeded

    от Gunther Piez
  • Error: User Rate Limit Exceeded

    от Mysticial
  • Error: User Rate Limit Exceeded

    от Gunther Piez
  • 3

    Error: User Rate Limit Exceeded

    Vtune for Linux (you can search for the Windows version) oprofile