Geek Answers Handbook

Simd vectorlength and unroll coefficient for fortran loop

I want to vectorize fortran below using SIMD directives

!DIR$ SIMD
    DO IELEM = 1 , NELEM
      X(IKLE(IELEM)) = X(IKLE(IELEM)) + W(IELEM)
    ENDDO

And I used the avx2 instruction. The program is compiled

ifort main_vec.f -simd -g -pg -O2 -vec-report6 -o vec.out -xcore-avx2 -align array32byte

Then I would like to add a sentence VECTORLENGTH(n)after SIMD. If there is no such sentence or n = 2, 4, the information does not provide information on the unroll coefficient

if n = 8, 16, vectorization support: unroll factor set to 2.

I read an Intel article on vectorization support: the unroll coefficient is set to xxxx So, I think the loop is deployed to something like:

    DO IELEM = 1 , NELEM, 2
      X(IKLE(IELEM)) = X(IKLE(IELEM)) + W(IELEM)
      X(IKLE(IELEM+1)) = X(IKLE(IELEM+1)) + W(IELEM+1)
    ENDDO

Then 2 X go to the vector register, 2 W go to another, add. But how does the VECTORLENGTH value work? Or maybe I really don't understand what the length of the vector means.

avx2, DOUBLE PRECISION X, ?

SSE2, VL = 8, , unroll 2. 4 2.

.loc    1  114  is_stmt 1
        movslq    main_vec_$IKLE.0.1(,%rdx,4), %rsi             #114.9
..LN202:
        movslq    4+main_vec_$IKLE.0.1(,%rdx,4), %rdi           #114.9
..LN203:
        movslq    8+main_vec_$IKLE.0.1(,%rdx,4), %r8            #114.9
..LN204:
        movslq    12+main_vec_$IKLE.0.1(,%rdx,4), %r9           #114.9
..LN205:
        movsd     -8+main_vec_$X.0.1(,%rsi,8), %xmm0            #114.26
..LN206:
        movslq    16+main_vec_$IKLE.0.1(,%rdx,4), %r10          #114.9
..LN207:
        movhpd    -8+main_vec_$X.0.1(,%rdi,8), %xmm0            #114.26
..LN208:
        movslq    20+main_vec_$IKLE.0.1(,%rdx,4), %r11          #114.9
..LN209:
        movsd     -8+main_vec_$X.0.1(,%r8,8), %xmm1             #114.26
..LN210:
        movslq    24+main_vec_$IKLE.0.1(,%rdx,4), %r14          #114.9
..LN211:
        addpd     main_vec_$W.0.1(,%rdx,8), %xmm0               #114.9
..LN212:
        movhpd    -8+main_vec_$X.0.1(,%r9,8), %xmm1             #114.26
..LN213:
..LN214:
        movslq    28+main_vec_$IKLE.0.1(,%rdx,4), %r15          #114.9
..LN215:
        movsd     -8+main_vec_$X.0.1(,%r10,8), %xmm2            #114.26
..LN216:
        addpd     16+main_vec_$W.0.1(,%rdx,8), %xmm1            #114.9
..LN217:
        movhpd    -8+main_vec_$X.0.1(,%r11,8), %xmm2            #114.26
..LN218:
..LN219:
        movsd     -8+main_vec_$X.0.1(,%r14,8), %xmm3            #114.26
..LN220:
        addpd     32+main_vec_$W.0.1(,%rdx,8), %xmm2            #114.9
..LN221:
        movhpd    -8+main_vec_$X.0.1(,%r15,8), %xmm3            #114.26
..LN222:
..LN223:
        addpd     48+main_vec_$W.0.1(,%rdx,8), %xmm3            #114.9
..LN224:
        movsd     %xmm0, -8+main_vec_$X.0.1(,%rsi,8)            #114.9
..LN225:
   .loc    1  113  is_stmt 1
        addq      $8, %rdx                                      #113.7
..LN226:
   .loc    1  114  is_stmt 1
        psrldq    $8, %xmm0                                     #114.9
..LN227:
   .loc    1  113  is_stmt 1
        cmpq      $26000, %rdx                                  #113.7
..LN228:
   .loc    1  114  is_stmt 1
        movsd     %xmm0, -8+main_vec_$X.0.1(,%rdi,8)            #114.9
..LN229:
        movsd     %xmm1, -8+main_vec_$X.0.1(,%r8,8)             #114.9
..LN230:
        psrldq    $8, %xmm1                                     #114.9
..LN231:
        movsd     %xmm1, -8+main_vec_$X.0.1(,%r9,8)             #114.9
..LN232:
        movsd     %xmm2, -8+main_vec_$X.0.1(,%r10,8)            #114.9
..LN233:
        psrldq    $8, %xmm2                                     #114.9
..LN234:
        movsd     %xmm2, -8+main_vec_$X.0.1(,%r11,8)            #114.9
..LN235:
        movsd     %xmm3, -8+main_vec_$X.0.1(,%r14,8)            #114.9
..LN236:
        psrldq    $8, %xmm3                                     #114.9
..LN237:
        movsd     %xmm3, -8+main_vec_$X.0.1(,%r15,8)            #114.9
..LN238:
+4
1

1) N - /, "" ( N X ). , :

Vector Length (abbreviated VL) = Vector Register Width / Sizeof (data type)

AVX2 = 256 . Sizeof ( ) = 8 = 64 . :

Vector Length (double FP, avx2) = 256 / 64 = 4

$DIR SIMD VECTORLENGTH (N) ( N X ). .

2) . ( "" ) .

M (M 2, 4,..), , , . , M ; "" / "" - ( ).

"-/". : "" "", /, .

3) + . , ( VL = N) ( M) . NxM, , ( ), . , , VL = 4 2, :

DO IELEM = 1 , NELEM, 8
  [X(IKLE(IELEM)),X(IKLE(IELEM+2)), X(IKLE(IELEM+4)), X(IKLE(IELEM+6))] = ...
  [X(IKLE(IELEM+1)),X(IKLE(IELEM+3)), X(IKLE(IELEM+5)), X(IKLE(IELEM+7))] = ...
ENDDO

"" .

4) :

5) P.S. ( ).

(, (16) avx2 FP), , ( ) " " /. M- - , ( , ). m- OpenMP, one. a) , b) c) , , vectorlength > 2 * ISA_VectorLength.

+5

More articles:


All Articles