带条件副本的 SIMD 指令

Question

我有一个看起来像这样的热点。在这里收集某种矢量会很好...关于如何让编译器喜欢这个的任何建议？

        do ii = 1, N
           if (diff(ii) .le. M ) then
              i = i0 + ii - 1
              rbuf( irb ) = i 
              irb = irb + 1               
           end if
        end do

使用 ifort 16.0.2 我的选择报告看起来像

LOOP BEGIN at code.f(197,13)
   remark #25084: Preprocess Loopnests: Moving Out Store    [ code.f(203,13) ]
     remark #15344: loop was not vectorized: vector dependence prevents vectorization
     remark #15346: vector dependence: assumed FLOW dependence between irb line 201 and irb line 200
     remark #15346: vector dependence: assumed ANTI dependence between irb line 200 and irb line 201
     remark #15346: vector dependence: assumed ANTI dependence between irb line 200 and irb line 201
     remark #15346: vector dependence: assumed FLOW dependence between irb line 201 and irb line 200
     remark #25439: unrolled with remainder by 2
     remark #25015: Estimate of max trip count of loop=1600
  LOOP END

这是小测试程序

program vect

integer :: ii, i0, irb
integer, parameter :: N=32
integer, parameter :: M=8
integer, dimension(N) :: diff
integer, dimension(2*N) :: rbuf

rbuf = 0

!only some values of diff will meet condition
!could be random
do ii=1, N
   diff(ii) = ii
end do

!from an outer loop
i0=1003

!this is code for filling up a buffer for an expensive vectorized
!subroutine with full vectors, irb < 2*N
irb=3

do ii = 1, N
   if (diff(ii) .le. M ) then
      i = i0 + ii - 1
      rbuf( irb ) = i 
      irb = irb + 1               
   end if
end do


!check 
do ii = 1, 2*N
   write(*,*) ii, rbuf(ii)
end do

end

Answer 1

根据目标架构，我能够让编译器使用指令进行矢量化。

!CDIR$ IVDEP
do ii = 1, N
 if (diff(ii) .le. M ) then
   i = i0 + ii - 1
   rbuf( irb ) = i 
   irb = irb + 1               
 end if
end do

和 -xMIC-AVX512 或 -mmic 将为这些体系结构提供矢量指令。例如

vpcompressd %zmm0, -4+vect_$RBUF.0.1(,%rax,4){%k1}      #29.15 c1

对于 AVX2，我认为正如@Peter Cordes 在他的评论中所建议的那样，人们已经求助于 intrinsics/asm，但很高兴知道编译器可以解决这个问题。

带条件副本的 SIMD 指令

SIMD instructions with condition copy

fortran

intel

simd

vectorization