https://gcc.gnu.org/bugzilla/show_bug.cgi?id=128737

            Bug ID: 128737
           Summary: associative arithmetic can be done in parallel with
                    four or more operands
           Product: gcc
           Version: 17.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: rtl-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: tkoenig at gcc dot gnu.org
  Target Milestone: ---

Consider the following code, where the parentheses in the _v2 versions
constrain the evaluation order.  Addition and multiplication are
commutative, and the result is the same regardless of rearrangement
of the variables.

function add_v1 (a,b,c,d) result (res)
  integer(8), value :: a, b, c, d
  integer(8) :: res
  res = a + b + c + d
end function add_v1

function add_v2 (a,b,c,d) result (res)
  integer(8), value :: a, b, c, d
  integer(8) :: res
  res = (a + b) + (c + d)
end function add_v2

function mul_v1 (a,b,c,d) result (res)
  integer(8), value :: a, b, c, d
  integer(8) :: res
  res = a * b * c * d
end function mul_v1

function mul_v2 (a,b,c,d) result (res)
  integer(8), value :: a, b, c, d
  integer(8) :: res
  res = (a * b) * (c * d)
end function mul_v2

This gives

add_v1_:
        addq    %rsi, %rdi
        addq    %rdx, %rdi
        leaq    (%rdi,%rcx), %rax
        ret
add_v2_:
        addq    %rsi, %rdi
        addq    %rcx, %rdx
        leaq    (%rdi,%rdx), %rax
        ret
mul_v1_:
        imulq   %rsi, %rdi
        imulq   %rdx, %rdi
        movq    %rdi, %rax
        imulq   %rcx, %rax
        ret
mul_v2_:
        imulq   %rsi, %rdi
        imulq   %rcx, %rdx
        movq    %rdi, %rax
        imulq   %rdx, %rax
        ret

where the v1 versions have some extra latency because of the dependency
chain, at least on OoO architectures.

This is not architecture specific, for example POWER has

add_v1_:
        add 3,3,4
        add 3,3,5
        add 3,3,6
        blr
add_v2_:
        add 3,3,4
        add 5,5,6
        add 3,3,5
        blr
mul_v1_:
        mulld 3,3,4
        mulld 3,3,5
        mulld 3,3,6
        blr
mul_v2_:
        mulld 3,3,4
        mulld 5,5,6
        mulld 3,3,5
        blr

Reply via email to