I am working on a language that is compiled with LLVM. Just for fun, I wanted to do some microbenchmarks. In one, I run some million sin / cos computations in a loop. In pseudocode, it looks like this:

var x: Double = 0.0
for (i <- 0 to 100 000 000)
  x = sin(x)^2 + cos(x)^2
return x.toInteger

If I'm computing sin/cos using LLVM IR inline assembly in the form:

%sc = call { double, double } asm "fsincos", "={st(1)},={st},1,~{dirflag},~{fpsr},~{flags}" (double %"res") nounwind

this is faster than using fsin and fcos separately instead of fsincos. However, it is slower than if I calling the llvm.sin.f64 and llvm.cos.f64 intrinsics separately, which compile to calls to the C math lib functions, at least with the target settings I'm using (x86_64 with SSE enabled).

It seems LLVM inserts some conversions between single/double precision FP -- that might be the culprit. Why is that? Sorry, I'm a relative newbie at assembly:

    .globl  main
    .align  16, 0x90
    .type   main,@function
main:                                   # @main
    .cfi_startproc
# BB#0:                                 # %loopEntry1
    xorps   %xmm0, %xmm0
    movl    $-1, %eax
    jmp     .LBB44_1
    .align  16, 0x90
.LBB44_2:                               # %then4
                                    #   in Loop: Header=BB44_1 Depth=1
    movss   %xmm0, -4(%rsp)
    flds    -4(%rsp)
    #APP
    fsincos
    #NO_APP
    fstpl   -16(%rsp)
    fstpl   -24(%rsp)
    movsd   -16(%rsp), %xmm0
    mulsd   %xmm0, %xmm0
    cvtsd2ss        %xmm0, %xmm1
    movsd   -24(%rsp), %xmm0
    mulsd   %xmm0, %xmm0
    cvtsd2ss        %xmm0, %xmm0
    addss   %xmm1, %xmm0
.LBB44_1:                               # %loop2
                                    # =>This Inner Loop Header: Depth=1
    incl    %eax
    cmpl    $99999999, %eax         # imm = 0x5F5E0FF
    jle     .LBB44_2
# BB#3:
assembly llvm inline-assembly x87
Edit
Report