It seems like a closure on a non bitstype still has issues, or is there
something wrong with doing this?
immutable Params
α::Float64
end
function test()
h = (t,u,du,p) -> @inbounds begin
du[1] = 1.01u[1]
du[2] = p.α*u[2]
end
h2 = (t,u,du) -> @inbounds begin
du[1] = 1.01u[1]
du[2] = 1.0*u[2]
end
const u = [0.1,0.2]
const du = zeros(2)
const p = Params(1.0)
l = (t,u,du) -> h(t,u,du,p)
println("Pass In Parameters")
@code_native h(1.0,u,du,p)
println("No Parameters")
@code_native h2(1.0,u,du)
println("Closures")
@code_native l(1.0,u,du)
end
test()
Pass In Parameters
.text
Filename: replacement_macros_tests.jl
pushq %rbp
movq %rsp, %rbp
Source line: 29
movq (%rdi), %rax
movsd (%rax), %xmm0 # xmm0 = mem[0],zero
movabsq $140006850762016, %rcx # imm = 0x7F55E29B1520
mulsd (%rcx), %xmm0
movq (%rsi), %rcx
movsd %xmm0, (%rcx)
Source line: 30
movsd (%rdx), %xmm0 # xmm0 = mem[0],zero
mulsd 8(%rax), %xmm0
movsd %xmm0, 8(%rcx)
popq %rbp
retq
No Parameters
.text
Filename: replacement_macros_tests.jl
pushq %rbp
movq %rsp, %rbp
Source line: 33
movq (%rdi), %rax
movsd (%rax), %xmm0 # xmm0 = mem[0],zero
movabsq $140006850762144, %rcx # imm = 0x7F55E29B15A0
mulsd (%rcx), %xmm0
movq (%rsi), %rcx
movsd %xmm0, (%rcx)
Source line: 34
movq 8(%rax), %rax
movq %rax, 8(%rcx)
popq %rbp
retq
nopw (%rax,%rax)
Closures
.text
Filename: replacement_macros_tests.jl
pushq %rbp
movq %rsp, %rbp
pushq %r15
pushq %r14
pushq %r13
pushq %r12
pushq %rbx
subq $72, %rsp
movq %rdx, %r14
movq %rsi, %r15
movsd %xmm0, -112(%rbp)
movabsq $140007647692112, %rbx # imm = 0x7F56121B4550
movq %fs:0, %r12
addq $-2672, %r12 # imm = 0xFFFFFFFFFFFFF590
xorpd %xmm0, %xmm0
movupd %xmm0, -64(%rbp)
movupd %xmm0, -80(%rbp)
movq $0, -48(%rbp)
movq $12, -104(%rbp)
movq (%r12), %rax
movq %rax, -96(%rbp)
leaq -104(%rbp), %rax
movq %rax, (%r12)
movq $0, -88(%rbp)
Source line: 39
movq (%rdi), %rax
movq (%rax), %r13
testq %r13, %r13
je L232
movq %r13, -88(%rbp)
movq %rbx, -80(%rbp)
movabsq $jl_gc_pool_alloc, %rax
movl $1432, %esi # imm = 0x598
movl $16, %edx
movq %r12, %rdi
callq *%rax
addq $1072064, %rbx # imm = 0x105BC0
movq %rbx, -8(%rax)
movsd -112(%rbp), %xmm0 # xmm0 = mem[0],zero
movsd %xmm0, (%rax)
movq %rax, -72(%rbp)
movq %r15, -64(%rbp)
movq %r14, -56(%rbp)
movq %r13, -48(%rbp)
movabsq $jl_apply_generic, %rax
movl $5, %esi
leaq -80(%rbp), %rdi
callq *%rax
movq -96(%rbp), %rax
movq %rax, (%r12)
addq $72, %rsp
popq %rbx
popq %r12
popq %r13
popq %r14
popq %r15
popq %rbp
retq
L232:
addq $1448, %rbx # imm = 0x5A8
movabsq $jl_throw, %rax
movq %rbx, %rdi
callq *%rax
nop
Clearly the 3rd method (using a closure on a parameter type) has a lot more
steps. My untrained eye says that means it's bad... is that simple analysis
wrong?
