148 lines
7.6 KiB
Plaintext
148 lines
7.6 KiB
Plaintext
Iterations: 100
|
|
Instructions: 5400
|
|
Total Cycles: 6595
|
|
Total uOps: 6800
|
|
|
|
Dispatch Width: 4
|
|
uOps Per Cycle: 1.03
|
|
IPC: 0.82
|
|
Block RThroughput: 17.0
|
|
|
|
|
|
Instruction Info:
|
|
[1]: #uOps
|
|
[2]: Latency
|
|
[3]: RThroughput
|
|
[4]: MayLoad
|
|
[5]: MayStore
|
|
[6]: HasSideEffects (U)
|
|
|
|
[1] [2] [3] [4] [5] [6] Instructions:
|
|
2 5 1.00 * push r15
|
|
2 5 1.00 * push r14
|
|
2 5 1.00 * push r13
|
|
2 5 1.00 * push r12
|
|
2 5 1.00 * push rbx
|
|
1 1 0.33 sub rsp, 32
|
|
1 1 0.33 mov rbx, rdi
|
|
1 5 0.50 * mov rax, qword ptr [rdi]
|
|
1 5 0.50 * mov r12, qword ptr [rdi + 16]
|
|
1 1 0.33 mov rcx, rax
|
|
1 1 0.33 sub rcx, r12
|
|
1 1 0.33 cmp rsi, rcx
|
|
1 1 1.00 jbe .LBB6_3
|
|
1 1 0.33 mov r15, r12
|
|
1 1 0.33 add r15, rsi
|
|
1 1 1.00 jae .LBB6_6
|
|
1 0 0.25 xor eax, eax
|
|
1 1 1.00 jmp .LBB6_5
|
|
1 5 0.50 * mov rax, qword ptr [rbx + 8]
|
|
1 1 0.50 lea r15, [r12 + rsi]
|
|
1 1 0.50 lea rcx, [r12 + 2*r12]
|
|
1 1 0.50 lea rdi, [rax + 2*rcx]
|
|
1 1 0.33 add rsi, rsi
|
|
1 1 0.50 lea rdx, [rsi + 2*rsi]
|
|
1 0 0.25 xor esi, esi
|
|
4 7 1.00 * call qword ptr [rip + memset@GOTPCREL]
|
|
1 1 1.00 * mov qword ptr [rbx + 16], r15
|
|
1 1 0.33 mov al, 1
|
|
1 1 0.33 add rsp, 32
|
|
1 6 0.50 * pop rbx
|
|
1 6 0.50 * pop r12
|
|
1 6 0.50 * pop r13
|
|
1 6 0.50 * pop r14
|
|
1 6 0.50 * pop r15
|
|
1 1 1.00 U ret
|
|
1 1 0.33 mov r13, rsi
|
|
1 1 0.50 lea rcx, [rax + rax]
|
|
1 1 0.33 cmp r15, rcx
|
|
3 3 1.00 cmova rcx, r15
|
|
1 1 0.33 cmp rcx, 5
|
|
1 1 0.33 mov r14d, 4
|
|
2 2 0.67 cmovae r14, rcx
|
|
1 5 0.50 * mov rdx, qword ptr [rbx + 8]
|
|
1 1 0.50 lea rdi, [rsp + 8]
|
|
1 1 0.33 mov rsi, rax
|
|
1 1 0.33 mov rcx, r14
|
|
3 5 1.00 call <alloc::raw_vec::RawVecInner>::finish_grow
|
|
2 6 0.50 * cmp dword ptr [rsp + 8], 1
|
|
1 1 1.00 je .LBB6_2
|
|
1 5 0.50 * mov rax, qword ptr [rsp + 16]
|
|
1 1 1.00 * mov qword ptr [rbx + 8], rax
|
|
1 1 1.00 * mov qword ptr [rbx], r14
|
|
1 1 0.33 mov rsi, r13
|
|
1 1 1.00 jmp .LBB6_4
|
|
|
|
|
|
Resources:
|
|
[0] - SBDivider
|
|
[1] - SBFPDivider
|
|
[2] - SBPort0
|
|
[3] - SBPort1
|
|
[4] - SBPort4
|
|
[5] - SBPort5
|
|
[6.0] - SBPort23
|
|
[6.1] - SBPort23
|
|
|
|
|
|
Resource pressure per iteration:
|
|
[0] [1] [2] [3] [4] [5] [6.0] [6.1]
|
|
- - 12.00 12.00 10.00 13.00 11.00 11.00
|
|
|
|
Resource pressure by instruction:
|
|
[0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
|
|
- - - - 1.00 - 0.49 0.51 push r15
|
|
- - - - 1.00 - 0.51 0.49 push r14
|
|
- - - - 1.00 - 0.50 0.50 push r13
|
|
- - - - 1.00 - 0.50 0.50 push r12
|
|
- - - - 1.00 - 0.50 0.50 push rbx
|
|
- - 0.01 0.99 - - - - sub rsp, 32
|
|
- - - - - 1.00 - - mov rbx, rdi
|
|
- - - - - - 0.50 0.50 mov rax, qword ptr [rdi]
|
|
- - - - - - 0.50 0.50 mov r12, qword ptr [rdi + 16]
|
|
- - - 1.00 - - - - mov rcx, rax
|
|
- - - 0.99 - 0.01 - - sub rcx, r12
|
|
- - - - - 1.00 - - cmp rsi, rcx
|
|
- - - - - 1.00 - - jbe .LBB6_3
|
|
- - 0.01 0.98 - 0.01 - - mov r15, r12
|
|
- - 0.99 0.01 - - - - add r15, rsi
|
|
- - - - - 1.00 - - jae .LBB6_6
|
|
- - - - - - - - xor eax, eax
|
|
- - - - - 1.00 - - jmp .LBB6_5
|
|
- - - - - - 0.50 0.50 mov rax, qword ptr [rbx + 8]
|
|
- - 1.00 - - - - - lea r15, [r12 + rsi]
|
|
- - 0.98 0.02 - - - - lea rcx, [r12 + 2*r12]
|
|
- - 0.99 0.01 - - - - lea rdi, [rax + 2*rcx]
|
|
- - - 1.00 - - - - add rsi, rsi
|
|
- - 0.99 0.01 - - - - lea rdx, [rsi + 2*rsi]
|
|
- - - - - - - - xor esi, esi
|
|
- - - - 1.00 1.00 1.00 1.00 call qword ptr [rip + memset@GOTPCREL]
|
|
- - - - 1.00 - 0.50 0.50 mov qword ptr [rbx + 16], r15
|
|
- - 0.01 0.99 - - - - mov al, 1
|
|
- - 1.00 - - - - - add rsp, 32
|
|
- - - - - - 0.50 0.50 pop rbx
|
|
- - - - - - 0.50 0.50 pop r12
|
|
- - - - - - 0.50 0.50 pop r13
|
|
- - - - - - 0.50 0.50 pop r14
|
|
- - - - - - 0.50 0.50 pop r15
|
|
- - - - - 1.00 - - ret
|
|
- - 1.00 - - - - - mov r13, rsi
|
|
- - 0.01 0.99 - - - - lea rcx, [rax + rax]
|
|
- - 0.99 0.01 - - - - cmp r15, rcx
|
|
- - 2.00 0.01 - 0.99 - - cmova rcx, r15
|
|
- - 0.01 0.99 - - - - cmp rcx, 5
|
|
- - 0.01 0.99 - - - - mov r14d, 4
|
|
- - 1.00 0.01 - 0.99 - - cmovae r14, rcx
|
|
- - - - - - 0.50 0.50 mov rdx, qword ptr [rbx + 8]
|
|
- - 0.01 0.99 - - - - lea rdi, [rsp + 8]
|
|
- - - 1.00 - - - - mov rsi, rax
|
|
- - - 0.01 - 0.99 - - mov rcx, r14
|
|
- - - - 1.00 1.00 0.50 0.50 call <alloc::raw_vec::RawVecInner>::finish_grow
|
|
- - - 0.99 - 0.01 0.50 0.50 cmp dword ptr [rsp + 8], 1
|
|
- - - - - 1.00 - - je .LBB6_2
|
|
- - - - - - 0.50 0.50 mov rax, qword ptr [rsp + 16]
|
|
- - - - 1.00 - 0.49 0.51 mov qword ptr [rbx + 8], rax
|
|
- - - - 1.00 - 0.51 0.49 mov qword ptr [rbx], r14
|
|
- - 0.99 0.01 - - - - mov rsi, r13
|
|
- - - - - 1.00 - - jmp .LBB6_4
|