Loop Id: 6043 | Module: exec | Source: csr_matop.c:540-548 | Coverage: 0.01% |
---|
Loop Id: 6043 | Module: exec | Source: csr_matop.c:540-548 | Coverage: 0.01% |
---|
0x566550 CMP %R11,%R15 |
0x566553 JLE 5667e0 |
0x566559 MOV -0x8(%RBX,%R15,8),%RDX |
0x56655e CMP %RDX,%RCX |
0x566561 JLE 5665a3 |
0x566563 LEA -0x1(%R15),%RSI |
0x566567 NOPW (%RAX,%RAX,1) |
(6051) 0x566570 MOV -0x8(%R9,%RCX,8),%RDX |
(6051) 0x566575 ADD %R13,%RDX |
(6051) 0x566578 MOV (%R14,%RDX,8),%RDI |
(6051) 0x56657c LEA -0x1(%RDI),%R8 |
(6051) 0x566580 MOV %R8,(%R14,%RDX,8) |
(6051) 0x566584 VMOVSD -0x8(%R10,%RCX,8),%XMM0 |
(6051) 0x56658b DEC %RCX |
(6051) 0x56658e VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6051) 0x566594 MOV %RSI,-0x8(%R12,%RDI,8) |
(6051) 0x566599 MOV -0x8(%RBX,%R15,8),%RDX |
(6051) 0x56659e CMP %RDX,%RCX |
(6051) 0x5665a1 JG 566570 |
0x5665a3 MOV -0x10(%RBX,%R15,8),%RCX |
0x5665a8 CMP %RCX,%RDX |
0x5665ab JLE 5665f3 |
0x5665ad LEA -0x2(%R15),%RSI |
0x5665b1 NOPW %CS:(%RAX,%RAX,1) |
(6050) 0x5665c0 MOV -0x8(%R9,%RDX,8),%RCX |
(6050) 0x5665c5 ADD %R13,%RCX |
(6050) 0x5665c8 MOV (%R14,%RCX,8),%RDI |
(6050) 0x5665cc LEA -0x1(%RDI),%R8 |
(6050) 0x5665d0 MOV %R8,(%R14,%RCX,8) |
(6050) 0x5665d4 VMOVSD -0x8(%R10,%RDX,8),%XMM0 |
(6050) 0x5665db DEC %RDX |
(6050) 0x5665de VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6050) 0x5665e4 MOV %RSI,-0x8(%R12,%RDI,8) |
(6050) 0x5665e9 MOV -0x10(%RBX,%R15,8),%RCX |
(6050) 0x5665ee CMP %RCX,%RDX |
(6050) 0x5665f1 JG 5665c0 |
0x5665f3 MOV -0x18(%RBX,%R15,8),%RDX |
0x5665f8 CMP %RDX,%RCX |
0x5665fb JLE 566643 |
0x5665fd LEA -0x3(%R15),%RSI |
0x566601 NOPW %CS:(%RAX,%RAX,1) |
(6049) 0x566610 MOV -0x8(%R9,%RCX,8),%RDX |
(6049) 0x566615 ADD %R13,%RDX |
(6049) 0x566618 MOV (%R14,%RDX,8),%RDI |
(6049) 0x56661c LEA -0x1(%RDI),%R8 |
(6049) 0x566620 MOV %R8,(%R14,%RDX,8) |
(6049) 0x566624 VMOVSD -0x8(%R10,%RCX,8),%XMM0 |
(6049) 0x56662b DEC %RCX |
(6049) 0x56662e VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6049) 0x566634 MOV %RSI,-0x8(%R12,%RDI,8) |
(6049) 0x566639 MOV -0x18(%RBX,%R15,8),%RDX |
(6049) 0x56663e CMP %RDX,%RCX |
(6049) 0x566641 JG 566610 |
0x566643 MOV -0x20(%RBX,%R15,8),%RCX |
0x566648 CMP %RCX,%RDX |
0x56664b JLE 566693 |
0x56664d LEA -0x4(%R15),%RSI |
0x566651 NOPW %CS:(%RAX,%RAX,1) |
(6048) 0x566660 MOV -0x8(%R9,%RDX,8),%RCX |
(6048) 0x566665 ADD %R13,%RCX |
(6048) 0x566668 MOV (%R14,%RCX,8),%RDI |
(6048) 0x56666c LEA -0x1(%RDI),%R8 |
(6048) 0x566670 MOV %R8,(%R14,%RCX,8) |
(6048) 0x566674 VMOVSD -0x8(%R10,%RDX,8),%XMM0 |
(6048) 0x56667b DEC %RDX |
(6048) 0x56667e VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6048) 0x566684 MOV %RSI,-0x8(%R12,%RDI,8) |
(6048) 0x566689 MOV -0x20(%RBX,%R15,8),%RCX |
(6048) 0x56668e CMP %RCX,%RDX |
(6048) 0x566691 JG 566660 |
0x566693 MOV -0x28(%RBX,%R15,8),%RDX |
0x566698 CMP %RDX,%RCX |
0x56669b JLE 5666e3 |
0x56669d LEA -0x5(%R15),%RSI |
0x5666a1 NOPW %CS:(%RAX,%RAX,1) |
(6047) 0x5666b0 MOV -0x8(%R9,%RCX,8),%RDX |
(6047) 0x5666b5 ADD %R13,%RDX |
(6047) 0x5666b8 MOV (%R14,%RDX,8),%RDI |
(6047) 0x5666bc LEA -0x1(%RDI),%R8 |
(6047) 0x5666c0 MOV %R8,(%R14,%RDX,8) |
(6047) 0x5666c4 VMOVSD -0x8(%R10,%RCX,8),%XMM0 |
(6047) 0x5666cb DEC %RCX |
(6047) 0x5666ce VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6047) 0x5666d4 MOV %RSI,-0x8(%R12,%RDI,8) |
(6047) 0x5666d9 MOV -0x28(%RBX,%R15,8),%RDX |
(6047) 0x5666de CMP %RDX,%RCX |
(6047) 0x5666e1 JG 5666b0 |
0x5666e3 MOV -0x30(%RBX,%R15,8),%RCX |
0x5666e8 CMP %RCX,%RDX |
0x5666eb JLE 566733 |
0x5666ed LEA -0x6(%R15),%RSI |
0x5666f1 NOPW %CS:(%RAX,%RAX,1) |
(6046) 0x566700 MOV -0x8(%R9,%RDX,8),%RCX |
(6046) 0x566705 ADD %R13,%RCX |
(6046) 0x566708 MOV (%R14,%RCX,8),%RDI |
(6046) 0x56670c LEA -0x1(%RDI),%R8 |
(6046) 0x566710 MOV %R8,(%R14,%RCX,8) |
(6046) 0x566714 VMOVSD -0x8(%R10,%RDX,8),%XMM0 |
(6046) 0x56671b DEC %RDX |
(6046) 0x56671e VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6046) 0x566724 MOV %RSI,-0x8(%R12,%RDI,8) |
(6046) 0x566729 MOV -0x30(%RBX,%R15,8),%RCX |
(6046) 0x56672e CMP %RCX,%RDX |
(6046) 0x566731 JG 566700 |
0x566733 MOV -0x38(%RBX,%R15,8),%RDX |
0x566738 CMP %RDX,%RCX |
0x56673b JLE 566783 |
0x56673d LEA -0x7(%R15),%RSI |
0x566741 NOPW %CS:(%RAX,%RAX,1) |
(6045) 0x566750 MOV -0x8(%R9,%RCX,8),%RDX |
(6045) 0x566755 ADD %R13,%RDX |
(6045) 0x566758 MOV (%R14,%RDX,8),%RDI |
(6045) 0x56675c LEA -0x1(%RDI),%R8 |
(6045) 0x566760 MOV %R8,(%R14,%RDX,8) |
(6045) 0x566764 VMOVSD -0x8(%R10,%RCX,8),%XMM0 |
(6045) 0x56676b DEC %RCX |
(6045) 0x56676e VMOVSD %XMM0,-0x8(%RAX,%RDI,8) |
(6045) 0x566774 MOV %RSI,-0x8(%R12,%RDI,8) |
(6045) 0x566779 MOV -0x38(%RBX,%R15,8),%RDX |
(6045) 0x56677e CMP %RDX,%RCX |
(6045) 0x566781 JG 566750 |
0x566783 MOV -0x40(%RBX,%R15,8),%RCX |
0x566788 ADD $-0x8,%R15 |
0x56678c CMP %RCX,%RDX |
0x56678f JLE 566550 |
0x566795 NOPW %CS:(%RAX,%RAX,1) |
(6044) 0x5667a0 MOV -0x8(%R9,%RDX,8),%RCX |
(6044) 0x5667a5 ADD %R13,%RCX |
(6044) 0x5667a8 MOV (%R14,%RCX,8),%RSI |
(6044) 0x5667ac LEA -0x1(%RSI),%RDI |
(6044) 0x5667b0 MOV %RDI,(%R14,%RCX,8) |
(6044) 0x5667b4 VMOVSD -0x8(%R10,%RDX,8),%XMM0 |
(6044) 0x5667bb DEC %RDX |
(6044) 0x5667be VMOVSD %XMM0,-0x8(%RAX,%RSI,8) |
(6044) 0x5667c4 MOV %R15,-0x8(%R12,%RSI,8) |
(6044) 0x5667c9 MOV (%RBX,%R15,8),%RCX |
(6044) 0x5667cd CMP %RCX,%RDX |
(6044) 0x5667d0 JG 5667a0 |
0x5667d2 JMP 566550 |
/home/eoseret/qaas_runs_CPU_9468/172-019-1763/intel/AMG/build/AMG/AMG/seq_mv/csr_matop.c: 540 - 548 |
-------------------------------------------------------------------------------- |
540: for (i = iEnd - 1; i >= iBegin; --i) { |
541: for (j = A_i[i + 1] - 1; j >= A_i[i]; --j) { |
542: HYPRE_Int idx = A_j[j]; |
543: --bucket[my_thread_num*num_colsA + idx]; |
544: |
545: HYPRE_Int offset = bucket[my_thread_num*num_colsA + idx]; |
546: |
547: AT_data[offset] = A_data[j]; |
548: AT_j[offset] = i; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.06 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixTranspose.extracted |
Source | csr_matop.c:540-541 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.83 |
CQA cycles if no scalar integer | 5.83 |
CQA cycles if FP arith vectorized | 5.83 |
CQA cycles if fully vectorized | 0.73 |
Front-end cycles | 5.83 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 5.50 |
P1 cycles | 5.50 |
P2 cycles | 5.50 |
P3 cycles | 5.00 |
P4 cycles | 2.67 |
P5 cycles | 2.67 |
P6 cycles | 2.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 43.00 |
Nb uops | 35.00 |
Nb loads | 8.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 10.97 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 8.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.06 |
Bottlenecks | micro-operation queue, |
Function | hypre_CSRMatrixTranspose.extracted |
Source | csr_matop.c:540-541 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 5.83 |
CQA cycles if no scalar integer | 5.83 |
CQA cycles if FP arith vectorized | 5.83 |
CQA cycles if fully vectorized | 0.73 |
Front-end cycles | 5.83 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 5.50 |
P1 cycles | 5.50 |
P2 cycles | 5.50 |
P3 cycles | 5.00 |
P4 cycles | 2.67 |
P5 cycles | 2.67 |
P6 cycles | 2.67 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.00 |
P11 cycles | 0.00 |
P12 cycles | 0.00 |
P13 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | NA |
Stall cycles (UFS) | NA |
Nb insns | 43.00 |
Nb uops | 35.00 |
Nb loads | 8.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 0.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 10.97 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | NA |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | NA |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | hypre_CSRMatrixTranspose.extracted |
Source file and lines | csr_matop.c:540-548 |
Module | exec |
nb instructions | 43 |
nb uops | 35 |
loop length | 240 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 5.83 cycles |
front end | 5.83 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.50 | 5.50 | 5.50 | 5.50 | 5.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 5.50 | 5.50 | 5.50 | 5.50 | 5.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 5.83 |
Dispatch | 5.50 |
Overall L1 | 5.83 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R11,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5667e0 <hypre_CSRMatrixTranspose.extracted+0x980> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV -0x8(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5665a3 <hypre_CSRMatrixTranspose.extracted+0x743> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x1(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW (%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x10(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5665f3 <hypre_CSRMatrixTranspose.extracted+0x793> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x2(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x18(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566643 <hypre_CSRMatrixTranspose.extracted+0x7e3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x3(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x20(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566693 <hypre_CSRMatrixTranspose.extracted+0x833> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x4(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x28(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5666e3 <hypre_CSRMatrixTranspose.extracted+0x883> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x5(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x30(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566733 <hypre_CSRMatrixTranspose.extracted+0x8d3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x6(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x38(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566783 <hypre_CSRMatrixTranspose.extracted+0x923> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x7(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x40(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
ADD $-0x8,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JLE 566550 <hypre_CSRMatrixTranspose.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
JMP 566550 <hypre_CSRMatrixTranspose.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |
Function | hypre_CSRMatrixTranspose.extracted |
Source file and lines | csr_matop.c:540-548 |
Module | exec |
nb instructions | 43 |
nb uops | 35 |
loop length | 240 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 5.83 cycles |
front end | 5.83 cycles |
ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.50 | 5.50 | 5.50 | 5.50 | 5.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
cycles | 5.50 | 5.50 | 5.50 | 5.50 | 5.00 | 2.67 | 2.67 | 2.67 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
Front-end | 5.83 |
Dispatch | 5.50 |
Overall L1 | 5.83 |
all | 0% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 12% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | ALU0/BRU0 | ALU1 | ALU2 | ALU3 | BRU1 | AGU0 | AGU1 | AGU2 | FP0 | FP1 | FP2 | FP3 | FP4 | FP5 | Latency | Recip. throughput | Vectorization |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R11,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5667e0 <hypre_CSRMatrixTranspose.extracted+0x980> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
MOV -0x8(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5665a3 <hypre_CSRMatrixTranspose.extracted+0x743> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x1(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW (%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x10(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5665f3 <hypre_CSRMatrixTranspose.extracted+0x793> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x2(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x18(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566643 <hypre_CSRMatrixTranspose.extracted+0x7e3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x3(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x20(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566693 <hypre_CSRMatrixTranspose.extracted+0x833> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x4(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x28(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 5666e3 <hypre_CSRMatrixTranspose.extracted+0x883> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x5(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x30(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566733 <hypre_CSRMatrixTranspose.extracted+0x8d3> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x6(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x38(%RBX,%R15,8),%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
CMP %RDX,%RCX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
JLE 566783 <hypre_CSRMatrixTranspose.extracted+0x923> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
LEA -0x7(%R15),%RSI | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
MOV -0x40(%RBX,%R15,8),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.33 | N/A |
ADD $-0x8,%R15 | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
JLE 566550 <hypre_CSRMatrixTranspose.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50-1 | N/A |
NOPW %CS:(%RAX,%RAX,1) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.09 | N/A |
JMP 566550 <hypre_CSRMatrixTranspose.extracted+0x6f0> | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | N/A |