Function: hypre_BoomerAMGCreate2ndS.extracted | Module: exec | Source: par_strength.c:1253-1278 [...] | Coverage: 0.03% |
---|
Function: hypre_BoomerAMGCreate2ndS.extracted | Module: exec | Source: par_strength.c:1253-1278 [...] | Coverage: 0.03% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 1253 - 1278 |
-------------------------------------------------------------------------------- |
1253: #pragma omp parallel private(i) |
[...] |
1259: hypre_GetSimpleThreadPartition(&i_begin, &i_end, num_cols_diag_S); |
1260: |
1261: for (i = i_begin; i < i_end; i++) |
1262: { |
1263: if (CF_marker[i] > 0) num_coarse_private++; |
1264: } |
1265: |
1266: hypre_prefix_sum(&num_coarse_private, &num_coarse, num_coarse_prefix_sum); |
1267: |
1268: for (i = i_begin; i < i_end; i++) |
1269: { |
1270: if (CF_marker[i] > 0) |
1271: { |
1272: fine_to_coarse[i] = num_coarse_private; |
1273: coarse_to_fine[num_coarse_private] = i; |
1274: num_coarse_private++; |
1275: } |
1276: else |
1277: { |
1278: fine_to_coarse[i] = -1; |
0x48abe0 PUSH %RBP |
0x48abe1 MOV %RSP,%RBP |
0x48abe4 PUSH %R15 |
0x48abe6 PUSH %R14 |
0x48abe8 PUSH %R12 |
0x48abea PUSH %RBX |
0x48abeb SUB $0x20,%RSP |
0x48abef MOV %R9,%R15 |
0x48abf2 MOV %R8,%R14 |
0x48abf5 MOV %RDX,%RBX |
0x48abf8 MOV 0x10(%RBP),%R12 |
0x48abfc LEA -0x30(%RBP),%RDI |
0x48ac00 LEA -0x38(%RBP),%RSI |
0x48ac04 MOV %RCX,%RDX |
0x48ac07 CALL 4df9e0 <hypre_GetSimpleThreadPartition> |
0x48ac0c MOV -0x30(%RBP),%RAX |
0x48ac10 MOV -0x38(%RBP),%R9 |
0x48ac14 MOV %R9,%R8 |
0x48ac17 SUB %RAX,%R8 |
0x48ac1a JLE 48ac26 |
0x48ac1c CMP $0x8,%R8 |
0x48ac20 JAE 48ac2a |
0x48ac22 XOR %EDX,%EDX |
0x48ac24 JMP 48ac6e |
0x48ac26 XOR %EDX,%EDX |
0x48ac28 JMP 48ac95 |
0x48ac2a MOV %R8,%RDI |
0x48ac2d SHR $0x3,%RDI |
0x48ac31 LEA (%RBX,%RAX,8),%RSI |
0x48ac35 XOR %EDX,%EDX |
0x48ac37 VPXOR %XMM0,%XMM0,%XMM0 |
0x48ac3b NOPL (%RAX,%RAX,1) |
(2325) 0x48ac40 VPCMPLTQ (%RSI),%YMM0,%K0 |
(2325) 0x48ac47 VPCMPLTQ 0x20(%RSI),%YMM0,%K1 |
(2325) 0x48ac4f KSHIFTLB $0x4,%K1,%K1 |
(2325) 0x48ac55 KORB %K1,%K0,%K0 |
(2325) 0x48ac59 KMOVB %K0,%ECX |
(2325) 0x48ac5d POPCNT %RCX,%RCX |
(2325) 0x48ac62 ADD %RCX,%RDX |
(2325) 0x48ac65 ADD $0x40,%RSI |
(2325) 0x48ac69 DEC %RDI |
(2325) 0x48ac6c JNE 48ac40 |
0x48ac6e MOV %R8,%RSI |
0x48ac71 AND $-0x8,%RSI |
0x48ac75 CMP %R8,%RSI |
0x48ac78 JAE 48ac95 |
0x48ac7a ADD %RSI,%RAX |
0x48ac7d NOPL (%RAX) |
(2326) 0x48ac80 XOR %ECX,%ECX |
(2326) 0x48ac82 CMPQ $0,(%RBX,%RAX,8) |
(2326) 0x48ac87 SETG %CL |
(2326) 0x48ac8a ADD %RCX,%RDX |
(2326) 0x48ac8d INC %RAX |
(2326) 0x48ac90 CMP %RAX,%R9 |
(2326) 0x48ac93 JNE 48ac80 |
0x48ac95 MOV %RDX,-0x28(%RBP) |
0x48ac99 LEA -0x28(%RBP),%RDI |
0x48ac9d MOV %R15,%RSI |
0x48aca0 MOV %R12,%RDX |
0x48aca3 VZEROUPPER |
0x48aca6 CALL 4dfbf0 <hypre_prefix_sum> |
0x48acab MOV -0x30(%RBP),%RAX |
0x48acaf MOV -0x38(%RBP),%R9 |
0x48acb3 MOV %R9,%R8 |
0x48acb6 SUB %RAX,%R8 |
0x48acb9 JLE 48adda |
0x48acbf MOV 0x18(%RBP),%R10 |
0x48acc3 MOV -0x28(%RBP),%RSI |
0x48acc7 CMP $0x4,%R8 |
0x48accb JB 48ad9e |
0x48acd1 MOV %R8,%RDI |
0x48acd4 SHR $0x2,%RDI |
0x48acd8 LEA 0x3(%RAX),%RCX |
0x48acdc JMP 48acf5 |
0x48acde XCHG %AX,%AX |
(2324) 0x48ace0 MOVQ $-0x1,(%R14,%RCX,8) |
(2324) 0x48ace8 ADD $0x4,%RCX |
(2324) 0x48acec DEC %RDI |
(2324) 0x48acef JE 48ad9e |
(2324) 0x48acf5 CMPQ $0,-0x18(%RBX,%RCX,8) |
(2324) 0x48acfb JLE 48ad50 |
(2324) 0x48acfd LEA -0x3(%RCX),%RDX |
(2324) 0x48ad01 MOV %RSI,-0x18(%R14,%RCX,8) |
(2324) 0x48ad06 MOV %RDX,(%R10,%RSI,8) |
(2324) 0x48ad0a INC %RSI |
(2324) 0x48ad0d CMPQ $0,-0x10(%RBX,%RCX,8) |
(2324) 0x48ad13 JLE 48ad61 |
(2324) 0x48ad15 LEA -0x2(%RCX),%RDX |
(2324) 0x48ad19 MOV %RSI,-0x10(%R14,%RCX,8) |
(2324) 0x48ad1e MOV %RDX,(%R10,%RSI,8) |
(2324) 0x48ad22 INC %RSI |
(2324) 0x48ad25 CMPQ $0,-0x8(%RBX,%RCX,8) |
(2324) 0x48ad2b JLE 48ad72 |
(2324) 0x48ad2d LEA -0x1(%RCX),%RDX |
(2324) 0x48ad31 MOV %RSI,-0x8(%R14,%RCX,8) |
(2324) 0x48ad36 MOV %RDX,(%R10,%RSI,8) |
(2324) 0x48ad3a INC %RSI |
(2324) 0x48ad3d CMPQ $0,(%RBX,%RCX,8) |
(2324) 0x48ad42 JG 48ad86 |
(2324) 0x48ad44 JMP 48ace0 |
0x48ad46 NOPW %CS:(%RAX,%RAX,1) |
(2324) 0x48ad50 MOVQ $-0x1,-0x18(%R14,%RCX,8) |
(2324) 0x48ad59 CMPQ $0,-0x10(%RBX,%RCX,8) |
(2324) 0x48ad5f JG 48ad15 |
(2324) 0x48ad61 MOVQ $-0x1,-0x10(%R14,%RCX,8) |
(2324) 0x48ad6a CMPQ $0,-0x8(%RBX,%RCX,8) |
(2324) 0x48ad70 JG 48ad2d |
(2324) 0x48ad72 MOVQ $-0x1,-0x8(%R14,%RCX,8) |
(2324) 0x48ad7b CMPQ $0,(%RBX,%RCX,8) |
(2324) 0x48ad80 JLE 48ace0 |
(2324) 0x48ad86 MOV %RSI,(%R14,%RCX,8) |
(2324) 0x48ad8a MOV %RCX,(%R10,%RSI,8) |
(2324) 0x48ad8e INC %RSI |
(2324) 0x48ad91 ADD $0x4,%RCX |
(2324) 0x48ad95 DEC %RDI |
(2324) 0x48ad98 JNE 48acf5 |
0x48ad9e MOV %R8,%RCX |
0x48ada1 AND $-0x4,%RCX |
0x48ada5 CMP %R8,%RCX |
0x48ada8 JAE 48adda |
0x48adaa ADD %RCX,%RAX |
0x48adad JMP 48adc0 |
0x48adaf NOP |
(2323) 0x48adb0 MOVQ $-0x1,(%R14,%RAX,8) |
(2323) 0x48adb8 INC %RAX |
(2323) 0x48adbb CMP %RAX,%R9 |
(2323) 0x48adbe JE 48adda |
(2323) 0x48adc0 CMPQ $0,(%RBX,%RAX,8) |
(2323) 0x48adc5 JLE 48adb0 |
(2323) 0x48adc7 MOV %RSI,(%R14,%RAX,8) |
(2323) 0x48adcb MOV %RAX,(%R10,%RSI,8) |
(2323) 0x48adcf INC %RSI |
(2323) 0x48add2 INC %RAX |
(2323) 0x48add5 CMP %RAX,%R9 |
(2323) 0x48add8 JNE 48adc0 |
0x48adda ADD $0x20,%RSP |
0x48adde POP %RBX |
0x48addf POP %R12 |
0x48ade1 POP %R14 |
0x48ade3 POP %R15 |
0x48ade5 POP %RBP |
0x48ade6 RET |
0x48ade7 NOPW (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_BoomerAMGCreate2ndS | par_strength.c:1253 | exec |
○ | hypre_BoomerAMGSetup | par_amg_setup.c:617 | exec |
○ | hypre_PCGSetup | pcg.c:234 | exec |
○ | main | amg.c:398 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | par_strength.c:1253-1278 |
Module | exec |
nb instructions | 74 |
nb uops | 79 |
loop length | 239 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 19.75 cycles |
front end | 19.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 8.00 | 8.00 | 7.00 | 7.00 | 8.00 | 8.00 | 8.00 | 7.00 |
cycles | 8.00 | 8.00 | 7.00 | 7.00 | 8.00 | 8.00 | 8.00 | 7.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 18.61 |
Stall cycles | 0.00 |
Front-end | 19.75 |
Dispatch | 8.00 |
Overall L1 | 19.75 |
all | 6% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x10(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x30(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RCX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4df9e0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 48ac26 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48ac2a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 48ac6e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 48ac95 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RBX,%RAX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48ac95 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x28(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x28(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R15,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4dfbf0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 48adda | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x18(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x28(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 48ad9e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA 0x3(%RAX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 48acf5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48adda | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 48adc0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | par_strength.c:1253-1278 |
Module | exec |
nb instructions | 74 |
nb uops | 79 |
loop length | 239 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 19.75 cycles |
front end | 19.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 8.00 | 8.00 | 7.00 | 7.00 | 8.00 | 8.00 | 8.00 | 7.00 |
cycles | 8.00 | 8.00 | 7.00 | 7.00 | 8.00 | 8.00 | 8.00 | 7.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 18.61 |
Stall cycles | 0.00 |
Front-end | 19.75 |
Dispatch | 8.00 |
Overall L1 | 19.75 |
all | 6% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 8% |
all | 12% |
load | 12% |
store | 12% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
SUB $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x10(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA -0x30(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x38(%RBP),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %RCX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4df9e0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 48ac26 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x8,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48ac2a | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 48ac6e | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 48ac95 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RBX,%RAX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPXOR %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48ac95 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,-0x28(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x28(%RBP),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R15,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4dfbf0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 48adda | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x18(%RBP),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x28(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 48ad9e | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R8,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x2,%RDI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA 0x3(%RAX),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 48acf5 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 48adda | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 48adc0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_BoomerAMGCreate2ndS.extracted– | 0.03 | 0.01 |
○Loop 2324 - par_strength.c:1268-1278 - exec | 0.01 | 0 |
○Loop 2325 - par_strength.c:1261-1263 - exec | 0.01 | 0 |
○Loop 2323 - par_strength.c:1268-1278 - exec | 0 | 0 |
○Loop 2326 - par_strength.c:1261-1263 - exec | 0 | 0 |