Function: hypre_SeqVectorAxpy.extracted | Module: exec | Source: vector.c:449-452 | Coverage: 0.71% |
---|
Function: hypre_SeqVectorAxpy.extracted | Module: exec | Source: vector.c:449-452 | Coverage: 0.71% |
---|
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/seq_mv/vector.c: 449 - 452 |
-------------------------------------------------------------------------------- |
449: #pragma omp parallel for private(i) HYPRE_SMP_SCHEDULE |
450: #endif |
451: for (i = 0; i < size; i++) |
452: y_data[i] += alpha * x_data[i]; |
0x4d7c20 PUSH %RBP |
0x4d7c21 MOV %RSP,%RBP |
0x4d7c24 PUSH %R15 |
0x4d7c26 PUSH %R14 |
0x4d7c28 PUSH %R12 |
0x4d7c2a PUSH %RBX |
0x4d7c2b SUB $0x20,%RSP |
0x4d7c2f MOV %R8,%RBX |
0x4d7c32 MOV %RCX,%R15 |
0x4d7c35 MOV %RDX,%R12 |
0x4d7c38 MOVL $0,-0x24(%RBP) |
0x4d7c3f MOV (%RDI),%R14D |
0x4d7c42 MOVQ $0,-0x30(%RBP) |
0x4d7c4a MOVQ $0x1,-0x38(%RBP) |
0x4d7c52 SUB $0x8,%RSP |
0x4d7c56 LEA -0x38(%RBP),%RAX |
0x4d7c5a LEA -0x24(%RBP),%RCX |
0x4d7c5e LEA -0x30(%RBP),%R8 |
0x4d7c62 LEA 0x10(%RBP),%R9 |
0x4d7c66 MOV $0x52c450,%EDI |
0x4d7c6b MOV %R14D,%ESI |
0x4d7c6e MOV $0x22,%EDX |
0x4d7c73 PUSH $0x1 |
0x4d7c75 PUSH $0x1 |
0x4d7c77 PUSH %RAX |
0x4d7c78 CALL 410420 <__kmpc_for_static_init_8@plt> |
0x4d7c7d ADD $0x20,%RSP |
0x4d7c81 MOV -0x30(%RBP),%RAX |
0x4d7c85 MOV 0x10(%RBP),%RDX |
0x4d7c89 MOV %RDX,%R9 |
0x4d7c8c SUB %RAX,%R9 |
0x4d7c8f JB 4d7d66 |
0x4d7c95 VMOVQ %R12,%XMM0 |
0x4d7c9a LEA (%R15,%RDX,8),%RCX |
0x4d7c9e LEA (%RBX,%RAX,8),%RSI |
0x4d7ca2 LEA (%R15,%RAX,8),%RDI |
0x4d7ca6 CMP %RSI,%RCX |
0x4d7ca9 JB 4d7cde |
0x4d7cab LEA (%RBX,%RDX,8),%RCX |
0x4d7caf CMP %RDI,%RCX |
0x4d7cb2 JB 4d7cde |
0x4d7cb4 INC %RDX |
0x4d7cb7 NOPW (%RAX,%RAX,1) |
(4043) 0x4d7cc0 VMOVSD (%R15,%RAX,8),%XMM1 |
(4043) 0x4d7cc6 VFMADD213SD (%RBX,%RAX,8),%XMM0,%XMM1 |
(4043) 0x4d7ccc VMOVSD %XMM1,(%RBX,%RAX,8) |
(4043) 0x4d7cd1 INC %RAX |
(4043) 0x4d7cd4 CMP %RAX,%RDX |
(4043) 0x4d7cd7 JNE 4d7cc0 |
0x4d7cd9 JMP 4d7d66 |
0x4d7cde INC %R9 |
0x4d7ce1 MOV %R9,%R8 |
0x4d7ce4 AND $-0x4,%R8 |
0x4d7ce8 JE 4d7d26 |
0x4d7cea LEA -0x1(%R8),%RDX |
0x4d7cee VBROADCASTSD %XMM0,%YMM0 |
0x4d7cf3 XOR %ECX,%ECX |
0x4d7cf5 NOPW %CS:(%RAX,%RAX,1) |
(4042) 0x4d7d00 VMOVUPD (%RDI,%RCX,8),%YMM1 |
(4042) 0x4d7d05 VFMADD213PD (%RSI,%RCX,8),%YMM0,%YMM1 |
(4042) 0x4d7d0b VMOVUPD %YMM1,(%RSI,%RCX,8) |
(4042) 0x4d7d10 ADD $0x4,%RCX |
(4042) 0x4d7d14 CMP %RDX,%RCX |
(4042) 0x4d7d17 JLE 4d7d00 |
0x4d7d19 CMP %R8,%R9 |
0x4d7d1c JE 4d7d66 |
0x4d7d1e VPBROADCASTQ %R9,%YMM1 |
0x4d7d24 JMP 4d7d34 |
0x4d7d26 VPBROADCASTQ %R9,%YMM1 |
0x4d7d2c VBROADCASTSD %XMM0,%YMM0 |
0x4d7d31 XOR %R8D,%R8D |
0x4d7d34 VPBROADCASTQ %R8,%YMM2 |
0x4d7d3a VPADDQ 0x1d31e(%RIP),%YMM2,%YMM2 |
0x4d7d42 VPCMPLTUQ %YMM1,%YMM2,%K1 |
0x4d7d49 ADD %R8,%RAX |
0x4d7d4c VMOVUPD (%R15,%RAX,8),%YMM1{%K1}{z} |
0x4d7d53 VMOVUPD (%RBX,%RAX,8),%YMM2{%K1}{z} |
0x4d7d5a VFMADD231PD %YMM1,%YMM0,%YMM2 |
0x4d7d5f VMOVUPD %YMM2,(%RBX,%RAX,8){%K1} |
0x4d7d66 MOV $0x52c470,%EDI |
0x4d7d6b MOV %R14D,%ESI |
0x4d7d6e ADD $0x20,%RSP |
0x4d7d72 POP %RBX |
0x4d7d73 POP %R12 |
0x4d7d75 POP %R14 |
0x4d7d77 POP %R15 |
0x4d7d79 POP %RBP |
0x4d7d7a VZEROUPPER |
0x4d7d7d JMP 410170 |
0x4d7d82 NOPW %CS:(%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►34.62+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_SeqVectorAxpy | vector.c:449 | exec |
○ | hypre_PCGSolve | pcg.c:526 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►34.62+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_SeqVectorAxpy | vector.c:449 | exec |
○ | hypre_PCGSolve | pcg.c:511 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 | |
►30.77+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | hypre_SeqVectorAxpy | vector.c:449 | exec |
○ | hypre_PCGSolve | pcg.c:709 | exec |
○ | main | amg.c:419 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | vector.c:449-452 |
Module | exec |
nb instructions | 78 |
nb uops | 81 |
loop length | 318 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 3 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 20.25 cycles |
front end | 20.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 8.17 | 7.83 | 13.00 | 10.25 | 10.25 | 8.00 |
cycles | 10.25 | 10.25 | 8.17 | 7.83 | 13.00 | 10.25 | 10.25 | 8.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 19.44 |
Stall cycles | 0.00 |
Front-end | 20.25 |
Dispatch | 13.00 |
Overall L1 | 20.25 |
all | 14% |
load | 50% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 14% |
all | 66% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 25% |
load | 75% |
store | 25% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 14% |
load | 28% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 14% |
all | 37% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 19% |
load | 39% |
store | 17% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
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 %R8,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVL $0,-0x24(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV (%RDI),%R14D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOVQ $0x1,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
SUB $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x38(%RBP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x24(%RBP),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x30(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x10(%RBP),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x52c450,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x22,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RAX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 410420 <__kmpc_for_static_init_8@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7d66 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVQ %R12,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R15,%RDX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RBX,%RAX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%R15,%RAX,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7cde | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%RDX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7cde | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d7d66 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4d7d26 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%R8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM0,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %ECX,%ECX | 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 |
CMP %R8,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4d7d66 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %R9,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 4d7d34 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VPBROADCASTQ %R9,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VBROADCASTSD %XMM0,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %R8,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ 0x1d31e(%RIP),%YMM2,%YMM2 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %YMM1,%YMM2,%K1 | |||||||||||
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD (%R15,%RAX,8),%YMM1{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD (%RBX,%RAX,8),%YMM2{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VFMADD231PD %YMM1,%YMM0,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM2,(%RBX,%RAX,8){%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x52c470,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,%ESI | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JMP 410170 <__kmpc_for_static_fini@plt> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | vector.c:449-452 |
Module | exec |
nb instructions | 78 |
nb uops | 81 |
loop length | 318 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 3 |
used zmm registers | 0 |
nb stack references | 4 |
micro-operation queue | 20.25 cycles |
front end | 20.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 10.25 | 10.25 | 8.17 | 7.83 | 13.00 | 10.25 | 10.25 | 8.00 |
cycles | 10.25 | 10.25 | 8.17 | 7.83 | 13.00 | 10.25 | 10.25 | 8.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 19.44 |
Stall cycles | 0.00 |
Front-end | 20.25 |
Dispatch | 13.00 |
Overall L1 | 20.25 |
all | 14% |
load | 50% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 14% |
all | 66% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 25% |
load | 75% |
store | 25% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 33% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 14% |
load | 28% |
store | 6% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 14% |
all | 37% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 19% |
load | 39% |
store | 17% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 14% |
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 %R8,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RCX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOVL $0,-0x24(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV (%RDI),%R14D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOVQ $0x1,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
SUB $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0x38(%RBP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x24(%RBP),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x30(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA 0x10(%RBP),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x52c450,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x22,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RAX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 410420 <__kmpc_for_static_init_8@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RDX,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB %RAX,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7d66 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVQ %R12,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
LEA (%R15,%RDX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RBX,%RAX,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%R15,%RAX,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RSI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7cde | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (%RBX,%RDX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 4d7cde | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4d7d66 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R9,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R8 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4d7d26 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA -0x1(%R8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VBROADCASTSD %XMM0,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %ECX,%ECX | 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 |
CMP %R8,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4d7d66 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VPBROADCASTQ %R9,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
JMP 4d7d34 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VPBROADCASTQ %R9,%YMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VBROADCASTSD %XMM0,%YMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
XOR %R8D,%R8D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VPBROADCASTQ %R8,%YMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPADDQ 0x1d31e(%RIP),%YMM2,%YMM2 | 1 | 0.33 | 0.33 | 0.50 | 0.50 | 0 | 0.33 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %YMM1,%YMM2,%K1 | |||||||||||
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVUPD (%R15,%RAX,8),%YMM1{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVUPD (%RBX,%RAX,8),%YMM2{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VFMADD231PD %YMM1,%YMM0,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM2,(%RBX,%RAX,8){%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x52c470,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14D,%ESI | 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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JMP 410170 <__kmpc_for_static_fini@plt> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼hypre_SeqVectorAxpy.extracted– | 0.71 | 0.26 |
○Loop 4042 - vector.c:449-452 - exec | 0.71 | 0.26 |
○Loop 4043 - vector.c:449-452 - exec | 0 | 0 |