Loop Id: 1790 | Module: exec | Source: stl_tree.h:782-1952 [...] | Coverage: 0.01% |
---|
Loop Id: 1790 | Module: exec | Source: stl_tree.h:782-1952 [...] | Coverage: 0.01% |
---|
0x49a9b0 TEST %EAX,%EAX |
0x49a9b2 JS 49aa10 |
0x49a9b4 MOV %R14,%RAX |
0x49a9b7 ADD $0x10,%RAX |
0x49a9bb MOV %R14,%R13 |
0x49a9be MOV (%RAX),%R14 [2] |
0x49a9c1 TEST %R14,%R14 |
0x49a9c4 JE 49aa1f |
0x49a9c6 MOV 0x28(%R14),%RBX [1] |
0x49a9ca CMP $0x7,%RBX |
0x49a9ce MOV $0x7,%EDX |
0x49a9d3 CMOVB %RBX,%RDX |
0x49a9d7 TEST %RDX,%RDX |
0x49a9da JE 49a9ec |
0x49a9dc MOV 0x20(%R14),%RDI [1] |
0x49a9e0 MOV %R12,%RSI |
0x49a9e3 CALL 403100 <memcmp@plt> |
0x49a9e8 TEST %EAX,%EAX |
0x49a9ea JNE 49a9b0 |
0x49a9ec ADD $-0x7,%RBX |
0x49a9f0 CMP $-0x7fffffff,%RBX |
0x49a9f7 MOV $-0x80000000,%RAX |
0x49a9fe CMOVGE %RBX,%RAX |
0x49aa02 CMP $0x7fffffff,%RBX |
0x49aa09 JLE 49a9b0 |
0x49aa0b JMP 49a9b4 |
0x49aa10 ADD $0x18,%R14 |
0x49aa14 MOV %R14,%RAX |
0x49aa17 MOV (%RAX),%R14 [3] |
0x49aa1a TEST %R14,%R14 |
0x49aa1d JNE 49a9c6 |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/char_traits.h: 386 - 399 |
-------------------------------------------------------------------------------- |
386: if (__n == 0) |
[...] |
399: return __builtin_memcmp(__s1, __s2, __n); |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/basic_string.h: 236 - 3833 |
-------------------------------------------------------------------------------- |
236: { return _M_dataplus._M_p; } |
[...] |
493: const difference_type __d = difference_type(__n1 - __n2); |
494: |
495: if (__d > __gnu_cxx::__numeric_traits<int>::__max) |
[...] |
1073: { return _M_string_length; } |
[...] |
3188: const size_type __len = std::min(__size, __osize); |
3189: |
3190: int __r = traits_type::compare(_M_data(), __str.data(), __len); |
3191: if (!__r) |
[...] |
3833: { return __lhs.compare(__rhs) < 0; } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_tree.h: 782 - 1952 |
-------------------------------------------------------------------------------- |
782: { return static_cast<_Link_type>(__x->_M_left); } |
[...] |
790: { return static_cast<_Link_type>(__x->_M_right); } |
[...] |
1951: while (__x != 0) |
1952: if (!_M_impl._M_key_compare(_S_key(__x), __k)) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | Kripke::SweepSolver(Kripke::Co[...] | stl_vector.h:366 | exec |
○ | Kripke::SteadyStateSolver(Krip[...] | stl_vector.h:366 | exec |
○ | main | kripke.cpp:482 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.72 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.41 |
Bottlenecks | micro-operation queue, |
Function | Kripke::SweepComm::markComplete(Kripke::SdomId) |
Source | char_traits.h:386-399,basic_string.h:236-3833,stl_tree.h:782-1952 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 7.75 |
CQA cycles if no scalar integer | 7.75 |
CQA cycles if FP arith vectorized | 7.75 |
CQA cycles if fully vectorized | 0.61 |
Front-end cycles | 7.75 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 5.50 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 1.00 |
P4 cycles | 5.50 |
P5 cycles | 5.50 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 11.32 |
Stall cycles (UFS) | 3.46 |
Nb insns | 31.00 |
Nb uops | 31.00 |
Nb loads | 4.00 |
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 | 4.13 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
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 | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 11.16 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 10.80 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 12.72 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.41 |
Bottlenecks | micro-operation queue, |
Function | Kripke::SweepComm::markComplete(Kripke::SdomId) |
Source | char_traits.h:386-399,basic_string.h:236-3833,stl_tree.h:782-1952 |
Source loop unroll info | multi-versionned |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 7.75 |
CQA cycles if no scalar integer | 7.75 |
CQA cycles if FP arith vectorized | 7.75 |
CQA cycles if fully vectorized | 0.61 |
Front-end cycles | 7.75 |
DIV/SQRT cycles | 5.50 |
P0 cycles | 5.50 |
P1 cycles | 2.00 |
P2 cycles | 2.00 |
P3 cycles | 1.00 |
P4 cycles | 5.50 |
P5 cycles | 5.50 |
P6 cycles | 1.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 11.32 |
Stall cycles (UFS) | 3.46 |
Nb insns | 31.00 |
Nb uops | 31.00 |
Nb loads | 4.00 |
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 | 4.13 |
Bytes prefetched | 0.00 |
Bytes loaded | 32.00 |
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 | 0.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 11.16 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 10.80 |
Path / |
Function | Kripke::SweepComm::markComplete(Kripke::SdomId) |
Source file and lines | stl_tree.h:782-1952 |
Module | exec |
nb instructions | 31 |
nb uops | 31 |
loop length | 108 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 7.75 cycles |
front end | 7.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.50 | 5.50 | 2.00 | 2.00 | 1.00 | 5.50 | 5.50 | 1.00 |
cycles | 5.50 | 5.50 | 2.00 | 2.00 | 1.00 | 5.50 | 5.50 | 1.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 11.32 |
Stall cycles | 3.46 |
RS full (events) | 6.43 |
Front-end | 7.75 |
Dispatch | 5.50 |
Overall L1 | 7.75 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 11% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 49aa10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R14,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 49aa1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x28(%R14),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x7,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x7,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RBX,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %RDX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 49a9ec | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x20(%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 403100 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 49a9b0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD $-0x7,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $-0x7fffffff,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $-0x80000000,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVGE %RBX,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
CMP $0x7fffffff,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 49a9b0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 49a9b4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0x18,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R14,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 49a9c6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | Kripke::SweepComm::markComplete(Kripke::SdomId) |
Source file and lines | stl_tree.h:782-1952 |
Module | exec |
nb instructions | 31 |
nb uops | 31 |
loop length | 108 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 7.75 cycles |
front end | 7.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.50 | 5.50 | 2.00 | 2.00 | 1.00 | 5.50 | 5.50 | 1.00 |
cycles | 5.50 | 5.50 | 2.00 | 2.00 | 1.00 | 5.50 | 5.50 | 1.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 11.32 |
Stall cycles | 3.46 |
RS full (events) | 6.43 |
Front-end | 7.75 |
Dispatch | 5.50 |
Overall L1 | 7.75 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 11% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 10% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 49aa10 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x10,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R14,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 49aa1f | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x28(%R14),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0x7,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $0x7,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVB %RBX,%RDX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %RDX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 49a9ec | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x20(%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 403100 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 49a9b0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
ADD $-0x7,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $-0x7fffffff,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV $-0x80000000,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVGE %RBX,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
CMP $0x7fffffff,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 49a9b0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 49a9b4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0x18,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %R14,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R14,%R14 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 49a9c6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |