Loop Id: 2355 | Module: exec | Source: par_strength.c:2000-2083 [...] | Coverage: 0.01% |
---|
Loop Id: 2355 | Module: exec | Source: par_strength.c:2000-2083 [...] | Coverage: 0.01% |
---|
0x498de0 INC %R15 |
0x498de3 CMP %R11,%R15 |
0x498de6 JE 499a39 |
0x498dec MOV 0xa0(%RBP),%RAX |
0x498df3 MOV (%RAX,%R15,8),%R8 |
0x498df7 MOV -0x30(%RBP),%R9 |
0x498dfb MOV -0x38(%RBP),%RDX |
0x498dff MOV -0x58(%RBP),%RAX |
0x498e03 MOV (%RAX,%R8,8),%R10 |
0x498e07 JMP 498e27 |
(2359) 0x498e20 INC %R10 |
(2359) 0x498e23 MOV -0x58(%RBP),%RAX |
(2359) 0x498e27 CMP 0x8(%RAX,%R8,8),%R10 |
(2359) 0x498e2c JGE 498f60 |
(2359) 0x498e32 MOV -0x88(%RBP),%RAX |
(2359) 0x498e39 MOV (%RAX,%R10,8),%RDI |
(2359) 0x498e3d MOV -0x68(%RBP),%RAX |
(2359) 0x498e41 CMPQ $0,(%RAX,%RDI,8) |
(2359) 0x498e46 JLE 498e6d |
(2359) 0x498e48 MOV 0x78(%RBP),%RAX |
(2359) 0x498e4c MOV (%RAX,%RDI,8),%RAX |
(2359) 0x498e50 CMP %R9,(%R14,%RAX,8) |
(2359) 0x498e54 JGE 498e6d |
(2359) 0x498e56 MOV -0x30(%RBP),%RCX |
(2359) 0x498e5a MOV %RCX,(%R14,%RAX,8) |
(2359) 0x498e5e MOV 0x30(%RBP),%RSI |
(2359) 0x498e62 MOV (%RSI),%RBX |
(2359) 0x498e65 MOV %RAX,(%RBX,%RCX,8) |
(2359) 0x498e69 INCQ -0x30(%RBP) |
(2359) 0x498e6d MOV -0x58(%RBP),%RAX |
(2359) 0x498e71 MOV (%RAX,%RDI,8),%RBX |
(2359) 0x498e75 MOV 0x8(%RAX,%RDI,8),%RAX |
(2359) 0x498e7a JMP 498e83 |
(2361) 0x498e80 INC %RBX |
(2361) 0x498e83 CMP %RAX,%RBX |
(2361) 0x498e86 JGE 498ee0 |
(2361) 0x498e88 MOV -0x88(%RBP),%RCX |
(2361) 0x498e8f MOV (%RCX,%RBX,8),%RCX |
(2361) 0x498e93 MOV -0x68(%RBP),%RSI |
(2361) 0x498e97 CMPQ $0,(%RSI,%RCX,8) |
(2361) 0x498e9c JLE 498e80 |
(2361) 0x498e9e MOV 0x78(%RBP),%RSI |
(2361) 0x498ea2 MOV (%RSI,%RCX,8),%RCX |
(2361) 0x498ea6 CMP %R15,%RCX |
(2361) 0x498ea9 JE 498e80 |
(2361) 0x498eab CMP %R9,(%R14,%RCX,8) |
(2361) 0x498eaf JGE 498e80 |
(2361) 0x498eb1 MOV -0x30(%RBP),%RAX |
(2361) 0x498eb5 MOV %RAX,(%R14,%RCX,8) |
(2361) 0x498eb9 MOV 0x30(%RBP),%RSI |
(2361) 0x498ebd MOV (%RSI),%RSI |
(2361) 0x498ec0 MOV %RCX,(%RSI,%RAX,8) |
(2361) 0x498ec4 INCQ -0x30(%RBP) |
(2361) 0x498ec8 MOV -0x58(%RBP),%RAX |
(2361) 0x498ecc MOV 0x8(%RAX,%RDI,8),%RAX |
(2361) 0x498ed1 JMP 498e80 |
(2359) 0x498ee0 MOV 0x10(%RBP),%RAX |
(2359) 0x498ee4 MOV (%RAX,%RDI,8),%RBX |
(2359) 0x498ee8 MOV 0x8(%RAX,%RDI,8),%RAX |
(2359) 0x498eed JMP 498f03 |
(2360) 0x498f00 INC %RBX |
(2360) 0x498f03 CMP %RAX,%RBX |
(2360) 0x498f06 JGE 498e20 |
(2360) 0x498f0c MOV 0x18(%RBP),%RCX |
(2360) 0x498f10 MOV (%RCX,%RBX,8),%RCX |
(2360) 0x498f14 MOV 0x70(%RBP),%RSI |
(2360) 0x498f18 CMPQ $0,(%RSI,%RCX,8) |
(2360) 0x498f1d JLE 498f00 |
(2360) 0x498f1f MOV 0x80(%RBP),%RSI |
(2360) 0x498f26 MOV (%RSI,%RCX,8),%RCX |
(2360) 0x498f2a CMP %RDX,(%R12,%RCX,8) |
(2360) 0x498f2e JGE 498f00 |
(2360) 0x498f30 MOV -0x38(%RBP),%RAX |
(2360) 0x498f34 MOV %RAX,(%R12,%RCX,8) |
(2360) 0x498f38 MOV (%R13),%RSI |
(2360) 0x498f3c MOV %RCX,(%RSI,%RAX,8) |
(2360) 0x498f40 INCQ -0x38(%RBP) |
(2360) 0x498f44 MOV 0x10(%RBP),%RAX |
(2360) 0x498f48 MOV 0x8(%RAX,%RDI,8),%RAX |
(2360) 0x498f4d JMP 498f00 |
0x498f60 MOV 0x10(%RBP),%RAX |
0x498f64 MOV (%RAX,%R8,8),%R10 |
0x498f68 JMP 498f87 |
(2356) 0x498f80 INC %R10 |
(2356) 0x498f83 MOV 0x10(%RBP),%RAX |
(2356) 0x498f87 CMP 0x8(%RAX,%R8,8),%R10 |
(2356) 0x498f8c JGE 498de0 |
(2356) 0x498f92 MOV 0x18(%RBP),%RAX |
(2356) 0x498f96 MOV (%RAX,%R10,8),%RDI |
(2356) 0x498f9a MOV 0x70(%RBP),%RAX |
(2356) 0x498f9e CMPQ $0,(%RAX,%RDI,8) |
(2356) 0x498fa3 JLE 498fca |
(2356) 0x498fa5 MOV 0x80(%RBP),%RAX |
(2356) 0x498fac MOV (%RAX,%RDI,8),%RAX |
(2356) 0x498fb0 CMP %RDX,(%R12,%RAX,8) |
(2356) 0x498fb4 JGE 498fca |
(2356) 0x498fb6 MOV -0x38(%RBP),%RCX |
(2356) 0x498fba MOV %RCX,(%R12,%RAX,8) |
(2356) 0x498fbe MOV (%R13),%RBX |
(2356) 0x498fc2 MOV %RAX,(%RBX,%RCX,8) |
(2356) 0x498fc6 INCQ -0x38(%RBP) |
(2356) 0x498fca MOV 0x50(%RBP),%RAX |
(2356) 0x498fce MOV (%RAX,%RDI,8),%RBX |
(2356) 0x498fd2 MOV 0x8(%RAX,%RDI,8),%RAX |
(2356) 0x498fd7 JMP 498fe3 |
(2358) 0x498fe0 INC %RBX |
(2358) 0x498fe3 CMP %RAX,%RBX |
(2358) 0x498fe6 JGE 499020 |
(2358) 0x498fe8 MOV 0x58(%RBP),%RCX |
(2358) 0x498fec MOV (%RCX,%RBX,8),%RCX |
(2358) 0x498ff0 CMP %R15,%RCX |
(2358) 0x498ff3 JE 498fe0 |
(2358) 0x498ff5 CMP %R9,(%R14,%RCX,8) |
(2358) 0x498ff9 JGE 498fe0 |
(2358) 0x498ffb MOV -0x30(%RBP),%RAX |
(2358) 0x498fff MOV %RAX,(%R14,%RCX,8) |
(2358) 0x499003 MOV 0x30(%RBP),%RSI |
(2358) 0x499007 MOV (%RSI),%RSI |
(2358) 0x49900a MOV %RCX,(%RSI,%RAX,8) |
(2358) 0x49900e INCQ -0x30(%RBP) |
(2358) 0x499012 MOV 0x50(%RBP),%RAX |
(2358) 0x499016 MOV 0x8(%RAX,%RDI,8),%RAX |
(2358) 0x49901b JMP 498fe0 |
(2356) 0x499020 MOV 0x60(%RBP),%RCX |
(2356) 0x499024 MOV (%RCX,%RDI,8),%RAX |
(2356) 0x499028 MOV 0x8(%RCX,%RDI,8),%RBX |
(2356) 0x49902d JMP 499043 |
(2357) 0x499040 INC %RAX |
(2357) 0x499043 CMP %RBX,%RAX |
(2357) 0x499046 JGE 498f80 |
(2357) 0x49904c MOV 0x68(%RBP),%RCX |
(2357) 0x499050 MOV (%RCX,%RAX,8),%RCX |
(2357) 0x499054 CMP %RDX,(%R12,%RCX,8) |
(2357) 0x499058 JGE 499040 |
(2357) 0x49905a MOV -0x38(%RBP),%RSI |
(2357) 0x49905e MOV %RSI,(%R12,%RCX,8) |
(2357) 0x499062 MOV (%R13),%RBX |
(2357) 0x499066 MOV %RCX,(%RBX,%RSI,8) |
(2357) 0x49906a INCQ -0x38(%RBP) |
(2357) 0x49906e MOV 0x60(%RBP),%RCX |
(2357) 0x499072 MOV 0x8(%RCX,%RDI,8),%RBX |
(2357) 0x499077 JMP 499040 |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/par_strength.c: 2000 - 2083 |
-------------------------------------------------------------------------------- |
2000: for (ic = ic_begin; ic < ic_end; ic++) |
[...] |
2006: HYPRE_Int i1 = coarse_to_fine[ic]; |
2007: |
2008: HYPRE_Int jj_row_begin_diag = num_nonzeros_diag; |
2009: HYPRE_Int jj_row_begin_offd = num_nonzeros_offd; |
2010: |
2011: for (jj1 = S_diag_i[i1]; jj1 < S_diag_i[i1+1]; jj1++) |
2012: { |
2013: i2 = S_diag_j[jj1]; |
2014: if (CF_marker[i2] > 0) |
2015: { |
2016: index = fine_to_coarse[i2]; |
2017: if (S_marker[index] < jj_row_begin_diag) |
2018: { |
2019: S_marker[index] = num_nonzeros_diag; |
2020: C_diag_j[num_nonzeros_diag] = index; |
2021: num_nonzeros_diag++; |
2022: } |
2023: } |
2024: for (jj2 = S_diag_i[i2]; jj2 < S_diag_i[i2+1]; jj2++) |
2025: { |
2026: i3 = S_diag_j[jj2]; |
2027: if (CF_marker[i3] > 0) |
2028: { |
2029: index = fine_to_coarse[i3]; |
2030: if (index != ic && S_marker[index] < jj_row_begin_diag) |
2031: { |
2032: S_marker[index] = num_nonzeros_diag; |
2033: C_diag_j[num_nonzeros_diag] = index; |
2034: num_nonzeros_diag++; |
2035: } |
2036: } |
2037: } |
2038: for (jj2 = S_offd_i[i2]; jj2 < S_offd_i[i2+1]; jj2++) |
2039: { |
2040: i3 = S_offd_j[jj2]; |
2041: if (CF_marker_offd[i3] > 0) |
2042: { |
2043: index = map_S_to_C[i3]; |
2044: if (S_marker_offd[index] < jj_row_begin_offd) |
2045: { |
2046: S_marker_offd[index] = num_nonzeros_offd; |
2047: C_offd_j[num_nonzeros_offd] = index; |
2048: num_nonzeros_offd++; |
2049: } |
2050: } |
2051: } |
2052: } |
2053: for (jj1 = S_offd_i[i1]; jj1 < S_offd_i[i1+1]; jj1++) |
2054: { |
2055: i2 = S_offd_j[jj1]; |
2056: if (CF_marker_offd[i2] > 0) |
2057: { |
2058: index = map_S_to_C[i2]; |
2059: if (S_marker_offd[index] < jj_row_begin_offd) |
2060: { |
2061: S_marker_offd[index] = num_nonzeros_offd; |
2062: C_offd_j[num_nonzeros_offd] = index; |
2063: num_nonzeros_offd++; |
2064: } |
2065: } |
2066: for (jj2 = S_ext_diag_i[i2]; jj2 < S_ext_diag_i[i2+1]; jj2++) |
2067: { |
2068: i3 = S_ext_diag_j[jj2]; |
2069: if (i3 != ic && S_marker[i3] < jj_row_begin_diag) |
2070: { |
2071: S_marker[i3] = num_nonzeros_diag; |
2072: C_diag_j[num_nonzeros_diag] = i3; |
2073: num_nonzeros_diag++; |
2074: } |
2075: } |
2076: for (jj2 = S_ext_offd_i[i2]; jj2 < S_ext_offd_i[i2+1]; jj2++) |
2077: { |
2078: i3 = S_ext_offd_j[jj2]; |
2079: if (S_marker_offd[i3] < jj_row_begin_offd) |
2080: { |
2081: S_marker_offd[i3] = num_nonzeros_offd; |
2082: C_offd_j[num_nonzeros_offd] = i3; |
2083: num_nonzeros_offd++; |
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:1668 | 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 / |
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 | 1.23 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:2000-2083 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 4.00 |
CQA cycles if fully vectorized | 0.50 |
Front-end cycles | 3.25 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.33 |
Stall cycles (UFS) | 0.90 |
Nb insns | 13.00 |
Nb uops | 13.00 |
Nb loads | 8.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 16.00 |
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 | 0.00 |
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 | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
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 | NA |
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 | 1.23 |
Bottlenecks | P2, P3, |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source | par_strength.c:2000-2083 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 4.00 |
CQA cycles if fully vectorized | 0.50 |
Front-end cycles | 3.25 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 0.00 |
P4 cycles | 1.00 |
P5 cycles | 2.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 4.33 |
Stall cycles (UFS) | 0.90 |
Nb insns | 13.00 |
Nb uops | 13.00 |
Nb loads | 8.00 |
Nb stores | 0.00 |
Nb stack references | 5.00 |
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 | 16.00 |
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 | 0.00 |
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 | NA |
Vector-efficiency ratio all | 12.50 |
Vector-efficiency ratio load | 12.50 |
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 | NA |
Path / |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:2000-2083 |
Module | exec |
nb instructions | 13 |
nb uops | 13 |
loop length | 51 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 3.25 cycles |
front end | 3.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.00 | 1.00 | 4.00 | 4.00 | 0.00 | 1.00 | 2.00 | 0.00 |
cycles | 1.00 | 1.00 | 4.00 | 4.00 | 0.00 | 1.00 | 2.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.33 |
Stall cycles | 0.90 |
LM full (events) | 2.16 |
Front-end | 3.25 |
Dispatch | 4.00 |
Overall L1 | 4.00 |
all | 0% |
load | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R11,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 499a39 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R15,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R8,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498e27 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R8,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498f87 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | hypre_BoomerAMGCreate2ndS.extracted.17 |
Source file and lines | par_strength.c:2000-2083 |
Module | exec |
nb instructions | 13 |
nb uops | 13 |
loop length | 51 |
used x86 registers | 8 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 5 |
micro-operation queue | 3.25 cycles |
front end | 3.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.00 | 1.00 | 4.00 | 4.00 | 0.00 | 1.00 | 2.00 | 0.00 |
cycles | 1.00 | 1.00 | 4.00 | 4.00 | 0.00 | 1.00 | 2.00 | 0.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 4.33 |
Stall cycles | 0.90 |
LM full (events) | 2.16 |
Front-end | 3.25 |
Dispatch | 4.00 |
Overall L1 | 4.00 |
all | 0% |
load | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 12% |
load | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
INC %R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R11,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 499a39 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0xa0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R15,8),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x30(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x38(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R8,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498e27 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV 0x10(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RAX,%R8,8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 498f87 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |