| Loop Id: 201 | Module: exec | Source: advec_mom.cpp:114-139 [...] | Coverage: 4.49% |
|---|
| Loop Id: 201 | Module: exec | Source: advec_mom.cpp:114-139 [...] | Coverage: 4.49% |
|---|
0x430ea0 LDR D30, [X23, X0,LSL #3] [4] |
0x430ea4 SUB W2, W0, #2 |
0x430ea8 SUB X1, X0, #1 |
0x430eac ORR X5, XZR, X0 |
0x430eb0 ORR W6, WZR, W2 |
0x430eb4 FCMPE D30, #0 |
0x430eb8 B.GE 430ecc |
0x430ebc ORR X5, XZR, X1 |
0x430ec0 ORR W6, WZR, W0 |
0x430ec4 ADD W2, W0, #1 |
0x430ec8 ORR X1, XZR, X0 |
0x430ecc ADD X10, X4, X5 |
0x430ed0 ADD X3, X4, X1 |
0x430ed4 ADD X5, X4, W2,SXTW |
0x430ed8 LDR D31, [X26, X5,LSL #3] [6] |
0x430edc FABS D27, D30 |
0x430ee0 ADD X8, X11, X1 |
0x430ee4 LDR D28, [X26, X3,LSL #3] [6] |
0x430ee8 LDR D29, [X26, X10,LSL #3] [6] |
0x430eec FSUB D0, D28, S31 |
0x430ef0 FSUB D1, D29, S28 |
0x430ef4 FABS D25, D0 |
0x430ef8 FMUL D2, D0, D1 |
0x430efc FABS D26, D1 |
0x430f00 FMINNM D22, D25, D26 |
0x430f04 FCMPE D2, #0 |
0x430f08 B.LS 430f58 |
0x430f0c LDR D3, [X9, X8,LSL #3] [2] |
0x430f10 FCMPE D1, #0 |
0x430f14 LDR D23, [X24, X0,LSL #3] [5] |
0x430f18 LDR D19, [X22, W6,SXTW #3] [3] |
0x430f1c FDIV D4, D27, D3 |
0x430f20 FCSEL D21, D16, D24, #9 |
0x430f24 FMUL D20, D23, D18 |
0x430f28 FADD D5, D4, D24 |
0x430f2c FSUB D6, D17, S4 |
0x430f30 FSUB D7, D24, S4 |
0x430f34 FMUL D31, D5, D25 |
0x430f38 FMUL D27, D6, D26 |
0x430f3c FDIV D29, D31, D19 |
0x430f40 FDIV D0, D27, D23 |
0x430f44 FADD D1, D29, D0 |
0x430f48 FMUL D25, D1, D20 |
0x430f4c FMINNM D26, D25, D22 |
0x430f50 FMUL D2, D26, D7 |
0x430f54 FMADD D28, D21, D2, D28 |
0x430f58 FMUL D30, D30, D28 |
0x430f5c STR D30, [X7, X0,LSL #3] [1] |
0x430f60 ADD X0, X0, #1 |
0x430f64 CMP X0, X25 |
0x430f68 B.NE 430ea0 |
/home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/context.h: 69 - 69 |
-------------------------------------------------------------------------------- |
69: T &operator()(size_t i, size_t j) const { return data[i + j * sizeX]; } |
/home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/build/CloverLeaf2.0-CXX/src/omp/advec_mom.cpp: 114 - 139 |
-------------------------------------------------------------------------------- |
114: if (node_flux(i, j) < 0.0) { |
115: upwind = i + 2; |
116: donor = i + 1; |
117: downwind = i; |
118: dif = donor; |
119: } else { |
120: upwind = i - 1; |
121: donor = i; |
122: downwind = i + 1; |
123: dif = upwind; |
124: } |
125: sigma = std::fabs(node_flux(i, j)) / (node_mass_pre(donor, j)); |
126: width = celldx[i]; |
127: vdiffuw = vel1(donor, j) - vel1(upwind, j); |
128: vdiffdw = vel1(downwind, j) - vel1(donor, j); |
129: limiter = 0.0; |
130: if (vdiffuw * vdiffdw > 0.0) { |
131: auw = std::fabs(vdiffuw); |
132: adw = std::fabs(vdiffdw); |
133: wind = 1.0; |
134: if (vdiffdw <= 0.0) wind = -1.0; |
135: limiter = |
136: wind * std::fmin(std::fmin(width * ((2.0 - sigma) * adw / width + (1.0 + sigma) * auw / celldx[dif]) / 6.0, auw), adw); |
137: } |
138: advec_vel_s = vel1(donor, j) + (1.0 - sigma) * limiter; |
139: mom_flux(i, j) = advec_vel_s * node_flux(i, j); |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►25.30+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►25.29+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►24.77+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►24.63+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►49.82+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►12.71+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►12.62+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►12.43+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►12.41+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►74.90+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►6.38+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►6.28+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►6.26+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►6.18+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►87.32+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►3.23+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►3.19+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►3.15+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►3.10+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►93.59+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.66+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.63+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.56+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.56+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►95.64+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.12+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:70 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.08+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:101 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.08+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:68 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| ►1.08+ | GOMP_parallel | libgomp.so.1.0.0 | |
| ○ | advec_mom_kernel(int, int, int[...] | advec_mom.cpp:146 | exec |
| ○ | advec_mom_driver(global_variab[...] | advec_mom.cpp:244 | exec |
| ○ | advection(global_variables&) | advection.cpp:99 | exec |
| ○ | hydro(global_variables&, paral[...] | basic_string.h:1231 | exec |
| ○ | main | clover_leaf.cpp:209 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | clover_leaf.cpp:51 | exec |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►96.83+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►97.42+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►97.90+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.19+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.40+ | omp_fulfill_event | libgomp.so.1.0.0 | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.25 - 3.05 |
| CQA speedup if FP arith vectorized | 1.84 |
| CQA speedup if fully vectorized | 3.12 - 2.38 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.14 - 1.44 |
| Bottlenecks | |
| Function | advec_mom_kernel(int, int, int, int, clover::Buffer2D |
| Source | context.h:69-69,advec_mom.cpp:114-139 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.25 - 7.12 |
| CQA cycles if no scalar integer | 2.33 |
| CQA cycles if FP arith vectorized | 3.02 - 3.86 |
| CQA cycles if fully vectorized | 1.68 - 2.99 |
| Front-end cycles | 4.94 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 3.00 |
| P3 cycles | 3.00 |
| P4 cycles | 3.00 |
| P5 cycles | 3.00 |
| P6 cycles | 4.75 |
| P7 cycles | 4.75 |
| P8 cycles | 4.75 |
| P9 cycles | 4.75 |
| P10 cycles | 2.33 |
| P11 cycles | 2.00 |
| P12 cycles | 2.17 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 2.63 - 5.24 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 39.50 |
| Nb uops | 39.50 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.10 - 1.54 |
| Nb FLOP add-sub | 4.00 |
| Nb FLOP mul | 4.50 |
| Nb FLOP fma | 0.50 |
| Nb FLOP div | 1.50 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 2.50 |
| Stride unknown | 1.50 |
| Stride indirect | 0.50 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | 0.00 |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 23.85 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 22.25 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | 25.00 |
| Vector-efficiency ratio other | 23.86 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.38 - 3.70 |
| CQA speedup if FP arith vectorized | 2.00 |
| CQA speedup if fully vectorized | 2.57 - 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.06 - 1.55 |
| Bottlenecks | P6, P8, |
| Function | advec_mom_kernel(int, int, int, int, clover::Buffer2D |
| Source | context.h:69-69,advec_mom.cpp:114-139 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.75 - 10.49 |
| CQA cycles if no scalar integer | 2.83 |
| CQA cycles if FP arith vectorized | 3.56 - 5.24 |
| CQA cycles if fully vectorized | 2.63 - 5.24 |
| Front-end cycles | 6.38 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 3.50 |
| P3 cycles | 3.50 |
| P4 cycles | 3.50 |
| P5 cycles | 3.50 |
| P6 cycles | 6.75 |
| P7 cycles | 6.75 |
| P8 cycles | 6.75 |
| P9 cycles | 6.75 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 5.25 - 10.49 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 51.00 |
| Nb uops | 51.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.67 - 1.72 |
| Nb FLOP add-sub | 6.00 |
| Nb FLOP mul | 7.00 |
| Nb FLOP fma | 1.00 |
| Nb FLOP div | 3.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 3.00 |
| Stride unknown | 2.00 |
| Stride indirect | 1.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | 0.00 |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 24.34 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 22.22 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | 25.00 |
| Vector-efficiency ratio other | 25.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.18 |
| CQA speedup if FP arith vectorized | 1.49 |
| CQA speedup if fully vectorized | 5.12 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.14 |
| Bottlenecks | micro-operation queue, |
| Function | advec_mom_kernel(int, int, int, int, clover::Buffer2D |
| Source | context.h:69-69,advec_mom.cpp:114-139 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 4.00 |
| CQA cycles if no scalar integer | 1.83 |
| CQA cycles if FP arith vectorized | 2.69 |
| CQA cycles if fully vectorized | 0.78 |
| Front-end cycles | 4.00 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 3.50 |
| P3 cycles | 3.50 |
| P4 cycles | 3.50 |
| P5 cycles | 3.50 |
| P6 cycles | 2.75 |
| P7 cycles | 2.75 |
| P8 cycles | 2.75 |
| P9 cycles | 2.75 |
| P10 cycles | 1.83 |
| P11 cycles | 1.50 |
| P12 cycles | 1.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 32.00 |
| Nb uops | 32.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.00 |
| Nb FLOP add-sub | 2.00 |
| Nb FLOP mul | 2.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 2.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 22.73 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 20.83 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 22.22 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.38 - 3.70 |
| CQA speedup if FP arith vectorized | 2.00 |
| CQA speedup if fully vectorized | 2.57 - 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.15 - 1.55 |
| Bottlenecks | P6, P8, |
| Function | advec_mom_kernel(int, int, int, int, clover::Buffer2D |
| Source | context.h:69-69,advec_mom.cpp:114-139 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 6.75 - 10.49 |
| CQA cycles if no scalar integer | 2.83 |
| CQA cycles if FP arith vectorized | 3.56 - 5.24 |
| CQA cycles if fully vectorized | 2.63 - 5.24 |
| Front-end cycles | 5.88 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 2.50 |
| P3 cycles | 2.50 |
| P4 cycles | 2.50 |
| P5 cycles | 2.50 |
| P6 cycles | 6.75 |
| P7 cycles | 6.75 |
| P8 cycles | 6.75 |
| P9 cycles | 6.75 |
| P10 cycles | 2.83 |
| P11 cycles | 2.50 |
| P12 cycles | 2.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 5.25 - 10.49 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 47.00 |
| Nb uops | 47.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 2.67 - 1.72 |
| Nb FLOP add-sub | 6.00 |
| Nb FLOP mul | 7.00 |
| Nb FLOP fma | 1.00 |
| Nb FLOP div | 3.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 3.00 |
| Stride unknown | 2.00 |
| Stride indirect | 1.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 0.00 |
| Vectorization ratio div_sqrt | 0.00 |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 24.65 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 23.44 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | 25.00 |
| Vector-efficiency ratio other | 25.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.91 |
| CQA speedup if FP arith vectorized | 1.53 |
| CQA speedup if fully vectorized | 4.98 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.27 |
| Bottlenecks | micro-operation queue, |
| Function | advec_mom_kernel(int, int, int, int, clover::Buffer2D |
| Source | context.h:69-69,advec_mom.cpp:114-139 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 3.50 |
| CQA cycles if no scalar integer | 1.83 |
| CQA cycles if FP arith vectorized | 2.28 |
| CQA cycles if fully vectorized | 0.70 |
| Front-end cycles | 3.50 |
| P0 cycles | 1.50 |
| P1 cycles | 1.50 |
| P2 cycles | 2.50 |
| P3 cycles | 2.50 |
| P4 cycles | 2.50 |
| P5 cycles | 2.50 |
| P6 cycles | 2.75 |
| P7 cycles | 2.75 |
| P8 cycles | 2.75 |
| P9 cycles | 2.75 |
| P10 cycles | 1.83 |
| P11 cycles | 1.50 |
| P12 cycles | 1.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 0 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 28.00 |
| Nb uops | 28.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 1.14 |
| Nb FLOP add-sub | 2.00 |
| Nb FLOP mul | 2.00 |
| 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 | 0.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 2.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 0.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | 0.00 |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 0.00 |
| Vector-efficiency ratio all | 23.68 |
| Vector-efficiency ratio load | 25.00 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 22.50 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 23.21 |
| Path / |
| nb instructions | 39.50 |
| nb uops | 39.50 |
| loop length | 158 |
| used w registers | 4 |
| used x registers | 14.50 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2.50 |
| used d registers | 17.50 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 0.93 |
| micro-operation queue | 4.94 cycles |
| front end | 4.94 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 3.00 | 3.00 | 3.00 | 3.00 | 4.75 | 4.75 | 4.75 | 4.75 | 2.33 | 2.00 | 2.17 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 3.00 | 3.00 | 3.00 | 3.00 | 4.75 | 4.75 | 4.75 | 4.75 | 2.33 | 2.00 | 2.17 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | 2.63-5.24 |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 4.94 |
| Dispatch | 4.94 |
| DIV/SQRT | 2.63-5.24 |
| Data deps. | 0.00 |
| Overall L1 | 5.25-7.12 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 22% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 18% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 18% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| div/sqrt | 25% |
| other | 25% |
| all | 23% |
| load | 25% |
| store | 25% |
| mul | 25% |
| add-sub | 22% |
| fma | 25% |
| div/sqrt | 25% |
| other | 23% |
| nb instructions | 51 |
| nb uops | 51 |
| loop length | 204 |
| used w registers | 4 |
| used x registers | 16 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 3 |
| used d registers | 24 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 0.86 |
| micro-operation queue | 6.38 cycles |
| front end | 6.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 3.50 | 3.50 | 3.50 | 3.50 | 6.75 | 6.75 | 6.75 | 6.75 | 2.83 | 2.50 | 2.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 3.50 | 3.50 | 3.50 | 3.50 | 6.75 | 6.75 | 6.75 | 6.75 | 2.83 | 2.50 | 2.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | 5.25-10.49 |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 6.38 |
| Dispatch | 6.75 |
| DIV/SQRT | 5.25-10.49 |
| Data deps. | 0.00 |
| Overall L1 | 6.75-10.49 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 22% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 16% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 25% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| div/sqrt | 25% |
| other | 25% |
| all | 24% |
| load | 25% |
| store | 25% |
| mul | 25% |
| add-sub | 22% |
| fma | 25% |
| div/sqrt | 25% |
| other | 25% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D30, [X23, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W2, W0, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| SUB X1, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ORR X5, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| FCMPE D30, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GE 430ecc <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR X5, XZR, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD W2, W0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| ORR X1, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ADD X10, X4, X5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X3, X4, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X5, X4, W2,SXTW | 1 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | N/A |
| LDR D31, [X26, X5,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FABS D27, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| ADD X8, X11, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| LDR D28, [X26, X3,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D29, [X26, X10,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D0, D28, S31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D1, D29, S28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FABS D25, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D0, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FABS D26, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMINNM D22, D25, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FCMPE D2, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.LS 430f58 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x1f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDR D3, [X9, X8,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FCMPE D1, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| LDR D23, [X24, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D19, [X22, W6,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FDIV D4, D27, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FCSEL D21, D16, D24, #9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| FMUL D20, D23, D18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FADD D5, D4, D24 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D6, D17, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D7, D24, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D31, D5, D25 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMUL D27, D6, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FDIV D29, D31, D19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FDIV D0, D27, D23 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FADD D1, D29, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D25, D1, D20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMINNM D26, D25, D22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D26, D7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMADD D28, D21, D2, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (25.0%) |
| FMUL D30, D30, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| STR D30, [X7, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD X0, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| CMP X0, X25 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 430ea0 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| nb instructions | 32 |
| nb uops | 32 |
| loop length | 128 |
| used w registers | 4 |
| used x registers | 13 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 11 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.00 |
| micro-operation queue | 4.00 cycles |
| front end | 4.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 3.50 | 3.50 | 3.50 | 3.50 | 2.75 | 2.75 | 2.75 | 2.75 | 1.83 | 1.50 | 1.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 3.50 | 3.50 | 3.50 | 3.50 | 2.75 | 2.75 | 2.75 | 2.75 | 1.83 | 1.50 | 1.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 4.00 |
| Dispatch | 3.50 |
| Data deps. | 0.00 |
| Overall L1 | 4.00 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 20% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 18% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 16% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 22% |
| load | 25% |
| store | 25% |
| mul | 25% |
| add-sub | 20% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 22% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D30, [X23, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W2, W0, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| SUB X1, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ORR X5, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| FCMPE D30, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GE 430ecc <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ORR X5, XZR, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| ADD W2, W0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| ORR X1, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ADD X10, X4, X5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X3, X4, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X5, X4, W2,SXTW | 1 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | N/A |
| LDR D31, [X26, X5,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FABS D27, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| ADD X8, X11, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| LDR D28, [X26, X3,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D29, [X26, X10,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D0, D28, S31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D1, D29, S28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FABS D25, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D0, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FABS D26, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMINNM D22, D25, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FCMPE D2, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.LS 430f58 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x1f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMUL D30, D30, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| STR D30, [X7, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD X0, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| CMP X0, X25 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 430ea0 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| nb instructions | 47 |
| nb uops | 47 |
| loop length | 188 |
| used w registers | 4 |
| used x registers | 16 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 3 |
| used d registers | 24 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 0.86 |
| micro-operation queue | 5.88 cycles |
| front end | 5.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 2.50 | 2.50 | 2.50 | 2.50 | 6.75 | 6.75 | 6.75 | 6.75 | 2.83 | 2.50 | 2.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 2.50 | 2.50 | 2.50 | 2.50 | 6.75 | 6.75 | 6.75 | 6.75 | 2.83 | 2.50 | 2.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | 5.25-10.49 |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 5.88 |
| Dispatch | 6.75 |
| DIV/SQRT | 5.25-10.49 |
| Data deps. | 0.00 |
| Overall L1 | 6.75-10.49 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | 0% |
| other | 0% |
| all | 23% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 18% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| div/sqrt | 25% |
| other | 25% |
| all | 24% |
| load | 25% |
| store | 25% |
| mul | 25% |
| add-sub | 23% |
| fma | 25% |
| div/sqrt | 25% |
| other | 25% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D30, [X23, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W2, W0, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| SUB X1, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ORR X5, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| FCMPE D30, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GE 430ecc <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD X10, X4, X5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X3, X4, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X5, X4, W2,SXTW | 1 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | N/A |
| LDR D31, [X26, X5,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FABS D27, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| ADD X8, X11, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| LDR D28, [X26, X3,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D29, [X26, X10,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D0, D28, S31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D1, D29, S28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FABS D25, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D0, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FABS D26, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMINNM D22, D25, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FCMPE D2, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.LS 430f58 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x1f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| LDR D3, [X9, X8,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FCMPE D1, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| LDR D23, [X24, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D19, [X22, W6,SXTW #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FDIV D4, D27, D3 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FCSEL D21, D16, D24, #9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| FMUL D20, D23, D18 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FADD D5, D4, D24 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D6, D17, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D7, D24, S4 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D31, D5, D25 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMUL D27, D6, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FDIV D29, D31, D19 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FDIV D0, D27, D23 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 7-15 | 1.75-3.50 | scal (25.0%) |
| FADD D1, D29, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D25, D1, D20 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMINNM D26, D25, D22 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D26, D7 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FMADD D28, D21, D2, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | scal (25.0%) |
| FMUL D30, D30, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| STR D30, [X7, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD X0, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| CMP X0, X25 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 430ea0 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| nb instructions | 28 |
| nb uops | 28 |
| loop length | 112 |
| used w registers | 4 |
| used x registers | 13 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 11 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 0 |
| ADD-SUB / MUL ratio | 1.00 |
| micro-operation queue | 3.50 cycles |
| front end | 3.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.50 | 1.50 | 2.50 | 2.50 | 2.50 | 2.50 | 2.75 | 2.75 | 2.75 | 2.75 | 1.83 | 1.50 | 1.67 | 0.00 | 0.00 |
| cycles | 1.50 | 1.50 | 2.50 | 2.50 | 2.50 | 2.50 | 2.75 | 2.75 | 2.75 | 2.75 | 1.83 | 1.50 | 1.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 0.00 |
| Front-end | 3.50 |
| Dispatch | 2.75 |
| Data deps. | 0.00 |
| Overall L1 | 3.50 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 0% |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 0% |
| all | 22% |
| load | 25% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 20% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 25% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | 25% |
| add-sub | 25% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 23% |
| load | 25% |
| store | 25% |
| mul | 25% |
| add-sub | 22% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 23% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR D30, [X23, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| SUB W2, W0, #2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| SUB X1, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| ORR X5, XZR, X0 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ORR W6, WZR, W2 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (12.5%) |
| FCMPE D30, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.GE 430ecc <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x16c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| ADD X10, X4, X5 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X3, X4, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| ADD X5, X4, W2,SXTW | 1 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 0.50 | N/A |
| LDR D31, [X26, X5,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FABS D27, D30 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| ADD X8, X11, X1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | scal (25.0%) |
| LDR D28, [X26, X3,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| LDR D29, [X26, X10,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | scal (25.0%) |
| FSUB D0, D28, S31 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FSUB D1, D29, S28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FABS D25, D0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMUL D2, D0, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| FABS D26, D1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FMINNM D22, D25, D26 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 2 | 0.25 | scal (25.0%) |
| FCMPE D2, #0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 | scal (25.0%) |
| B.LS 430f58 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x1f8> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| FMUL D30, D30, D28 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 3 | 0.25 | scal (25.0%) |
| STR D30, [X7, X0,LSL #3] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 | scal (25.0%) |
| ADD X0, X0, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.25 | N/A |
| CMP X0, X25 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 430ea0 <_Z16advec_mom_kerneliiiiRN6clover8Buffer2DIdEES2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_S2_RNS_8Buffer1DIdEES5_iii._omp_fn.6+0x140> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Run 1x1 | Number processes: 1Number nodes: NARun Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_NUM_THREADS: 1OMP_PLACES: threads |
|---|---|
| Run 1x2 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x4 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x8 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x16 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x24 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x32 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 32OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x40 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 40OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x48 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 48OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x56 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 56OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| Run 1x64 | Number processes: 1Run Command: <executable>MPI Command: mpirun -n <number_processes> --bind-to core --map-by package:PE=64 --rank-by fill --report-bindings Dataset: Run Directory: /home/eoseret/qaas/qaas_runs/178-219-7589/intel/CloverLeaf2.0-CXX/run/oneview_runs/multicore/gcc_4/oneview_run_1782227431OMP_NUM_THREADS: 64OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads |
| (1x1) Efficiency | (1x1) Potential Speed-Up (%) | (1x2) Efficiency | (1x2) Potential Speed-Up (%) | (1x4) Efficiency | (1x4) Potential Speed-Up (%) | (1x8) Efficiency | (1x8) Potential Speed-Up (%) | (1x16) Efficiency | (1x16) Potential Speed-Up (%) | (1x24) Efficiency | (1x24) Potential Speed-Up (%) | (1x32) Efficiency | (1x32) Potential Speed-Up (%) | (1x40) Efficiency | (1x40) Potential Speed-Up (%) | (1x48) Efficiency | (1x48) Potential Speed-Up (%) | (1x56) Efficiency | (1x56) Potential Speed-Up (%) | (1x64) Efficiency | (1x64) Potential Speed-Up (%) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 1 | 0.02 | 0.99 | 0.07 | 0.98 | 0.1 | 0.87 | 0.39 | 0.61 | 1.13 | 0.5 | 1.44 | 0.42 | 1.66 | 0.36 | 1.83 | 0.31 | 1.97 | 0.27 | 2.07 |
| Run | Number of threads | Efficiency (ideal is 1) | Speedup | Ideal Speedup | Time (s) | Coverage (%) |
|---|---|---|---|---|---|---|
| 1x1 | 1 | 1 | 1 | 1 | 66.675003051758 | 4.485942363739 |
| 1x2 | 2 | 1 | 1.99 | 2 | 33.48999786377 | 4.463996887207 |
| 1x4 | 4 | 0.99 | 3.94 | 4 | 16.829999923706 | 4.4127478599548 |
| 1x8 | 8 | 0.98 | 7.8 | 8 | 8.5349998474121 | 3.9376375675201 |
| 1x16 | 16 | 0.87 | 13.85 | 16 | 4.7549996376038 | 2.8624620437622 |
| 1x24 | 24 | 0.61 | 14.64 | 24 | 4.6199998855591 | 2.9035181999207 |
| 1x32 | 32 | 0.5 | 16.01 | 32 | 4.1349997520447 | 2.8841962814331 |
| 1x40 | 40 | 0.42 | 16.92 | 40 | 3.9550001621246 | 2.8776965141296 |
| 1x48 | 48 | 0.36 | 17.28 | 48 | 3.7950000762939 | 2.8661744594574 |
| 1x56 | 56 | 0.31 | 17.36 | 56 | 3.82000041008 | 2.8587641716003 |
| 1x64 | 64 | 0.27 | 17.41 | 64 | 3.8250000476837 | 2.8465325832367 |
