| Loop Id: 16 | Module: exec | Source: cg.cpp:86-90 | Coverage: 32.81% |
|---|
| Loop Id: 16 | Module: exec | Source: cg.cpp:86-90 | Coverage: 32.81% |
|---|
0x4112b8 ADD X25, X20, X3 |
0x4112bc LDR D5, [X6, X3] [2] |
0x4112c0 LDR D6, [X4, X3] [8] |
0x4112c4 LDP D3, D2, [X25, #1016] [7] |
0x4112c8 ADD X25, X21, X3 |
0x4112cc LDUR D7, [X25, #504] [6] |
0x4112d0 FADD D16, D5, D6 |
0x4112d4 LDR D17, [X5, X3] [1] |
0x4112d8 SUBS X24, X24, #1 |
0x4112dc FADD D4, D2, D3 |
0x4112e0 FMUL D3, D3, D7 |
0x4112e4 LDR D7, [X25, #8] [6] |
0x4112e8 FADD D4, D4, D1 |
0x4112ec FMADD D2, D2, D7, D3 |
0x4112f0 FMUL D3, D6, D17 |
0x4112f4 LDR D6, [X25] [6] |
0x4112f8 LDR D7, [X7, X3] [3] |
0x4112fc FADD D4, D4, D16 |
0x411300 FMADD D3, D5, D7, D3 |
0x411304 FNMSUB D2, D4, D6, D2 |
0x411308 FSUB D2, D2, S3 |
0x41130c STR D2, [X23, X3] [5] |
0x411310 ADD X3, X3, #8 |
0x411314 LDR D3, [X25] [6] |
0x411318 FMADD D0, D2, D3, D0 |
0x41131c STR D0, [SP, #16] [4] |
0x411320 B.NE 4112b8 |
/home/eoseret/qaas/qaas_runs/178-237-4322/intel/TeaLeaf/build/TeaLeaf/src/omp/cg.cpp: 86 - 90 |
-------------------------------------------------------------------------------- |
86: for (int kk = halo_depth; kk < x - halo_depth; ++kk) { |
87: const int index = kk + jj * x; |
88: const double smvp = tealeaf_SMVP(p); |
89: w[index] = smvp; |
90: pw_temp += w[index] * p[index]; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►98.43+ | __kmp_invoke_microtask | libomp.so | |
| ○ | __kmp_invoke_task_func | libomp.so | |
| ○ | __kmp_launch_thread | libomp.so | |
| ○ | __kmp_launch_worker(void*) | libomp.so | |
| ○ | start_thread | libc.so.6 | |
| ○ | thread_start | libc.so.6 | |
| ►1.57+ | __kmp_invoke_microtask | libomp.so | |
| ○ | __kmp_invoke_task_func | libomp.so | |
| ○ | __kmp_fork_call | libomp.so | |
| ○ | __kmpc_fork_call | libomp.so | |
| ○ | run_cg_calc_w(Chunk*, Settings[...] | cg.cpp:94 | exec |
| ○ | cg_main_step_driver(Chunk*, Se[...] | cg_driver.cpp:57 | exec |
| ○ | cg_driver(Chunk*, Settings&, d[...] | cg_driver.cpp:18 | exec |
| ○ | solve(Chunk*, Settings&, int, [...] | diffuse.cpp:45 | exec |
| ○ | diffuse(Chunk*, Settings&) | diffuse.cpp:12 | exec |
| ○ | main | main.cpp:169 | exec |
| ○ | __libc_start_call_main | libc.so.6 | |
| ○ | __libc_start_main | libc.so.6 | |
| ○ | _start | exec |
| 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 | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 3.67 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.09 |
| Bottlenecks | P10, P11, P12, |
| Function | cg_calc_w(int, int, int, double*, double const*, double*, double const*, double const*) [clone .omp_outlined] |
| Source | cg.cpp:86-90 |
| 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 | 3.67 |
| CQA cycles if no scalar integer | 3.67 |
| CQA cycles if FP arith vectorized | 3.67 |
| CQA cycles if fully vectorized | 1.00 |
| Front-end cycles | 3.38 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 1.00 |
| P3 cycles | 1.00 |
| P4 cycles | 1.00 |
| P5 cycles | 1.00 |
| P6 cycles | 3.25 |
| P7 cycles | 3.25 |
| P8 cycles | 3.25 |
| P9 cycles | 3.25 |
| P10 cycles | 3.67 |
| P11 cycles | 3.67 |
| P12 cycles | 3.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 27.00 |
| Nb uops | 27.00 |
| Nb loads | NA |
| Nb stores | 2.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 4.09 |
| Nb FLOP add-sub | 5.00 |
| Nb FLOP mul | 2.00 |
| Nb FLOP fma | 4.00 |
| 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 | 1.00 |
| Stride 1 | 0.00 |
| Stride n | 5.00 |
| Stride unknown | 2.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 4.35 |
| Vectorization ratio load | 11.11 |
| 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 | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 26.09 |
| Vector-efficiency ratio load | 27.78 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | 25.00 |
| 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 | 3.67 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.09 |
| Bottlenecks | P10, P11, P12, |
| Function | cg_calc_w(int, int, int, double*, double const*, double*, double const*, double const*) [clone .omp_outlined] |
| Source | cg.cpp:86-90 |
| 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 | 3.67 |
| CQA cycles if no scalar integer | 3.67 |
| CQA cycles if FP arith vectorized | 3.67 |
| CQA cycles if fully vectorized | 1.00 |
| Front-end cycles | 3.38 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 1.00 |
| P3 cycles | 1.00 |
| P4 cycles | 1.00 |
| P5 cycles | 1.00 |
| P6 cycles | 3.25 |
| P7 cycles | 3.25 |
| P8 cycles | 3.25 |
| P9 cycles | 3.25 |
| P10 cycles | 3.67 |
| P11 cycles | 3.67 |
| P12 cycles | 3.67 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 27.00 |
| Nb uops | 27.00 |
| Nb loads | NA |
| Nb stores | 2.00 |
| Nb stack references | 1.00 |
| FLOP/cycle | 4.09 |
| Nb FLOP add-sub | 5.00 |
| Nb FLOP mul | 2.00 |
| Nb FLOP fma | 4.00 |
| 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 | 1.00 |
| Stride 1 | 0.00 |
| Stride n | 5.00 |
| Stride unknown | 2.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 4.35 |
| Vectorization ratio load | 11.11 |
| 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 | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 26.09 |
| Vector-efficiency ratio load | 27.78 |
| Vector-efficiency ratio store | 25.00 |
| Vector-efficiency ratio mul | 25.00 |
| Vector-efficiency ratio add_sub | 25.00 |
| Vector-efficiency ratio fma | 25.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | cg_calc_w(int, int, int, double*, double const*, double*, double const*, double const*) [clone .omp_outlined] |
| Source file and lines | cg.cpp:86-90 |
| Module | exec |
| nb instructions | 27 |
| nb uops | 27 |
| loop length | 108 |
| used w registers | 0 |
| used x registers | 10 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 10 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 2.50 |
| micro-operation queue | 3.38 cycles |
| front end | 3.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 1.00 | 1.00 | 1.00 | 1.00 | 3.25 | 3.25 | 3.25 | 3.25 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 1.00 | 1.00 | 1.00 | 1.00 | 3.25 | 3.25 | 3.25 | 3.25 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 3.38 |
| Dispatch | 3.67 |
| Data deps. | 2.00 |
| Overall L1 | 3.67 |
| all | 8% |
| load | 11% |
| 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 | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 4% |
| load | 11% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 27% |
| load | 27% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| 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 | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 26% |
| load | 27% |
| store | 25% |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| 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 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X25, X20, X3 | 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 D5, [X6, X3] | 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 D6, [X4, X3] | 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%) |
| LDP D3, D2, [X25, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (50.0%) |
| ADD X25, X21, X3 | 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 |
| LDUR D7, [X25, #504] | 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%) |
| FADD D16, D5, D6 | 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%) |
| LDR D17, [X5, X3] | 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%) |
| SUBS X24, X24, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| FADD D4, D2, D3 | 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 D3, D3, 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%) |
| LDR D7, [X25, #8] | 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%) |
| FADD D4, D4, 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%) |
| FMADD D2, D2, D7, D3 | 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 D3, D6, D17 | 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%) |
| LDR D6, [X25] | 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 D7, [X7, X3] | 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%) |
| FADD D4, D4, D16 | 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%) |
| FMADD D3, D5, D7, D3 | 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%) |
| FNMSUB D2, D4, D6, D2 | 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%) |
| FSUB D2, D2, S3 | 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%) |
| STR D2, [X23, X3] | 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 X3, X3, #8 | 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 D3, [X25] | 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%) |
| FMADD D0, D2, D3, D0 | 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%) |
| STR D0, [SP, #16] | 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%) |
| B.NE 4112b8 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x144> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | cg_calc_w(int, int, int, double*, double const*, double*, double const*, double const*) [clone .omp_outlined] |
| Source file and lines | cg.cpp:86-90 |
| Module | exec |
| nb instructions | 27 |
| nb uops | 27 |
| loop length | 108 |
| used w registers | 0 |
| used x registers | 10 |
| used b registers | 0 |
| used h registers | 0 |
| used s registers | 2 |
| used d registers | 10 |
| used q registers | 0 |
| used v registers | 0 |
| used z registers | 0 |
| nb stack references | 1 |
| ADD-SUB / MUL ratio | 2.50 |
| micro-operation queue | 3.38 cycles |
| front end | 3.38 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 1.00 | 1.00 | 1.00 | 1.00 | 3.25 | 3.25 | 3.25 | 3.25 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 1.00 | 1.00 | 1.00 | 1.00 | 3.25 | 3.25 | 3.25 | 3.25 | 3.67 | 3.67 | 3.67 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 3.38 |
| Dispatch | 3.67 |
| Data deps. | 2.00 |
| Overall L1 | 3.67 |
| all | 8% |
| load | 11% |
| 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 | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 4% |
| load | 11% |
| store | 0% |
| mul | 0% |
| add-sub | 0% |
| fma | 0% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 27% |
| load | 27% |
| store | 25% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 25% |
| 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 | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 26% |
| load | 27% |
| store | 25% |
| mul | 25% |
| add-sub | 25% |
| fma | 25% |
| 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 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ADD X25, X20, X3 | 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 D5, [X6, X3] | 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 D6, [X4, X3] | 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%) |
| LDP D3, D2, [X25, #1016] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (50.0%) |
| ADD X25, X21, X3 | 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 |
| LDUR D7, [X25, #504] | 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%) |
| FADD D16, D5, D6 | 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%) |
| LDR D17, [X5, X3] | 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%) |
| SUBS X24, X24, #1 | 1 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | scal (25.0%) |
| FADD D4, D2, D3 | 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 D3, D3, 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%) |
| LDR D7, [X25, #8] | 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%) |
| FADD D4, D4, 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%) |
| FMADD D2, D2, D7, D3 | 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 D3, D6, D17 | 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%) |
| LDR D6, [X25] | 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 D7, [X7, X3] | 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%) |
| FADD D4, D4, D16 | 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%) |
| FMADD D3, D5, D7, D3 | 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%) |
| FNMSUB D2, D4, D6, D2 | 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%) |
| FSUB D2, D2, S3 | 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%) |
| STR D2, [X23, X3] | 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 X3, X3, #8 | 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 D3, [X25] | 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%) |
| FMADD D0, D2, D3, D0 | 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%) |
| STR D0, [SP, #16] | 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%) |
| B.NE 4112b8 <_Z9cg_calc_wiiiPdPKdS_S1_S1_.omp_outlined+0x144> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
