options

Functions and Loops

Columns Filter

Max Thread Time / Walltime run_0 (%) Coverage run_0 (%) Coverage Excluding Loops run_0 (%) Max Inclusive Time Over Threads run_0 (s) Max Exclusive Time Over Threads run_0 (s) Inclusive Time w.r.t. Wall Time run_0 (s) Exclusive Time w.r.t. Wall Time run_0 (s) Nb Threads run_0 Deviation (coverage) run_0 Deviation (walltime) run_0 Categories run_0 Compilation Options Max Thread Time / Walltime Coverage Coverage Excluding Loops Max Inclusive Time Over Threads Max Exclusive Time Over Threads Inclusive Time w.r.t. Wall Time Exclusive Time w.r.t. Wall Time Nb Threads Deviation (coverage) Deviation (walltime) Categories Compilation Options
NameModuleMax Thread Time / Walltime run_0 (%)Coverage run_0 (%)Coverage Excluding Loops run_0 (%)Max Inclusive Time Over Threads run_0 (s)Max Exclusive Time Over Threads run_0 (s)Inclusive Time w.r.t. Wall Time run_0 (s)Exclusive Time w.r.t. Wall Time run_0 (s)Nb Threads run_0Deviation (coverage) run_0Deviation (walltime) run_0Categories run_0Compilation Options
ggml_vec_dot_q8_0_q8_0+libggml-cpu.so87.3184.950.1794.920.2991.060.18523.213.52libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 2498 - quants.c:1066-1073 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 2499 - quants.c:101-1042 - libggml-cpu.so [...]87.1784.7884.7894.7894.7890.8890.88523.233.54
bool _INTERNAL021345c1::__kmp_wait_template<kmp_flag_64<false, true>, true, false, true>(kmp_info*, kmp_flag_64<false, true>*, void*)libiomp5.so26.7011.3411.3429.0329.0312.1512.15514.304.57OMP (%): 100.00
_INTERNAL021345c1::__kmp_hyper_barrier_gather(barrier_type, kmp_info*, int, int, void (*)(void*, void*), void*)libiomp5.so7.671.231.238.348.341.311.31522.142.29OMP (%): 100.00
ggml_compute_forward_flash_attn_ext+libggml-cpu.so1.030.510.001.120.020.540.00430.370.40libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 1754 - ops.cpp:8759-8927 - libggml-cpu.so [...]+0.010.500.001.230.020.540.00130.000.00
Loop 1755 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1761 - vec.h:375-751 - libggml-cpu.so [...]+0.180.490.081.120.190.520.08330.030.04
Loop 1764 - vec.h:386-387 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1767 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1769 - vec.h:502-503 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1771 - vec.h:740-745 - libggml-cpu.so0.000.000.000.010.010.000.0040.000.00
Loop 1762 - vec.h:386-387 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1768 - vec.h:491-497 - libggml-cpu.so0.850.410.410.920.920.440.44370.250.26
Loop 1765 - vec.h:375-381 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1766 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1770 - vec.h:750-751 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1763 - vec.h:375-381 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1759 - ops.cpp:8885-8886 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1760 - ops.cpp:8885-8886 - libggml-cpu.so [...]0.050.010.010.050.050.010.01310.010.01
Loop 1756 - vec.h:677-682 - libggml-cpu.so0.040.000.000.040.040.000.00100.010.01
Loop 1758 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1757 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
ggml_vec_dot_f16+libggml-cpu.so0.830.400.090.900.230.430.10340.180.19libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 766 - vec.cpp:324-325 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 765 - vec.cpp:324-325 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 767 - vec.cpp:311-316 - libggml-cpu.so0.730.310.310.790.790.330.33340.140.15
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()libiomp5.so0.580.350.350.630.630.380.38520.090.10OMP (%): 100.00
ggml_compute_forward_mul_mat+libggml-cpu.so0.390.240.030.420.080.260.03520.070.08libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 61 - ggml-cpu.c:1125-1395 - libggml-cpu.so [...]+0.160.190.080.430.170.210.09520.040.04
Loop 62 - ggml-cpu.c:1162-1198 - libggml-cpu.so [...]+0.020.110.000.260.020.120.00310.000.00
Loop 63 - ggml-cpu.c:1163-1198 - libggml-cpu.so [...]+0.010.110.000.240.010.120.00250.000.00
Loop 64 - ggml-cpu.c:1164-1198 - libggml-cpu.so [...]+0.090.110.050.220.100.110.05520.020.02
Loop 67 - ggml-cpu.c:1193-1194 - libggml-cpu.so0.090.050.050.100.100.060.06520.020.02
Loop 65 - ggml-cpu.c:1197-1198 - libggml-cpu.so0.020.010.010.030.030.010.01420.000.00
Loop 66 - ggml-cpu.c:1197-1198 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 69 - ggml-cpu.c:1316-1328 - libggml-cpu.so+0.000.000.000.020.000.000.0020.000.00
Loop 68 - ggml-cpu.c:1317-1328 - libggml-cpu.so0.010.000.000.010.010.000.00230.000.00
Loop 70 - ggml-cpu.c:1289-1295 - libggml-cpu.so+0.000.010.000.030.010.010.0040.000.00
Loop 71 - ggml-cpu.c:1290-1295 - libggml-cpu.so+0.010.010.000.030.010.010.0060.000.00
Loop 72 - ggml-cpu.c:1291-1295 - libggml-cpu.so0.020.000.000.020.020.000.00330.000.00
Loop 73 - ggml-cpu.c:1291-1295 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 75 - ggml-cpu.c:1248-1260 - libggml-cpu.so+0.000.010.000.030.000.010.0010.000.00
Loop 74 - ggml-cpu.c:1249-1260 - libggml-cpu.so0.030.010.010.030.030.010.01440.000.01
_INTERNAL021345c1::__kmp_hyper_barrier_release(barrier_type, kmp_info*, int, int, int, void*)libiomp5.so1.530.160.161.661.660.170.17520.290.31OMP (%): 100.00
__sched_yieldlibc.so.60.310.100.100.330.330.110.11520.050.06System (%): 100.00
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)+libggml-cpu.so0.160.100.000.170.000.110.00520.040.04libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 2293 - sgemm.cpp:814-853 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 2295 - sgemm.cpp:138-1044 - libggml-cpu.so [...]+0.000.100.000.180.000.110.0030.000.00
Loop 2294 - sgemm.cpp:138-1044 - libggml-cpu.so [...]0.160.100.100.170.170.110.11520.040.04
quantize_row_q8_0+libggml-cpu.so0.160.080.000.170.010.090.00520.030.03libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 2489 - quants.c:298-355 - libggml-cpu.so [...]0.150.080.080.160.160.080.08520.030.03
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long)+libggml-cpu.so0.110.070.000.120.000.070.00520.020.02libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 2305 - sgemm.cpp:814-853 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 2307 - sgemm.cpp:138-1044 - libggml-cpu.so [...]+0.000.070.000.120.000.070.0000.000.00
Loop 2306 - sgemm.cpp:138-1044 - libggml-cpu.so [...]0.110.070.070.120.120.070.07520.020.02
__libm_expf_l9llama-cli0.170.070.070.180.180.070.07330.030.03Math (%): 100.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()libiomp5.so0.460.050.050.500.500.060.06410.100.11OMP (%): 100.00
__libm_sincosf_e7llama-cli0.100.040.040.110.110.040.04520.020.02Exe (%): 100.00
ggml_compute_forward_rope_f32(ggml_compute_params const*, ggml_tensor*, bool)+libggml-cpu.so0.100.040.000.110.020.040.00510.020.02libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 1409 - ops.cpp:6210-6484 - libggml-cpu.so [...]+0.000.030.000.140.000.030.0020.000.00
Loop 1410 - ops.cpp:6210-6484 - libggml-cpu.so [...]+0.020.030.000.140.020.030.00240.000.00
Loop 1437 - ops.cpp:6220-6245 - libggml-cpu.so [...]0.040.010.010.040.040.020.02480.010.01
Loop 1426 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1418 - ops.cpp:6220-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1431 - ops.cpp:6220-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1434 - ops.cpp:6210-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1427 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1428 - ops.cpp:6220-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1422 - ops.cpp:6220-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1421 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1438 - ops.cpp:6210-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1435 - ops.cpp:6210-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1424 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1423 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1439 - ops.cpp:6210-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1425 - ops.cpp:6220-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1411 - ops.cpp:6365-6484 - libggml-cpu.so [...]+0.030.010.010.070.040.010.01310.010.01
Loop 1416 - ops.cpp:6413-6426 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1412 - ops.cpp:6462-6475 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1414 - ops.cpp:6479-6484 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1417 - ops.cpp:6429-6442 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1415 - ops.cpp:6446-6457 - libggml-cpu.so0.040.010.010.040.040.010.01250.010.01
Loop 1413 - ops.cpp:6479-6484 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1432 - ops.cpp:6220-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1436 - ops.cpp:6220-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1429 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1420 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1433 - ops.cpp:6210-6245 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1419 - ops.cpp:6220-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1430 - ops.cpp:6210-6303 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
ggml_graph_compute_thread+libggml-cpu.so0.060.030.010.060.030.040.01520.010.02libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 84 - ggml-cpu.c:2087-2088 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 82 - ggml-cpu.c:533-2891 - libggml-cpu.so [...]0.060.030.030.060.060.030.03520.010.02
Loop 83 - ggml-cpu.c:2087-2088 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
__kmp_barrierlibiomp5.so0.070.030.030.080.080.040.04520.010.02OMP (%): 100.00
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<3>(long, long, long, long)+libggml-cpu.so0.080.020.000.090.000.020.00520.020.02libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 2298 - sgemm.cpp:138-1044 - libggml-cpu.so [...]+0.000.020.000.090.000.020.0010.000.00
Loop 2297 - sgemm.cpp:138-1044 - libggml-cpu.so [...]0.080.020.020.090.090.020.02520.020.02
Loop 2296 - sgemm.cpp:814-853 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
__intel_avx_rep_memcpy+llama-cli0.090.020.020.100.100.020.02470.020.02Memory (%): 100.00
Loop 3159 - - llama-cli0.000.000.000.000.000.000.0000.000.00
Loop 3160 - - llama-cli0.000.000.000.010.010.000.0040.000.00
_intel_fast_memcpyllama-cli0.050.010.010.050.050.020.02440.010.01Memory (%): 100.00
ggml_compute_forward_rms_norm+libggml-cpu.so0.510.010.000.560.010.010.00170.120.13libggml-cpu.so (%): 100.00clang based Intel(R) oneAPI DPC++/C++ Compiler 2024.0.0 (2024.0.0.20231017)
Loop 1175 - ops.cpp:4319-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1176 - ops.cpp:4320-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1177 - ops.cpp:4321-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1178 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1179 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1159 - ops.cpp:4319-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1160 - ops.cpp:4320-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1161 - ops.cpp:4321-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1162 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1163 - ops.cpp:4325-4326 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1164 - ops.cpp:4325-4326 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1169 - ops.cpp:4319-4338 - libggml-cpu.so [...]+0.000.010.000.550.000.010.0000.000.00
Loop 1170 - ops.cpp:4320-4338 - libggml-cpu.so [...]+0.000.010.000.550.000.010.0010.000.00
Loop 1171 - vec.h:673-682 - libggml-cpu.so [...]+0.000.010.000.550.000.010.0010.000.00
Loop 1172 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0010.000.00
Loop 1173 - ops.cpp:4325-4326 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1174 - ops.cpp:4325-4326 - libggml-cpu.so0.490.010.010.540.540.010.0120.350.37
Loop 1165 - ops.cpp:4319-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1166 - ops.cpp:4320-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1167 - vec.h:677-682 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1168 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1148 - ops.cpp:4319-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1149 - ops.cpp:4321-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1147 - ops.cpp:4320-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1145 - ops.cpp:4320-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1146 - ops.cpp:4321-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1180 - ops.cpp:4319-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1181 - ops.cpp:4320-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1182 - ops.cpp:4321-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1184 - vec.h:677-682 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1186 - ops.cpp:4325-4326 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1185 - ops.cpp:4325-4326 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1183 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
Loop 1153 - ops.cpp:4319-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1152 - ops.cpp:4320-4333 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1150 - ops.cpp:4320-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1151 - ops.cpp:4321-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1154 - ops.cpp:4321-4333 - libggml-cpu.so [...]0.000.000.000.000.000.000.0000.000.00
Loop 1155 - ops.cpp:4319-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1156 - ops.cpp:4320-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1157 - ops.cpp:4321-4355 - libggml-cpu.so [...]+0.000.000.000.000.000.000.0000.000.00
Loop 1158 - vec.h:687-688 - libggml-cpu.so0.000.000.000.000.000.000.0000.000.00
×