options

Functions and Loops

47 loops and 84 functions have been discarded from the report because their coverage is lower than the threshold set by object_coverage_threshold (0.01%). It represents about 0.99% of the application. To include them, change the value of object_coverage_threshold in the experiment directory configuration file, then rerun the command with the additionnal parameter --force-static-analysis.
Inclusive metrics are only related to the given object code and do not include other external objects / libraries.

Columns Filter

Coverage gcc_0 (%) Coverage Excluding Loops gcc_0 (%) Max Inclusive Time Over Threads gcc_0 (s) Max Exclusive Time Over Threads gcc_0 (s) Inclusive Time w.r.t. Wall Time gcc_0 (s) Exclusive Time w.r.t. Wall Time gcc_0 (s) Nb Threads gcc_0 Deviation (coverage) gcc_0 Deviation (walltime) gcc_0 Categories gcc_0 Compilation Options
NameModuleCoverage gcc_0 (%)Coverage Excluding Loops gcc_0 (%)Max Inclusive Time Over Threads gcc_0 (s)Max Exclusive Time Over Threads gcc_0 (s)Inclusive Time w.r.t. Wall Time gcc_0 (s)Exclusive Time w.r.t. Wall Time gcc_0 (s)Nb Threads gcc_0Deviation (coverage) gcc_0Deviation (walltime) gcc_0Categories gcc_0Compilation Options
gomp_team_barrier_wait_endlibgomp.so.1.0.081.8081.8021.5021.5020.9620.96726.544.79OMP (%): 100.00
ggml_vec_dot_q8_0_q8_0+libggml-cpu.so10.650.023.490.022.730.01722.520.60/scratch/users/amazouz/QAAS/service/Llama.cpp/ortce-gh/175-931-3387/llama.cpp/build/llama.cpp/../gcc/bin/libggml-blas.so (%): 100.00GNU C11 14.2.0 -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+sve2-sm4+norng+dotprod+i8mm+sve+nosme -mlittle-endian -mabi=lp64 -g -O3 -O3 -std=gnu11 -fno-omit-frame-pointer -fcf-protection=none -fPIC -fopenmp
Loop 2043 - quants.c:1010-1026 - libggml-cpu.so [...]0.000.000.000.000.000.0000.000.00
Loop 2039 - quants.c:908-1128 - libggml-cpu.so [...]+10.630.033.520.012.720.01330.030.00
Loop 2041 - quants.c:979-1000 - libggml-cpu.so [...]10.6010.603.493.492.722.72722.520.60
Loop 2042 - quants.c:910-929 - libggml-cpu.so [...]0.000.000.010.010.000.0010.000.00
Loop 2040 - quants.c:1117-1124 - libggml-cpu.so [...]0.000.000.000.000.000.0000.000.00
Loop 2044 - quants.c:1046-1075 - libggml-cpu.so [...]0.000.000.000.000.000.0000.000.00
syscalllibc.so.66.466.464.284.281.661.66724.180.69System (%): 100.00
__aarch64_ldadd4_acq_rellibgomp.so.1.0.00.180.180.310.310.050.05560.290.04OMP (%): 100.00
ggml_vec_swiglu_f32+libggml-cpu.so0.050.000.390.000.010.0040.760.19/scratch/users/amazouz/QAAS/service/Llama.cpp/ortce-gh/175-931-3387/llama.cpp/build/llama.cpp/../gcc/bin/libggml-blas.so (%): 100.00GNU C++17 14.2.0 -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+sve2-sm4+norng+dotprod+i8mm+sve+nosme -mlittle-endian -mabi=lp64 -g -O3 -O3 -std=gnu++17 -fno-omit-frame-pointer -fcf-protection=none -fPIC -fopenmp
Loop 756 - vec.cpp:385-387 - libggml-cpu.so [...]0.050.050.390.390.010.0140.760.19
llama_token_data_array_partial_sort_inplace(llama_token_data_array*, int)+libllama.so0.050.000.400.000.010.0010.000.00/scratch/users/amazouz/QAAS/service/Llama.cpp/ortce-gh/175-931-3387/llama.cpp/build/llama.cpp/../gcc/bin/libllama.so (%): 100.00GNU C++17 14.2.0 -mlittle-endian -mabi=lp64 -g -O3 -O3 -fno-omit-frame-pointer -fcf-protection=none -fPIC GNU C17 14.2.0 -mlittle-endian -mabi=lp64 -g -g -g -O2 -O2 -O2 -fbuilding-libgcc -fno-stack-protector -fPIC
Loop 3482 - stl_heap.h:262-422 - libllama.so [...]+0.050.000.400.000.010.0000.000.00
Loop 3483 - stl_algo.h:1594-1595 - libllama.so [...]0.050.050.400.400.010.0110.000.00
Loop 3484 - stl_heap.h:262-422 - libllama.so [...]0.000.000.000.000.000.0000.000.00
Loop 3485 - stl_heap.h:355-360 - libllama.so0.000.000.000.000.000.0000.000.00
common_sampler_sample(common_sampler*, llama_context*, int, bool)+exec0.030.000.260.000.010.0010.000.00Exe (%): 100.00GNU C++17 14.2.0 -mlittle-endian -mabi=lp64 -g -O3 -O3 -fno-omit-frame-pointer -fcf-protection=none -fPIC GNU C17 14.2.0 -mlittle-endian -mabi=lp64 -g -g -g -O2 -O2 -O2 -fbuilding-libgcc -fno-stack-protector -fPIC
Loop 3889 - sampling.cpp:116-382 - exec [...]+0.030.000.260.000.010.0000.000.00
Loop 3890 - stl_vector.h:993-1949 - exec [...]+0.030.000.260.000.010.0010.000.00
Loop 3894 - sampling.cpp:125-126 - exec [...]0.030.030.250.250.010.0110.000.00
Loop 3893 - sampling.cpp:125-126 - exec0.000.000.000.000.000.0000.000.00
Loop 3891 - sampling.cpp:125-126 - exec0.000.000.000.000.000.0000.000.00
Loop 3892 - sampling.cpp:125-126 - exec [...]0.000.000.000.000.000.0000.000.00
×