options

OpenMP Regions

requested parallelismwalltime sum (s)nb instancesany sync average per thread time (s)any wait average per thread time (s)parallelism overhead (%)local speedup if perfectly balancedglobal speedup if perfectly balanced
start addrfunction namesource locationlevelancestor thread numinvokerparallel or teams1x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x1921x61x721x961x1201x1281x1441x1681x192
libggml-cpu.so:0x30185ggml_graph_computeggml-cpu.c:314800runtimeparallel6729612012814416819257.32013.47813.29512.87212.57412.98416.97417.89451351351351351351351351312.3218.1908.5928.4588.3288.96512.29513.06612.2218.1278.5308.3938.2618.90012.22712.99421.560.864.665.766.269.072.473.01.2742.5492.8272.9162.9613.2313.6283.7061.2682.3292.5362.5892.6132.8123.1783.266
libggml-cpu.so:0x57d9fggml_backend_amx_convert_weight(ggml_tensor*, void const*, u...mmq.cpp:233700runtimeparallel672961201281441681920.3750.1320.1380.1430.1430.1470.1530.17022522522522522522522522542.5 E-341.6 E-346.4 E-356.4 E-340.8 E-351.3 E-360.8 E-367.8 E-342.4 E-341.6 E-346.4 E-356.4 E-340.7 E-351.3 E-360.8 E-367.8 E-311.331.633.739.528.534.939.839.91.1281.4621.5081.6531.3991.5361.6621.6631.0011.0031.0031.0041.0031.0041.0031.004
×