8.5.3.5 : The compilation
Let's compile :
|
$ make -- Configuring done -- Generating done -- Build files have been written to: ExampleOptimisation/build [ 2%] Built target hadamard_product_O2 [ 6%] Built target hadamard_product_O1 [ 11%] Built target hadamard_product_vectorize [ 13%] Built target hadamard_product_O0 [ 15%] Built target hadamard_product_O3 [ 18%] Built target hadamard_product_Ofast [ 20%] Built target hadamard_product_intrinsics [ 22%] Built target asterics_hpc [ 25%] Built target saxpy_O2 [ 27%] Built target saxpy_O0 [ 29%] Built target saxpy_O3 [ 34%] Built target saxpy_O1 [ 36%] Built target saxpy_Ofast [ 40%] Built target saxpy_vectorize [ 43%] Built target saxpy_intrinsics [ 45%] Built target reduction_real_O2 Scanning dependencies of target reduction_real_intrinsics_interleave8_O3 [ 47%] Building CXX object 4-Reduction/CMakeFiles/reduction_real_intrinsics_interleave8_O3.dir/reduction_intrinsics_interleave8.cpp.o [ 50%] Building CXX object 4-Reduction/CMakeFiles/reduction_real_intrinsics_interleave8_O3.dir/main_intrinsics_interleave8.cpp.o [ 50%] Linking CXX executable reduction_real_intrinsics_interleave8_O3 [ 50%] Built target reduction_real_intrinsics_interleave8_O3 [ 54%] Built target reduction_real_O1 [ 59%] Built target reduction_real_Ofast [ 61%] Built target reduction_O0 [ 65%] Built target reduction_O1 [ 68%] Built target reduction_O2 [ 70%] Built target reduction_O3 [ 72%] Built target reduction_real_intrinsics_interleave4_O3 [ 77%] Built target reduction_real_vectorize_Ofast [ 81%] Built target reduction_real_intrinsics_interleave2_O3 [ 86%] Built target reduction_real_intrinsics_O3 [ 90%] Built target reduction_real_O3 [ 95%] Built target reduction_real_O0 [100%] Built target reduction_real_vectorize_O3 |
Let's get the performances :
|
$ make plot_all [ 1%] Built target asterics_hpc [ 3%] Built target reduction_real_vectorize_O3 [ 6%] Built target reduction_real_Ofast [ 8%] Built target reduction_real_vectorize_Ofast [ 10%] Built target reduction_real_intrinsics_O3 [ 13%] Built target reduction_real_O3 [ 18%] Built target plot_reductionIntrinsics [ 19%] Built target hadamard_product_intrinsics [ 21%] Built target hadamard_product_vectorize [ 22%] Built target hadamard_product_O3 [ 26%] Built target plot_hadamardIntrinsics [ 27%] Built target hadamard_product_Ofast [ 28%] Built target hadamard_product_O2 [ 31%] Built target hadamard_product_O1 [ 32%] Built target hadamard_product_O0 [ 36%] Built target plot_hadamardBase [ 37%] Built target plot_hadamardVectorize [ 38%] Built target saxpy_intrinsics [ 39%] Built target saxpy_O3 [ 42%] Built target saxpy_vectorize [ 44%] Built target plot_saxpyIntrinsics [ 46%] Built target plot_saxpyVectorize [ 48%] Built target saxpy_Ofast [ 49%] Built target saxpy_O2 [ 50%] Built target saxpy_O0 [ 53%] Built target saxpy_O1 [ 57%] Built target plot_saxpyBase [ 60%] Built target reduction_real_intrinsics_interleave8_O3 [ 61%] Built target reduction_real_intrinsics_interleave4_O3 [ 63%] Built target reduction_real_intrinsics_interleave2_O3 Scanning dependencies of target plot_reductionIntrinsicsInterleave8 [ 65%] Run reduction_real_intrinsics_interleave8_O3 program Reduction intrinsics interleave 8 evaluateReduction : nbElement = 1024, cyclePerElement = 0.0957031 cy/el, elapsedTime = 98 cy evaluateReduction : nbElement = 2048, cyclePerElement = 0.0756836 cy/el, elapsedTime = 155 cy evaluateReduction : nbElement = 3072, cyclePerElement = 0.0696615 cy/el, elapsedTime = 214 cy evaluateReduction : nbElement = 4992, cyclePerElement = 0.0655048 cy/el, elapsedTime = 327 cy evaluateReduction : nbElement = 10048, cyclePerElement = 0.117436 cy/el, elapsedTime = 1180 cy [ 65%] Call gnuplot reductionIntrinsicsInterleave8 [ 68%] Built target plot_reductionIntrinsicsInterleave8 [ 72%] Built target plot_reductionVectorize [ 73%] Built target reduction_O3 [ 74%] Built target reduction_O0 [ 77%] Built target reduction_O1 [ 78%] Built target reduction_O2 [ 81%] Built target plot_reductionBase [ 84%] Built target reduction_real_O0 [ 85%] Built target reduction_real_O2 [ 87%] Built target reduction_real_O1 [ 91%] Built target plot_reductionReal [ 95%] Built target plot_reductionIntrinsicsInterleave2 [100%] Built target plot_reductionIntrinsicsInterleave4 [100%] Built target plot_all |