Task 3: Instruction Parallelism Max-Reduction

A possible solution can be found at:

Please tell me about any errors or problems you may encounter.

Scaffold Head: #include <random> // prng support #include <cstdint> // uint32_t #include <iostream> // std::cout #include <immintrin.h> // AVX intrinsics // timers distributed with this book #include "include/hpc_helpers.hpp" // memory aligned arrays can be used as usual void init(float * x, uint64_t length) { std::mt19937 engine(42); std::uniform_real_distribution<float> dist(-1.0, +1.0); for (uint64_t i = 0; i < length; i++) x[i] = dist(engine); } float plain_max(float * x, uint64_t length) { float result = -INFINITY; for (uint64_t i = 0; i < length; i++) result = x[i] > result ? x[i] : result; return result; } void check(float x, float true_result) { if (x != true_result){ std::cout << "Error: wrong result" << std::endl; std::cout << "Your result is: " << x << " but should have been: " << true_result << std::endl; } }

Tests