% 1. Setup Data OUTSIDE the timer
d = gpuDevice;
N = 10000;

fprintf('Preparing data...\n');
A_cpu_double = rand(N, N);          % Create double on CPU
A_cpu_single = single(A_cpu_double); % Create single on CPU

% Warmup run (wakes up the GPU from idle state)
A_warm = gpuArray.rand(1000, 1000, 'single');
B_warm = A_warm * A_warm;
wait(d); 

fprintf('------------------------------------------------\n');

% TEST 1: Double Precision (The "Slow" way)
% We move data to GPU first so we only measure calculation time
A_gpu_double = gpuArray(A_cpu_double); 
wait(d); % Ensure transfer is done before starting timer

fprintf('Running DOUBLE precision test... ');
tic;
B_gpu = A_gpu_double * A_gpu_double;
wait(d); % FORCE MATLAB TO WAIT FOR GPU
time_double = toc;
fprintf('Done.\n');
fprintf('Double Precision Time: %.4f seconds\n', time_double);

% TEST 2: Single Precision (The "Fast" way)
A_gpu_single = gpuArray(A_cpu_single);
wait(d); % Ensure transfer is done

fprintf('Running SINGLE precision test... ');
tic;
B_gpu = A_gpu_single * A_gpu_single;
wait(d); % FORCE MATLAB TO WAIT FOR GPU
time_single = toc;
fprintf('Done.\n');
fprintf('Single Precision Time: %.4f seconds\n', time_single);

% Calculate Speedup
fprintf('------------------------------------------------\n');
fprintf('Speedup Factor using single precision: %.2fx\n', time_double / time_single);

%
% Create 10,000 small matrices (10x10) stacked in a 3D array
A_stack = gpuArray.rand(10, 10, 10000, 'single');
B_stack = gpuArray.rand(10, 10, 10000, 'single');

% BAD: Looping (GPU overhead kills you)
tic;
for i=1:10000
   C(:,:,i) = A_stack(:,:,i) * B_stack(:,:,i);
end
wait(d);
loop_time = toc;

% GOOD: Pagefun (Executes all 10,000 mults simultaneously)
tic;
C_stack = pagefun(@mtimes, A_stack, B_stack);
wait(d);
pagefun_time = toc;

fprintf('------------------------------------------------\n');
fprintf('Speedup Factor using pagefun: %.2fx\n', loop_time / pagefun_time);


fprintf('Total VRAM:      %.2f GB\n', d.TotalMemory / 1e9);
fprintf('Available VRAM:  %.2f GB\n', d.AvailableMemory / 1e9);
fprintf('Usage:           %.1f%%\n', 100 * (1 - d.AvailableMemory / d.TotalMemory));