100 likes | 226 Vues
This outline provides a comprehensive guide on implementing parallel dimensions in matrix constructors using specific front-end tags. It covers the configuration of matrices, commands for random generation, and the propagation of parallelism with a focus on handling confidential information. By utilizing parameters such as m and n, the outline details procedures for matrix creation and manipulation, ensuring efficient data handling in parallel computing contexts. The processing commands emphasize confidentiality while teaching how to manage and transmit data effectively.
E N D
The “*p” Outline: Front end tag for Parallel Dimensions Trigger for matrix Constructors Propagator of Parallelism Confidential Information
The “*p” Outline: Front end tag for Parallel Dimensions Trigger for matrix Constructors Propagator of Parallelism Confidential Information
The “*p”: Front end tag for “parallel dimensions” Commands, pointers transmitted. Not the data! Confidential Information
The “*p”: Front end tag for “parallel dimensions” >> m=100, n=200*p m = 100 n = 200p m,n Commands, pointers transmitted. Not the data! Confidential Information
The “*p”: Front end tag for “parallel dimensions” >> m=100, n=200*p m = 100 n = 200p >> a=rand(m,n), b=rand(n,m) a = ddense object: 100-by-200p b = ddense object: 200p-by-100 m,n Build random m,n a,b return pointer Commands, pointers transmitted. Not the data! Confidential Information
The “*p”: Front end tag for “parallel dimensions” >> m=100, n=200*p m = 100 n = 200p >> a=rand(m,n), b=rand(n,m) a = ddense object: 100-by-200p b = ddense object: 200p-by-100 >> np ans = 4 m,n Build random m,n a,b return pointer a: col dist 100x50 per processor b: row dist50x100 per processor Commands, pointers transmitted. Not the data! Confidential Information
The “*p” Outline: Front end tag for Parallel Dimensions Trigger for matrix Constructors Propagator of Parallelism Confidential Information
The “*p”: Trigger for Matrix Constructors >> m=100, n=200*p m = 100 n = 200p >> a=rand(100,200*p); a=randn(m,n); >> a=zeros(m,n); a=ones(m,n); >> a=eye(200*p); >> a=1:200*p; m,n Matrix Constructor m,n a return pointer Commands, pointers transmitted. Not the data! Confidential Information
The “*p” Outline: Front end tag for Parallel Dimensions Trigger for matrix Constructors Propagator of Parallelism Confidential Information
The “*p”: Propagator of Parallelism n >> n=2000*p; %Trigger constructors >> a=rand(3,n); >> x=rand(n,1); %Propagate Parallelism!!! >> k=size(x,1); >> b=ones(k); >> e=eye(size(a)); a x k b e k,n a,b,e,x Confidential Information