Differences

This shows you the differences between two versions of the page.

--- tiled_code_generator_dtiler [2014/12/11 19:58]
yun
+++ tiled_code_generator_dtiler [2017/04/19 13:31]
@@ Line 1: / Line 1: @@
-======Tiled Code Generator======
-Tiling is an important program transformation that is used to improve data locality and parallelization granularity. We provide a tiled code generator that produces tiled code with wavefront parallelization supported for the shared memory machine.
-===Usage===
-Let's use the classic matrix multiplication as an illustration example, whose alphabets code is the following:
-<sxh alphabets; gutter:false>
-affine matrix_product {P, Q, R|P>0 && Q>0 && R>0}
-       given  float A {i,k| 0<=i<P && 0<=k<Q};
-              float B {k,j| 0<=k<Q && 0<=j<R};
-     returns  float C {i,j,k| 0<=i<P && 0<=j<R && k==Q};
-using
-   float temp_C {i,j,k|0<=i<P && 0<=j<R && 0<=k<=Q};
-through
-   temp_C[i,j,k] = case
-                      {|k>0}  : temp_C[i,j,k-1] + A[i,k-1]*B[k-1,j];
-                      {|k==0} : 0;
-                   esac;
-   C      = temp_C;
-.
-</sxh>
-The tiled code generator is called through ScheduledC, therefore, the first step for the code generation is the same with ScheduledC -- specify spacetime map and memory map.

AlphaZ