As you can see it stores the dst[y] on each iteration. With function definition of:
void sum_of_squares_1(float dst[restrict ROWS], float src[restrict ROWS][COLS])
The disassembly becomes completely different. However the speed of the end result did not really change that much.
Could you throw objdump -d of the best icc output to pastebin? I'm interested to see what kind of code it produces.
Without it the code of sum_of_squares_1 is as following:
As you can see it stores the dst[y] on each iteration. With function definition of: void sum_of_squares_1(float dst[restrict ROWS], float src[restrict ROWS][COLS]) The disassembly becomes completely different. However the speed of the end result did not really change that much.Could you throw objdump -d of the best icc output to pastebin? I'm interested to see what kind of code it produces.