\item Standard Register File(s) overloaded with CSR "reg is vector"\\
(see pseudocode slides for examples)
\item Element width (and type?) concepts remain same as RVV\\
- (CSRs are used to "interpret" elements in registers)
+ (CSRs give new size (and meaning?) to elements in registers)
\item CSRs are key-value tables (overlaps allowed)\vspace{10pt}
\end{itemize}
Key differences from RVV:\vspace{10pt}
CSRvect1 = \{type: F, key: a3, val: a3, elwidth: dflt\}
CSRvect2 = \{type: F, key: a7, val: a7, elwidth: dflt\}
loop:
- setvl t0, a0, 4 # vl = t0 = min(4, n)
- ld a3, a1 # load 4 registers a3-6 from x
- slli t1, t0, 3 # t1 = vl * 8 (in bytes)
- ld a7, a2 # load 4 registers a7-10 from y
- add a1, a1, t1 # increment pointer to x by vl*8
- fmadd a7, a3, fa0, a7 # v1 += v0 * fa0 (y = a * x + y)
- sub a0, a0, t0 # n -= vl (t0)
- st a7, a2 # store 4 registers a7-10 to y
- add a2, a2, t1 # increment pointer to y by vl*8
- bnez a0, loop # repeat if n != 0
+ setvl t0, a0, 4 # vl = t0 = min(4, n)
+ ld a3, a1 # load 4 registers a3-6 from x
+ slli t1, t0, 3 # t1 = vl * 8 (in bytes)
+ ld a7, a2 # load 4 registers a7-10 from y
+ add a1, a1, t1 # increment pointer to x by vl*8
+ fmadd a7, a3, fa0, a7 # v1 += v0 * fa0 (y = a * x + y)
+ sub a0, a0, t0 # n -= vl (t0)
+ st a7, a2 # store 4 registers a7-10 to y
+ add a2, a2, t1 # increment pointer to y by vl*8
+ bnez a0, loop # repeat if n != 0
\end{semiverbatim}
\end{frame}