fixed vreg clearning

rvvector/basic/vx_vec.s

@@ -1,30 +1,23 @@
 
 
-
 .type vx_vec_test, @function
 .global vx_vec_test
 vx_vec_test:
-	li a1, 7
-	sw a1, 0(a0)
-	ret
-
-
-
-
-# 	slli a0, a0, 2
-# 	add a0, a0, a3
-# 	vmv.v.x vv0, a2
-# 	# vsplat4 vv0, a2
-# stripmine_loop:
-# 	vlb4 vv1, (a1)
-# 	vcmpez4 vp0, vv1
-# 	!vp0 vlw4 vv1, (a3)
-# 	!vp0 vlw4 vv2, (a4)
-# 	!vp0 vfma4 vv1, vv0, vv1, vv2
-# 	!vp0 vsw4 vv1, (a4)
-# 	addi a1, a1, 4
-# 	addi a3, a3, 16
-# 	addi a4, a4, 16
-# 	bleu a3, a0, stripmine_loop
-	# handle edge cases
-	# when (n % 4) != 0 ...
+# vector-vector add routine of 32-bit integers
+# void vvaddint32(size_t n, const int*x, const int*y, int*z)
+# { for (size_t i=0; i<n; i++) { z[i]=x[i]+y[i]; } }
+#
+# a0 = n, a1 = x, a2 = y, a3 = z
+# Non-vector instructions are indented
+    vsetvli t0, a0, e32 # Set vector length based on 32-bit vectors
+    vlw.v v0, (a1)           # Get first vector
+      sub a0, a0, t0         # Decrement number done
+      slli t0, t0, 2         # Multiply number done by 4 bytes
+      add a1, a1, t0         # Bump pointer
+    vlw.v v1, (a2)           # Get second vector
+      add a2, a2, t0         # Bump pointer
+    vadd.vv v2, v0, v1        # Sum vectors
+    vsw.v v2, (a3)           # Store result
+      add a3, a3, t0         # Bump pointer
+      bnez a0, vx_vec_test   # Loop back 
+    ret                    # Finished