Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The arguments for vsetvli instruction #1

Open
zhuweipu opened this issue Mar 23, 2021 · 1 comment
Open

The arguments for vsetvli instruction #1

zhuweipu opened this issue Mar 23, 2021 · 1 comment

Comments

@zhuweipu
Copy link

Hello, I am confused about the arguments for vsetvli instruction in the vector test loop.

vsetvli t0, a2, e8,m1 uses a2 as the AVL to set vl register, but a2 = src2, a3 is actually the number of vector elements.

Is there anything wrong?

# void add_data_vec_8(int8_t *dest_data, int8_t *src1, int8_t *src2, int data_num);
# a0=dest, a1=src1, a2=src2, a3=n
#
add_data_vec_8:
    // mv      a3, a0          # Copy destination
.loop_8:
    vsetvli t0, a2, e8,m1   # Vectors of 8b
    vle8.v  v0, (a1)        # Load bytes
    add     a1, a1, t0  	# Bump pointer
    vle8.v  v1, (a2)        # Load bytes
    add     a2, a2, t0  	# Bump pointer
    sub     a3, a3, t0  	# Decrement count
    vadd.vv v2, v1, v0      # Vector Add
    vse8.v  v2, (a0)    	# Store bytes
    add     a0, a0, t0  	# Bump pointer
    bnez    a3, .loop_8    	# Any more?
    ret                 	# Return
@msyksphinz-self
Copy link
Owner

Oh yes you're right. I fixed but sorry I didn't test my fix at all.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants