This discussion has been locked.

You can no longer post new replies to this discussion. If you have a question you can start a new discussion

VZIP instruction

Note: This was originally posted on 25th June 2009 at http://forums.arm.com

Hello,

I am using NEON instructions in my application as Inline Assembly routine.

I am getting some different out put by executing VZIP instruction.

As per ARM DDI0406B_arm_architecture_reference_manual.pdf (Page A8-806), It should interleaves data as per size.

I have used "VZIP.8 D8,D12" instruction. D8 and D12 values are as per below

D8 = { 0x94,0x4f,0x51,0x55,0x51,0x55,0x55,0x4f}
D12 = {0x6a,0x4f,0x51,0x55,0x51,0x55,0x55,0x4f}

As per manual, after executing instruction output should be as per below

D8 = {0x94,0x6a,0x4f,0x4f,0x51,0x51,0x55,0x55}
D12 ={0x51,0x51,0x55,0x55,0x55,0x55,0x4f,0x4f}

Instead of above output, I am getting different as per below.

D8 = {0x94, 0x94, 0x94, 0x94, 0x51, 0x51, 0x55, 0x55}
D12 = {0x51, 0x51, 0x51, 0x51, 0x55, 0x55, 0x4f, 0x4f}

I am using QEMU Simulator option for debugging application.

Please guide me, what are other settings require at time of instruction execution to get output proper?