Hello,
How can I know the exact structure of ALU in the A53 ?
For example:
How many mnemonics like: vmlaq_f32, vsubq_f32, vaddq_f32 can work in parallel ?
Can I run store,load of float32x4 in parallel to vsubq_f32, vaddq_f32 ?
How many 128bits registers can I use ?
Thank you,
Zvika