I have a question regarding operation labeling of Arm64 instructions. I can see in reference manual [1] that most of the instructions in "floating-point and Advanced SIMD category" have both scalar and vector versions. My understanding is that source files src/arcch/arm/isa/insts/fp64.isa and src/arcch/arm/isa/insts/neon64.isa should correspond to scalar and vector versions of those instructions respectively. But, instructions in fp64.isa are also labelled as Simd operations. For example "fdiv" instruction in both files is labelled as "SimdFloatDivOp". Am I right in my understanding ? If yes, why do not we have scalar fp operations ?
Thanks for your time ! [1] https://people.mozilla.org/~sstangl/arm/AArch64-Reference-Manual.pdf
_______________________________________________ gem5-users mailing list gem5-users@gem5.org http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
