[RISCV] Add cost model tests for scalable FP reductions. NFC

There are already some in reduce-scalable-fp.ll but this makes it a
bit easier to see the difference alongside their fixed-length
counter

[RISCV] Add cost model tests for scalable FP reductions. NFC

There are already some in reduce-scalable-fp.ll but this makes it a
bit easier to see the difference alongside their fixed-length
counterparts.

show more ...

[RISCV] Fix bf16 cost model tests. NFC

These were inadvertently changed in #112393

[ValueTypes][RISCV] Add v1bf16 type (#111112)

When trying to add RISC-V fadd reduction cost model tests for bf16, I
noticed a crash when the vector was of <1 x bfloat>.

It turns out that this wa

[ValueTypes][RISCV] Add v1bf16 type (#111112)

When trying to add RISC-V fadd reduction cost model tests for bf16, I
noticed a crash when the vector was of <1 x bfloat>.

It turns out that this was being scalarized because unlike f16/f32/f64,
there's no v1bf16 value type, and the existing cost model code assumed
that the legalized type would always be a vector.

This adds v1bf16 to bring bf16 in line with the other fp types.

It also adds some more RISC-V bf16 reduction tests which previously
crashed, including tests to ensure that SLP won't emit fadd/fmul
reductions for bf16 or f16 w/ zvfhmin after #111000.

show more ...

[RISCV] Add tests for @llvm.vector.reduce.fmul. NFC