Re: [Qemu-devel] [PATCH v2 13/29] tcg: Add INDEX_op_dup_mem_vec

2019-05-02 Thread Richard Henderson
On 5/2/19 6:30 AM, Alex Bennée wrote: >> +static void do_dup_store(TCGType type, uint32_t dofs, uint32_t oprsz, >> + uint32_t maxsz, TCGv_vec t_vec) >> +{ >> +uint32_t i = 0; >> + >> +switch (type) { >> +case TCG_TYPE_V256: >> +/* >> + * Recall th

Re: [Qemu-devel] [PATCH v2 13/29] tcg: Add INDEX_op_dup_mem_vec

2019-05-02 Thread Alex Bennée
Richard Henderson writes: > Allow the backend to expand dup from memory directly, instead of > forcing the value into a temp first. This is especially important > if integer/vector register moves do not exist. > > Note that officially tcg_out_dupm_vec is allowed to fail. > If it did, we could

[Qemu-devel] [PATCH v2 13/29] tcg: Add INDEX_op_dup_mem_vec

2019-04-30 Thread Richard Henderson
Allow the backend to expand dup from memory directly, instead of forcing the value into a temp first. This is especially important if integer/vector register moves do not exist. Note that officially tcg_out_dupm_vec is allowed to fail. If it did, we could fix this up relatively easily: VECE ==