[llvm] [RISCV] Use LMUL=1 for vmv_s_x_vl with non-undef passthru (PR #66659)

Luke Lau via llvm-commits llvm-commits at lists.llvm.org
Mon Oct 2 01:52:33 PDT 2023

Previous message: [llvm] [RISCV] Create new build vector instead of relying on getNode constan… (PR #67944)
Next message: [llvm] [RISCV] Use LMUL=1 for vmv_s_x_vl with non-undef passthru (PR #66659)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

lukel97 wrote:

Ping
The test diff is smaller now after rebasing on top of #66087. It does the same optimisation for the vmv.s.xs  generated from insert_vector_elt, and this PR catches the remaining other cases.

https://github.com/llvm/llvm-project/pull/66659

Previous message: [llvm] [RISCV] Create new build vector instead of relying on getNode constan… (PR #67944)
Next message: [llvm] [RISCV] Use LMUL=1 for vmv_s_x_vl with non-undef passthru (PR #66659)
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list