mbox series

[v3,00/16] target/arm: partial vector cleanup

Message ID 20200508152200.6547-1-richard.henderson@linaro.org
Headers show
Series target/arm: partial vector cleanup | expand

Message

Richard Henderson May 8, 2020, 3:21 p.m. UTC 
This is not complete, but shows the direction I'd like to go.

Version 2 extracts more bits from my sve2 branch.  There's
still more to pull back, especially for crypto_helper.c, where
there are also tail clearing bugs to fix.

Version 3 rebases on master, which has some of the arm neon
decodetree conversion applied.


r~


Richard Henderson (16):
  target/arm: Create gen_gvec_[us]sra
  target/arm: Create gen_gvec_{u,s}{rshr,rsra}
  target/arm: Create gen_gvec_{sri,sli}
  target/arm: Remove unnecessary range check for VSHL
  target/arm: Tidy handle_vec_simd_shri
  target/arm: Create gen_gvec_{ceq,clt,cle,cgt,cge}0
  target/arm: Create gen_gvec_{mla,mls}
  target/arm: Swap argument order for VSHL during decode
  target/arm: Create gen_gvec_{cmtst,ushl,sshl}
  target/arm: Create gen_gvec_{uqadd,sqadd,uqsub,sqsub}
  target/arm: Remove fp_status from helper_{recpe,rsqrte}_u32
  target/arm: Create gen_gvec_{qrdmla,qrdmls}
  target/arm: Pass pointer to qc to qrdmla/qrdmls
  target/arm: Clear tail in gvec_fmul_idx_*, gvec_fmla_idx_*
  target/arm: Vectorize SABD/UABD
  target/arm: Vectorize SABA/UABA

 target/arm/helper.h             |   71 +-
 target/arm/translate.h          |   84 +-
 target/arm/neon-dp.decode       |    9 +-
 target/arm/neon_helper.c        |   10 -
 target/arm/translate-a64.c      |  210 +---
 target/arm/translate-neon.inc.c |   59 +-
 target/arm/translate.c          | 1908 ++++++++++++++++++++-----------
 target/arm/vec_helper.c         |  233 +++-
 target/arm/vfp_helper.c         |    4 +-
 9 files changed, 1667 insertions(+), 921 deletions(-)

-- 
2.20.1

Comments

Peter Maydell May 12, 2020, 12:55 p.m. UTC | #1 
On Fri, 8 May 2020 at 16:22, Richard Henderson
<richard.henderson@linaro.org> wrote:
>

> This is not complete, but shows the direction I'd like to go.

>

> Version 2 extracts more bits from my sve2 branch.  There's

> still more to pull back, especially for crypto_helper.c, where

> there are also tail clearing bugs to fix.

>

> Version 3 rebases on master, which has some of the arm neon

> decodetree conversion applied.


Something in this patchset produces a failure on VRSRA:
testcases/aarch32-all-v80/insn_VRSRA__INC.risu.bin
from Alex's set produces different results.

thanks
-- PMM