llvm-mirror/bswap64.ll at 805c8ee060a9f9c3659db0109a74f864972127a9 - llvm-mirror - Git.je (Gitea)

RPCS3/llvm-mirror

mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 20:43:44 +02:00

Guozhi Wei cb3c30a9d4 [PPC] Use xxbrd to speed up bswap64

Power doesn't have bswap instructions, so llvm generates following code sequence for bswap64.

  rotldi   5, 3, 16
  rotldi   4, 3, 8
  rotldi   9, 3, 24
  rotldi   10, 3, 32
  rotldi   11, 3, 48
  rotldi   12, 3, 56
  rldimi 4, 5, 8, 48
  rldimi 4, 9, 16, 40
  rldimi 4, 10, 24, 32
  rldimi 4, 11, 40, 16
  rldimi 4, 12, 48, 8
  rldimi 4, 3, 56, 0

But Power9 has vector bswap instructions, they can also be used to speed up scalar bswap intrinsic. With this patch, bswap64 can be translated to:

  mtvsrdd 34, 3, 3
  xxbrd 34, 34
  mfvsrld 3, 34

Differential Revision: https://reviews.llvm.org/D39510

llvm-svn: 317499

2017-11-06 19:09:38 +00:00

14 lines

259 B

LLVM

Raw Blame History

 ; RUN: llc -verify-machineinstrs < %s -mtriple=ppc64le-- -mcpu=pwr9 | FileCheck %s
 declare i64 @llvm.bswap.i64(i64)
 ; CHECK: mtvsrdd
 ; CHECK: xxbrd
 ; CHECK: mfvsrd
 define i64 @bswap64(i64 %x) {
 entry:
   %0 = call i64 @llvm.bswap.i64(i64 %x)
   ret i64 %0
 }