diff options
| author | Nemanja Ivanovic <nemanja.i.ibm@gmail.com> | 2016-09-22 09:52:19 +0000 |
|---|---|---|
| committer | Nemanja Ivanovic <nemanja.i.ibm@gmail.com> | 2016-09-22 09:52:19 +0000 |
| commit | 6e7879c5e6e26c2c6d00618f12af20012eecff41 (patch) | |
| tree | e75271eca7c8a4f68a884aad96748b64ab021bb5 /llvm/test/CodeGen/PowerPC/vsx-ldst.ll | |
| parent | 2ce2ab3a4dc1df6ec87a42aa2baa6741c2456e0c (diff) | |
| download | bcm5719-llvm-6e7879c5e6e26c2c6d00618f12af20012eecff41.tar.gz bcm5719-llvm-6e7879c5e6e26c2c6d00618f12af20012eecff41.zip | |
[Power9] Add exploitation of non-permuting memory ops
This patch corresponds to review:
https://reviews.llvm.org/D19825
The new lxvx/stxvx instructions do not require the swaps to line the elements
up correctly. In order to select them over the lxvd2x/lxvw4x instructions which
require swaps, the patterns for the old instruction have a predicate that
ensures they won't be selected on Power9 and newer CPUs.
llvm-svn: 282143
Diffstat (limited to 'llvm/test/CodeGen/PowerPC/vsx-ldst.ll')
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/vsx-ldst.ll | 16 |
1 files changed, 13 insertions, 3 deletions
diff --git a/llvm/test/CodeGen/PowerPC/vsx-ldst.ll b/llvm/test/CodeGen/PowerPC/vsx-ldst.ll index 3c06a3fdc34..a146182de99 100644 --- a/llvm/test/CodeGen/PowerPC/vsx-ldst.ll +++ b/llvm/test/CodeGen/PowerPC/vsx-ldst.ll @@ -1,18 +1,28 @@ -; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64-unknown-linux-gnu < %s > %t +; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O2 \ +; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s > %t ; RUN: grep lxvw4x < %t | count 3 ; RUN: grep lxvd2x < %t | count 3 ; RUN: grep stxvw4x < %t | count 3 ; RUN: grep stxvd2x < %t | count 3 -; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O0 -fast-isel=1 -mtriple=powerpc64-unknown-linux-gnu < %s > %t + +; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O0 -fast-isel=1 \ +; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s > %t ; RUN: grep lxvw4x < %t | count 3 ; RUN: grep lxvd2x < %t | count 3 ; RUN: grep stxvw4x < %t | count 3 ; RUN: grep stxvd2x < %t | count 3 -; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64le-unknown-linux-gnu < %s > %t +; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx -O2 \ +; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s > %t ; RUN: grep lxvd2x < %t | count 6 ; RUN: grep stxvd2x < %t | count 6 +; RUN: llc -verify-machineinstrs -mcpu=pwr9 -O2 \ +; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s > %t +; RUN: grep lxvx < %t | count 6 +; RUN: grep stxvx < %t | count 6 + + @vsi = global <4 x i32> <i32 -1, i32 2, i32 -3, i32 4>, align 16 @vui = global <4 x i32> <i32 0, i32 1, i32 2, i32 3>, align 16 @vf = global <4 x float> <float -1.500000e+00, float 2.500000e+00, float -3.500000e+00, float 4.500000e+00>, align 16 |
