RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
Code Issues Projects Releases Wiki Activity

[PowerPC 4/4] Enable little-endian support for VSX.

Browse Source 
With the foregoing three patches, VSX instructions can be used for
little endian.  This patch removes the restriction that prevented
this, and re-enables the test cases from the first three patches.

llvm-svn: 223792
This commit is contained in:
Bill Schmidt 2014-12-09 16:59:57 +00:00
parent 015b0526cc
commit 41e95a89e4
5 changed files with 10 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/Target/PowerPC/PPCSubtarget.cpp
View File

@ -154,13 +154,6 @@ void PPCSubtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
// Determine endianness.
IsLittleEndian = (TargetTriple.getArch() == Triple::ppc64le);
// FIXME: For now, we disable VSX in little-endian mode until endian
// issues in those instructions can be addressed.
if (IsLittleEndian) {
HasVSX = false;
HasP8Vector = false;
}
// Determine default ABI.
if (TargetABI == PPC_ABI_UNKNOWN) {
if (!isDarwin() && IsPPC64) {

14
test/CodeGen/PowerPC/vsx-ldst-builtin-le.ll
View File

@ -1,13 +1,7 @@
;; Note: This test case disable VSX until LE support is enabled, as
;; otherwise we fail trying to deal with the @llvm.ppc.vsx.* builtins
;; for loads and stores.
; RUN: llc -mcpu=pwr8 -O2 -mtriple=powerpc64-unknown-linux-gnu < %s
;; FIXME: Delete this and above lines when VSX LE support enabled.
; R;UN: llc -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64le-unknown-linux-gnu < %s > %t
; R;UN: grep lxvd2x < %t | count 18
; R;UN: grep stxvd2x < %t | count 18
; R;UN: grep xxpermdi < %t | count 36
; RUN: llc -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64le-unknown-linux-gnu < %s > %t
; RUN: grep lxvd2x < %t | count 18
; RUN: grep stxvd2x < %t | count 18
; RUN: grep xxpermdi < %t | count 36
@vf = global <4 x float> <float -1.500000e+00, float 2.500000e+00, float -3.500000e+00, float 4.500000e+00>, align 16
@vd = global <2 x double> <double 3.500000e+00, double -7.500000e+00>, align 16

11
test/CodeGen/PowerPC/vsx-ldst.ll
View File

@ -9,13 +9,10 @@
; RUN: grep stxvw4x < %t | count 3
; RUN: grep stxvd2x < %t | count 3
;; Note: The LE test variant is disabled until LE support for VSX is enabled,
;; as otherwise we fail to get the expected counts.
; R;UN: llc -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64le-unknown-linux-gnu < %s > %t
; R;UN: grep lxvd2x < %t | count 6
; R;UN: grep stxvd2x < %t | count 6
; R;UN: grep xxpermdi < %t | count 12
; RUN: llc -mcpu=pwr8 -mattr=+vsx -O2 -mtriple=powerpc64le-unknown-linux-gnu < %s > %t
; RUN: grep lxvd2x < %t | count 6
; RUN: grep stxvd2x < %t | count 6
; RUN: grep xxpermdi < %t | count 12
@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

7
test/CodeGen/PowerPC/vsx_insert_extract_le.ll
View File

@ -1,9 +1,4 @@
; Note: This test is disabled until VSX is enabled for LE, as otherwise
; we don't get the correct code gen.
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64-unknown-linux-gnu < %s
; FIXME: Remove this and all above lines when VSX is enabled for LE.
; R;UN: llc -mcpu=pwr8 -mattr=+vsx -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
; RUN: llc -mcpu=pwr8 -mattr=+vsx -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
define <2 x double> @testi0(<2 x double>* %p1, double* %p2) {
%v = load <2 x double>* %p1

7
test/CodeGen/PowerPC/vsx_shuffle_le.ll
View File

@ -1,9 +1,4 @@
; Note: This test is disabled until VSX is enabled for LE, as otherwise
; we don't get the correct code gen.
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64-unknown-linux-gnu < %s
; FIXME: Remove this and all above lines when VSX is enabled for LE.
; R;UN: llc -mcpu=pwr8 -mattr=+vsx -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
; RUN: llc -mcpu=pwr8 -mattr=+vsx -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s
define <2 x double> @test00(<2 x double>* %p1, <2 x double>* %p2) {
%v1 = load <2 x double>* %p1