RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 05:23:45 +02:00
Code Issues Projects Releases Wiki Activity
b006cbb88e
llvm-mirror/test/CodeGen/PowerPC/vec_shuffle_le.ll
Bill Schmidt cb25653e71 [PowerPC 1/4] Little-endian adjustments for VSX loads/stores 
This patch addresses the inherent big-endian bias in the lxvd2x,
lxvw4x, stxvd2x, and stxvw4x instructions.  These instructions load
vector elements into registers left-to-right (with the first element
loaded into the high-order bits of the register), regardless of the
endian setting of the processor.  However, these are the only
vector memory instructions that permit unaligned storage accesses, so
we want to use them for little-endian.

To make this work, a lxvd2x or lxvw4x is replaced with an lxvd2x
followed by an xxswapd, which swaps the doublewords.  This works for
lxvw4x as well as lxvd2x, because for lxvw4x on an LE system the
vector elements are in LE order (right-to-left) within each
doubleword.  (Thus after lxvw2x of a <4 x float> the elements will
appear as 1, 0, 3, 2.  Following the swap, they will appear as 3, 2,
0, 1, as desired.)   For stores, an stxvd2x or stxvw4x is replaced
with an stxvd2x preceded by an xxswapd.

Introduction of extra swap instructions provides correctness, but
obviously is not ideal from a performance perspective.  Future patches
will address this with optimizations to remove most of the introduced
swaps, which have proven effective in other implementations.

The introduction of the swaps is performed during lowering of LOAD,
STORE, INTRINSIC_W_CHAIN, and INTRINSIC_VOID operations.  The latter
are used to translate intrinsics that specify the VSX loads and stores
directly into equivalent sequences for little endian.  Thus code that
uses vec_vsx_ld and vec_vsx_st does not have to be modified to be
ported from BE to LE.

We introduce new PPCISD opcodes for LXVD2X, STXVD2X, and XXSWAPD for
use during this lowering step.  In PPCInstrVSX.td, we add new SDType
and SDNode definitions for these (PPClxvd2x, PPCstxvd2x, PPCxxswapd).
These are recognized during instruction selection and mapped to the
correct instructions.

Several tests that were written to use -mcpu=pwr7 or pwr8 are modified
to disable VSX on LE variants because code generation changes with
this and subsequent patches in this set.  I chose to include all of
these in the first patch than try to rigorously sort out which tests
were broken by one or another of the patches.  Sorry about that.

The new test vsx-ldst-builtin-le.ll, and the changes to vsx-ldst.ll,
are disabled until LE support is enabled because of breakages that
occur as noted in those tests.  They are re-enabled in patch 4/4.

llvm-svn: 223783
2014-12-09 16:35:51 +00:00

210 lines
8.0 KiB
LLVM
Raw Blame History

; RUN: llc < %s -mtriple=powerpc64le-unknown-linux-gnu -mattr=+altivec -mattr=-vsx -mcpu=pwr7 | FileCheck %s
define void @VPKUHUM_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VPKUHUM_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vpkuhum [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VPKUHUM_xx(<16 x i8>* %A) {
entry:
; CHECK: VPKUHUM_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
; CHECK: vpkuhum
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VPKUWUM_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VPKUWUM_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 1, i32 4, i32 5, i32 8, i32 9, i32 12, i32 13, i32 16, i32 17, i32 20, i32 21, i32 24, i32 25, i32 28, i32 29>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vpkuwum [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VPKUWUM_xx(<16 x i8>* %A) {
entry:
; CHECK: VPKUWUM_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 0, i32 1, i32 4, i32 5, i32 8, i32 9, i32 12, i32 13, i32 0, i32 1, i32 4, i32 5, i32 8, i32 9, i32 12, i32 13>
; CHECK: vpkuwum
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGLB_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGLB_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrglb [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGLB_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGLB_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 0, i32 0, i32 1, i32 1, i32 2, i32 2, i32 3, i32 3, i32 4, i32 4, i32 5, i32 5, i32 6, i32 6, i32 7, i32 7>
; CHECK: vmrglb
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGHB_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGHB_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrghb [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGHB_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGHB_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 8, i32 8, i32 9, i32 9, i32 10, i32 10, i32 11, i32 11, i32 12, i32 12, i32 13, i32 13, i32 14, i32 14, i32 15, i32 15>
; CHECK: vmrghb
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGLH_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGLH_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrglh [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGLH_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGLH_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 0, i32 1, i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 4, i32 5, i32 4, i32 5, i32 6, i32 7, i32 6, i32 7>
; CHECK: vmrglh
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGHH_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGHH_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrghh [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGHH_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGHH_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 8, i32 9, i32 8, i32 9, i32 10, i32 11, i32 10, i32 11, i32 12, i32 13, i32 12, i32 13, i32 14, i32 15, i32 14, i32 15>
; CHECK: vmrghh
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGLW_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGLW_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrglw [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGLW_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGLW_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7>
; CHECK: vmrglw
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VMRGHW_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VMRGHW_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 24, i32 25, i32 26, i32 27, i32 12, i32 13, i32 14, i32 15, i32 28, i32 29, i32 30, i32 31>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vmrghw [[REG3:[0-9]+]], [[REG2]], [[REG1]]
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VMRGHW_xx(<16 x i8>* %A) {
entry:
; CHECK: VMRGHW_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 12, i32 13, i32 14, i32 15>
; CHECK: vmrghw
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
define void @VSLDOI_xy(<16 x i8>* %A, <16 x i8>* %B) {
entry:
; CHECK: VSLDOI_xy:
%tmp = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp2, <16 x i32> <i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27>
; CHECK: lvx [[REG1:[0-9]+]]
; CHECK: lvx [[REG2:[0-9]+]]
; CHECK: vsldoi [[REG3:[0-9]+]], [[REG2]], [[REG1]], 4
store <16 x i8> %tmp3, <16 x i8>* %A
ret void
}
define void @VSLDOI_xx(<16 x i8>* %A) {
entry:
; CHECK: VSLDOI_xx:
%tmp = load <16 x i8>* %A
%tmp2 = shufflevector <16 x i8> %tmp, <16 x i8> %tmp, <16 x i32> <i32 12, i32 13, i32 14, i32 15, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
; CHECK: vsldoi
store <16 x i8> %tmp2, <16 x i8>* %A
ret void
}
Reference in New Issue View Git Blame Copy Permalink