1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
llvm-mirror/test/CodeGen/SystemZ/vec-perm-13.ll
Ulrich Weigand 5d4e78925f [SystemZ] Fix another assertion failure in tryBuildVectorShuffle
This fixes yet another scenario where tryBuildVectorShuffle would
attempt to create a BUILD_VECTOR node with an invalid combination
of types.  This can happen if the incoming BUILD_VECTOR has elements
of a type different from the vector element type, which is allowed
in certain cases as long as they are all the same type.

When one of these elements is used in the residual vector, and
UNDEF elements are added to fill up the residual vector, those
UNDEFs then have to use the type of the original element, not
the vector element type, or else the resulting BUILD_VECTOR
will have an invalid type combination.

llvm-svn: 249706
2015-10-08 17:46:59 +00:00

39 lines
1.6 KiB
LLVM

; Test vector shuffles on vectors with implicitly extended elements
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | \
; RUN: FileCheck -check-prefix=CHECK-CODE %s
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | \
; RUN: FileCheck -check-prefix=CHECK-VECTOR %s
define <4 x i16> @f1(<4 x i16> %x) {
; CHECK-CODE-LABEL: f1:
; CHECK-CODE: larl [[REG:%r[0-5]]],
; CHECK-CODE: vl [[MASK:%v[0-9]+]], 0([[REG]])
; CHECK-CODE: vgbm [[ELT:%v[0-9]+]], 0
; CHECK-CODE: vperm %v24, %v24, [[ELT]], [[MASK]]
; CHECK-CODE: br %r14
; CHECK-VECTOR: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .byte 6
; CHECK-VECTOR-NEXT: .byte 7
; CHECK-VECTOR-NEXT: .byte 16
; CHECK-VECTOR-NEXT: .byte 17
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
; CHECK-VECTOR-NEXT: .space 1
%elt = extractelement <4 x i16> %x, i32 3
%vec1 = insertelement <4 x i16> undef, i16 %elt, i32 2
%vec2 = insertelement <4 x i16> %vec1, i16 0, i32 3
ret <4 x i16> %vec2
}