ef7aad0db4
Instead of doing multiple unpacks when zero extending vectors (e.g. v2i16 -> v2i64), benchmarks have shown that it is better to do a VPERM (vector permute) since that is only one sequential instruction on the critical path. This patch achieves this by 1. Expand ZERO_EXTEND_VECTOR_INREG into a vector shuffle with a zero vector instead of (multiple) unpacks. 2. Improve SystemZ::GeneralShuffle to perform a single unpack as the last operation if Bytes matches it. Review: Ulrich Weigand Differential Revision: https://reviews.llvm.org/D78486
95 lines
2.2 KiB
LLVM
95 lines
2.2 KiB
LLVM
; Test that vector zexts are done efficently also in case of fewer elements
|
|
; than allowed, e.g. <2 x i32>.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
|
|
|
|
|
|
define <2 x i16> @fun1(<2 x i8> %val1) {
|
|
; CHECK-LABEL: fun1:
|
|
; CHECK: vuplhb %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i8> %val1 to <2 x i16>
|
|
ret <2 x i16> %z
|
|
}
|
|
|
|
define <2 x i32> @fun2(<2 x i8> %val1) {
|
|
; CHECK-LABEL: fun2:
|
|
; CHECK: larl %r1, .LCPI1_0
|
|
; CHECK-NEXT: vl %v0, 0(%r1), 3
|
|
; CHECK-NEXT: vperm %v24, %v0, %v24, %v0
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i8> %val1 to <2 x i32>
|
|
ret <2 x i32> %z
|
|
}
|
|
|
|
define <2 x i64> @fun3(<2 x i8> %val1) {
|
|
; CHECK-LABEL: fun3:
|
|
; CHECK: larl %r1, .LCPI2_0
|
|
; CHECK-NEXT: vl %v0, 0(%r1), 3
|
|
; CHECK-NEXT: vperm %v24, %v0, %v24, %v0
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i8> %val1 to <2 x i64>
|
|
ret <2 x i64> %z
|
|
}
|
|
|
|
define <2 x i32> @fun4(<2 x i16> %val1) {
|
|
; CHECK-LABEL: fun4:
|
|
; CHECK: vuplhh %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i16> %val1 to <2 x i32>
|
|
ret <2 x i32> %z
|
|
}
|
|
|
|
define <2 x i64> @fun5(<2 x i16> %val1) {
|
|
; CHECK-LABEL: fun5:
|
|
; CHECK: larl %r1, .LCPI4_0
|
|
; CHECK-NEXT: vl %v0, 0(%r1), 3
|
|
; CHECK-NEXT: vperm %v24, %v0, %v24, %v0
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i16> %val1 to <2 x i64>
|
|
ret <2 x i64> %z
|
|
}
|
|
|
|
define <2 x i64> @fun6(<2 x i32> %val1) {
|
|
; CHECK-LABEL: fun6:
|
|
; CHECK: vuplhf %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <2 x i32> %val1 to <2 x i64>
|
|
ret <2 x i64> %z
|
|
}
|
|
|
|
define <4 x i16> @fun7(<4 x i8> %val1) {
|
|
; CHECK-LABEL: fun7:
|
|
; CHECK: vuplhb %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <4 x i8> %val1 to <4 x i16>
|
|
ret <4 x i16> %z
|
|
}
|
|
|
|
define <4 x i32> @fun8(<4 x i8> %val1) {
|
|
; CHECK-LABEL: fun8:
|
|
; CHECK: larl %r1, .LCPI7_0
|
|
; CHECK-NEXT: vl %v0, 0(%r1), 3
|
|
; CHECK-NEXT: vperm %v24, %v0, %v24, %v0
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <4 x i8> %val1 to <4 x i32>
|
|
ret <4 x i32> %z
|
|
}
|
|
|
|
define <4 x i32> @fun9(<4 x i16> %val1) {
|
|
; CHECK-LABEL: fun9:
|
|
; CHECK: vuplhh %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <4 x i16> %val1 to <4 x i32>
|
|
ret <4 x i32> %z
|
|
}
|
|
|
|
define <8 x i16> @fun10(<8 x i8> %val1) {
|
|
; CHECK-LABEL: fun10:
|
|
; CHECK: vuplhb %v24, %v24
|
|
; CHECK-NEXT: br %r14
|
|
%z = zext <8 x i8> %val1 to <8 x i16>
|
|
ret <8 x i16> %z
|
|
}
|
|
|