maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64] Add a tablegen pattern for UZP2. 

Converts concat_vectors((trunc (lshr)), (trunc (lshr))) to UZP2
when the shift amount is half the width of the vector element.

Differential Revision: https://reviews.llvm.org/D116021
This commit is contained in:
Alexandros Lamprineas 2021-12-21 15:41:06 +00:00
parent 1a929525e8
commit ada028c32f
2 changed files with 60 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/AArch64/AArch64InstrInfo.td
View File

@ -5316,6 +5316,19 @@ def : Pat<(v4i32 (concat_vectors (v2i32 (trunc (v2i64 V128:$Vn))),
(v2i32 (trunc (v2i64 V128:$Vm))))),
(UZP1v4i32 V128:$Vn, V128:$Vm)>;
def : Pat<(v16i8 (concat_vectors
(v8i8 (trunc (AArch64vlshr (v8i16 V128:$Vn), (i32 8)))),
(v8i8 (trunc (AArch64vlshr (v8i16 V128:$Vm), (i32 8)))))),
(UZP2v16i8 V128:$Vn, V128:$Vm)>;
def : Pat<(v8i16 (concat_vectors
(v4i16 (trunc (AArch64vlshr (v4i32 V128:$Vn), (i32 16)))),
(v4i16 (trunc (AArch64vlshr (v4i32 V128:$Vm), (i32 16)))))),
(UZP2v8i16 V128:$Vn, V128:$Vm)>;
def : Pat<(v4i32 (concat_vectors
(v2i32 (trunc (AArch64vlshr (v2i64 V128:$Vn), (i32 32)))),
(v2i32 (trunc (AArch64vlshr (v2i64 V128:$Vm), (i32 32)))))),
(UZP2v4i32 V128:$Vn, V128:$Vm)>;
//----------------------------------------------------------------------------
// AdvSIMD TBL/TBX instructions
//----------------------------------------------------------------------------

47
llvm/test/CodeGen/AArch64/arm64-uzp2-combine.ll Normal file
View File

@ -0,0 +1,47 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple aarch64-none-linux-gnu | FileCheck %s
; Test the (concat_vectors (trunc (lshr)), (trunc (lshr))) pattern.
define <16 x i8> @test_combine_v8i16_to_v16i8(<8 x i16> %x, <8 x i16> %y) {
; CHECK-LABEL: test_combine_v8i16_to_v16i8:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: uzp2 v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%lshr1 = lshr <8 x i16> %x, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%trunc1 = trunc <8 x i16> %lshr1 to <8 x i8>
%lshr2 = lshr <8 x i16> %y, <i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8, i16 8>
%trunc2 = trunc <8 x i16> %lshr2 to <8 x i8>
%shuffle = shufflevector <8 x i8> %trunc1, <8 x i8> %trunc2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %shuffle
}
define <8 x i16> @test_combine_v4i32_to_v8i16(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: test_combine_v4i32_to_v8i16:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: uzp2 v0.8h, v0.8h, v1.8h
; CHECK-NEXT: ret
entry:
%lshr1 = lshr <4 x i32> %x, <i32 16, i32 16, i32 16, i32 16>
%trunc1 = trunc <4 x i32> %lshr1 to <4 x i16>
%lshr2 = lshr <4 x i32> %y, <i32 16, i32 16, i32 16, i32 16>
%trunc2 = trunc <4 x i32> %lshr2 to <4 x i16>
%shuffle = shufflevector <4 x i16> %trunc1, <4 x i16> %trunc2, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
ret <8 x i16> %shuffle
}
define <4 x i32> @test_combine_v2i64_to_v4i32(<2 x i64> %x, <2 x i64> %y) {
; CHECK-LABEL: test_combine_v2i64_to_v4i32:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: uzp2 v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%lshr1 = lshr <2 x i64> %x, <i64 32, i64 32>
%trunc1 = trunc <2 x i64> %lshr1 to <2 x i32>
%lshr2 = lshr <2 x i64> %y, <i64 32, i64 32>
%trunc2 = trunc <2 x i64> %lshr2 to <2 x i32>
%shuffle = shufflevector <2 x i32> %trunc1, <2 x i32> %trunc2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x i32> %shuffle
}