1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
llvm-mirror/test/CodeGen/AArch64/aarch64-bswap-ext.ll
Andrew Savonichev 607f7c19c2 [AArch64] Combine vector shift instructions in SelectionDAG
bswap.v2i16 + sitofp in LLVM IR generate a sequence of:

  - REV32 + USHR for bswap.v2i16
  - SHL + SSHR + SCVTF for sext to v2i32 and scvt

The shift instructions are excessive as noted in PR24820, and they can
be optimized to just SSHR.

Differential Revision: https://reviews.llvm.org/D102333
2021-05-20 10:50:13 +03:00

28 lines
914 B
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
define <2 x i32> @test1(<2 x i16> %v2i16) {
; CHECK-LABEL: test1:
; CHECK: // %bb.0:
; CHECK-NEXT: rev32 v0.8b, v0.8b
; CHECK-NEXT: sshr v0.2s, v0.2s, #16
; CHECK-NEXT: ret
%v2i16_rev = call <2 x i16> @llvm.bswap.v2i16(<2 x i16> %v2i16)
%v2i32 = sext <2 x i16> %v2i16_rev to <2 x i32>
ret <2 x i32> %v2i32
}
define <2 x float> @test2(<2 x i16> %v2i16) {
; CHECK-LABEL: test2:
; CHECK: // %bb.0:
; CHECK-NEXT: rev32 v0.8b, v0.8b
; CHECK-NEXT: sshr v0.2s, v0.2s, #16
; CHECK-NEXT: scvtf v0.2s, v0.2s
; CHECK-NEXT: ret
%v2i16_rev = call <2 x i16> @llvm.bswap.v2i16(<2 x i16> %v2i16)
%v2f32 = sitofp <2 x i16> %v2i16_rev to <2 x float>
ret <2 x float> %v2f32
}
declare <2 x i16> @llvm.bswap.v2i16(<2 x i16>) nounwind readnone