953838dcea
Custom lower vector type bitreverse to scalar bitrev and vshuf4i instructions. Keep `v2i64` and `v4i64` bitreverse `Expand`, it's good enough.
96 lines
3.4 KiB
LLVM
96 lines
3.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc --mtriple=loongarch64 -mattr=+lasx --verify-machineinstrs < %s \
|
|
; RUN: | FileCheck %s
|
|
|
|
declare <32 x i8> @llvm.bitreverse.v32i8(<32 x i8>)
|
|
|
|
define <32 x i8> @test_bitreverse_v32i8(<32 x i8> %a) nounwind {
|
|
; CHECK-LABEL: test_bitreverse_v32i8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 0
|
|
; CHECK-NEXT: bitrev.8b $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 0
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 1
|
|
; CHECK-NEXT: bitrev.8b $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 1
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 2
|
|
; CHECK-NEXT: bitrev.8b $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 2
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 3
|
|
; CHECK-NEXT: bitrev.8b $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 3
|
|
; CHECK-NEXT: xvori.b $xr0, $xr1, 0
|
|
; CHECK-NEXT: ret
|
|
%b = call <32 x i8> @llvm.bitreverse.v32i8(<32 x i8> %a)
|
|
ret <32 x i8> %b
|
|
}
|
|
|
|
declare <16 x i16> @llvm.bitreverse.v16i16(<16 x i16>)
|
|
|
|
define <16 x i16> @test_bitreverse_v16i16(<16 x i16> %a) nounwind {
|
|
; CHECK-LABEL: test_bitreverse_v16i16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 0
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 0
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 1
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 1
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 2
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 2
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 3
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 3
|
|
; CHECK-NEXT: xvshuf4i.h $xr0, $xr1, 27
|
|
; CHECK-NEXT: ret
|
|
%b = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> %a)
|
|
ret <16 x i16> %b
|
|
}
|
|
|
|
declare <8 x i32> @llvm.bitreverse.v8i32(<8 x i32>)
|
|
|
|
define <8 x i32> @test_bitreverse_v8i32(<8 x i32> %a) nounwind {
|
|
; CHECK-LABEL: test_bitreverse_v8i32:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 0
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 0
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 1
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 1
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 2
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 2
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 3
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 3
|
|
; CHECK-NEXT: xvshuf4i.w $xr0, $xr1, 177
|
|
; CHECK-NEXT: ret
|
|
%b = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> %a)
|
|
ret <8 x i32> %b
|
|
}
|
|
|
|
declare <4 x i64> @llvm.bitreverse.v4i64(<4 x i64>)
|
|
|
|
define <4 x i64> @test_bitreverse_v4i64(<4 x i64> %a) nounwind {
|
|
; CHECK-LABEL: test_bitreverse_v4i64:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 0
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 0
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 1
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 1
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 2
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 2
|
|
; CHECK-NEXT: xvpickve2gr.d $a0, $xr0, 3
|
|
; CHECK-NEXT: bitrev.d $a0, $a0
|
|
; CHECK-NEXT: xvinsgr2vr.d $xr1, $a0, 3
|
|
; CHECK-NEXT: xvori.b $xr0, $xr1, 0
|
|
; CHECK-NEXT: ret
|
|
%b = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> %a)
|
|
ret <4 x i64> %b
|
|
}
|