mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-10 06:54:54 +00:00
can. As Nate pointed out, VTBL isn't super performant, but it *has* to be better than this: _shuf: @ BB#0: @ %entry push {r4, r7, lr} add r7, sp, #4 sub sp, #12 mov r4, sp bic r4, r4, #7 mov sp, r4 mov r2, sp vmov d16, r0, r1 orr r0, r2, #6 orr r3, r2, #7 vst1.8 {d16[0]}, [r3] vst1.8 {d16[5]}, [r0] subs r4, r7, #4 orr r0, r2, #5 vst1.8 {d16[4]}, [r0] orr r0, r2, #4 vst1.8 {d16[4]}, [r0] orr r0, r2, #3 vst1.8 {d16[0]}, [r0] orr r0, r2, #2 vst1.8 {d16[2]}, [r0] orr r0, r2, #1 vst1.8 {d16[1]}, [r0] vst1.8 {d16[3]}, [r2] vldr.64 d16, [sp] vmov r0, r1, d16 mov sp, r4 pop {r4, r7, pc} The "illegal" testcase in vext.ll is no longer illegal. <rdar://problem/9078775> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127630 91177308-0d34-0410-b5e6-96231b3b80d8
124 lines
4.6 KiB
LLVM
124 lines
4.6 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i8> @test_vextd(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: test_vextd:
|
|
;CHECK: vext
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10>
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i8> @test_vextRd(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: test_vextRd:
|
|
;CHECK: vext
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 13, i32 14, i32 15, i32 0, i32 1, i32 2, i32 3, i32 4>
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @test_vextq(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: test_vextq:
|
|
;CHECK: vext
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <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, i32 16, i32 17, i32 18>
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @test_vextRq(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: test_vextRq:
|
|
;CHECK: vext
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6>
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @test_vextd16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: test_vextd16:
|
|
;CHECK: vext
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @test_vextq32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
;CHECK: test_vextq32:
|
|
;CHECK: vext
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
; Undef shuffle indices should not prevent matching to VEXT:
|
|
|
|
define <8 x i8> @test_vextd_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: test_vextd_undef:
|
|
;CHECK: vext
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 3, i32 undef, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10>
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @test_vextRq_undef(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: test_vextRq_undef:
|
|
;CHECK: vext
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 23, i32 24, i32 25, i32 26, i32 undef, i32 undef, i32 29, i32 30, i32 31, i32 0, i32 1, i32 2, i32 3, i32 4, i32 undef, i32 6>
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
; Tests for ReconstructShuffle function. Indices have to be carefully
|
|
; chosen to reach lowering phase as a BUILD_VECTOR.
|
|
|
|
; One vector needs vext, the other can be handled by extract_subvector
|
|
; Also checks interleaving of sources is handled correctly.
|
|
; Essence: a vext is used on %A and something saner than stack load/store for final result.
|
|
define <4 x i16> @test_interleaved(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: test_interleaved:
|
|
;CHECK: vext.16
|
|
;CHECK-NOT: vext.16
|
|
;CHECK: vzip.16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <4 x i32> <i32 3, i32 8, i32 5, i32 9>
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
; An undef in the shuffle list should still be optimizable
|
|
define <4 x i16> @test_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: test_undef:
|
|
;CHECK: vzip.16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <4 x i32> <i32 undef, i32 8, i32 5, i32 9>
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
; We should ignore a build_vector with more than two sources.
|
|
; Use illegal <32 x i16> type to produce such a shuffle after legalizing types.
|
|
; Try to look for fallback to stack expansion.
|
|
define <4 x i16> @test_multisource(<32 x i16>* %B) nounwind {
|
|
;CHECK: test_multisource:
|
|
;CHECK: vst1.16
|
|
%tmp1 = load <32 x i16>* %B
|
|
%tmp2 = shufflevector <32 x i16> %tmp1, <32 x i16> undef, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
|
|
ret <4 x i16> %tmp2
|
|
}
|
|
|
|
; We don't handle shuffles using more than half of a 128-bit vector.
|
|
; Again, test for fallback to stack expansion
|
|
define <4 x i16> @test_largespan(<8 x i16>* %B) nounwind {
|
|
;CHECK: test_largespan:
|
|
;CHECK: vst1.16
|
|
%tmp1 = load <8 x i16>* %B
|
|
%tmp2 = shufflevector <8 x i16> %tmp1, <8 x i16> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
ret <4 x i16> %tmp2
|
|
}
|