mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 21:13:02 +02:00
f1715d1306
When matching an interleaved load to an ldN pattern, the interleaved access pass checks that all users of the load are shuffles. If the load is used by an instruction other than a shuffle, the pass gives up and an ldN is not generated. This patch considers users of the load that are extractelement instructions. It attempts to modify the extracts to use one of the available shuffles rather than the load. After the transformation, the load is only used by shuffles and will then be matched with an ldN pattern. Differential Revision: http://reviews.llvm.org/D20250 llvm-svn: 270142
283 lines
13 KiB
LLVM
283 lines
13 KiB
LLVM
; RUN: llc -mtriple=aarch64 -lower-interleaved-accesses=true < %s | FileCheck %s -check-prefix=NEON
|
|
; RUN: llc -mtriple=aarch64 -lower-interleaved-accesses=true -mattr=-neon < %s | FileCheck %s -check-prefix=NONEON
|
|
|
|
; NEON-LABEL: load_factor2:
|
|
; NEON: ld2 { v0.8b, v1.8b }, [x0]
|
|
; NONEON-LABEL: load_factor2:
|
|
; NONEON-NOT: ld2
|
|
define <8 x i8> @load_factor2(<16 x i8>* %ptr) {
|
|
%wide.vec = load <16 x i8>, <16 x i8>* %ptr, align 4
|
|
%strided.v0 = shufflevector <16 x i8> %wide.vec, <16 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
%strided.v1 = shufflevector <16 x i8> %wide.vec, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
%add = add nsw <8 x i8> %strided.v0, %strided.v1
|
|
ret <8 x i8> %add
|
|
}
|
|
|
|
; NEON-LABEL: load_factor3:
|
|
; NEON: ld3 { v0.4s, v1.4s, v2.4s }, [x0]
|
|
; NONEON-LABEL: load_factor3:
|
|
; NONEON-NOT: ld3
|
|
define <4 x i32> @load_factor3(i32* %ptr) {
|
|
%base = bitcast i32* %ptr to <12 x i32>*
|
|
%wide.vec = load <12 x i32>, <12 x i32>* %base, align 4
|
|
%strided.v2 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
|
|
%strided.v1 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
|
|
%add = add nsw <4 x i32> %strided.v2, %strided.v1
|
|
ret <4 x i32> %add
|
|
}
|
|
|
|
; NEON-LABEL: load_factor4:
|
|
; NEON: ld4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
|
|
; NONEON-LABEL: load_factor4:
|
|
; NONEON-NOT: ld4
|
|
define <4 x i32> @load_factor4(i32* %ptr) {
|
|
%base = bitcast i32* %ptr to <16 x i32>*
|
|
%wide.vec = load <16 x i32>, <16 x i32>* %base, align 4
|
|
%strided.v0 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
|
|
%strided.v2 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
|
|
%add = add nsw <4 x i32> %strided.v0, %strided.v2
|
|
ret <4 x i32> %add
|
|
}
|
|
|
|
; NEON-LABEL: store_factor2:
|
|
; NEON: st2 { v0.8b, v1.8b }, [x0]
|
|
; NONEON-LABEL: store_factor2:
|
|
; NONEON-NOT: st2
|
|
define void @store_factor2(<16 x i8>* %ptr, <8 x i8> %v0, <8 x i8> %v1) {
|
|
%interleaved.vec = shufflevector <8 x i8> %v0, <8 x i8> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
|
|
store <16 x i8> %interleaved.vec, <16 x i8>* %ptr, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_factor3:
|
|
; NEON: st3 { v0.4s, v1.4s, v2.4s }, [x0]
|
|
; NONEON-LABEL: store_factor3:
|
|
; NONEON-NOT: st3
|
|
define void @store_factor3(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
|
|
%base = bitcast i32* %ptr to <12 x i32>*
|
|
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%v2_u = shufflevector <4 x i32> %v2, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_u, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
|
|
store <12 x i32> %interleaved.vec, <12 x i32>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_factor4:
|
|
; NEON: st4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
|
|
; NONEON-LABEL: store_factor4:
|
|
; NONEON-NOT: st4
|
|
define void @store_factor4(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
|
|
%base = bitcast i32* %ptr to <16 x i32>*
|
|
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%v2_v3 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_v3, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
|
|
store <16 x i32> %interleaved.vec, <16 x i32>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; The following cases test that interleaved access of pointer vectors can be
|
|
; matched to ldN/stN instruction.
|
|
|
|
; NEON-LABEL: load_ptrvec_factor2:
|
|
; NEON: ld2 { v0.2d, v1.2d }, [x0]
|
|
; NONEON-LABEL: load_ptrvec_factor2:
|
|
; NONEON-NOT: ld2
|
|
define <2 x i32*> @load_ptrvec_factor2(i32** %ptr) {
|
|
%base = bitcast i32** %ptr to <4 x i32*>*
|
|
%wide.vec = load <4 x i32*>, <4 x i32*>* %base, align 4
|
|
%strided.v0 = shufflevector <4 x i32*> %wide.vec, <4 x i32*> undef, <2 x i32> <i32 0, i32 2>
|
|
ret <2 x i32*> %strided.v0
|
|
}
|
|
|
|
; NEON-LABEL: load_ptrvec_factor3:
|
|
; NEON: ld3 { v0.2d, v1.2d, v2.2d }, [x0]
|
|
; NONEON-LABEL: load_ptrvec_factor3:
|
|
; NONEON-NOT: ld3
|
|
define void @load_ptrvec_factor3(i32** %ptr, <2 x i32*>* %ptr1, <2 x i32*>* %ptr2) {
|
|
%base = bitcast i32** %ptr to <6 x i32*>*
|
|
%wide.vec = load <6 x i32*>, <6 x i32*>* %base, align 4
|
|
%strided.v2 = shufflevector <6 x i32*> %wide.vec, <6 x i32*> undef, <2 x i32> <i32 2, i32 5>
|
|
store <2 x i32*> %strided.v2, <2 x i32*>* %ptr1
|
|
%strided.v1 = shufflevector <6 x i32*> %wide.vec, <6 x i32*> undef, <2 x i32> <i32 1, i32 4>
|
|
store <2 x i32*> %strided.v1, <2 x i32*>* %ptr2
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: load_ptrvec_factor4:
|
|
; NEON: ld4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
|
|
; NONEON-LABEL: load_ptrvec_factor4:
|
|
; NONEON-NOT: ld4
|
|
define void @load_ptrvec_factor4(i32** %ptr, <2 x i32*>* %ptr1, <2 x i32*>* %ptr2) {
|
|
%base = bitcast i32** %ptr to <8 x i32*>*
|
|
%wide.vec = load <8 x i32*>, <8 x i32*>* %base, align 4
|
|
%strided.v1 = shufflevector <8 x i32*> %wide.vec, <8 x i32*> undef, <2 x i32> <i32 1, i32 5>
|
|
%strided.v3 = shufflevector <8 x i32*> %wide.vec, <8 x i32*> undef, <2 x i32> <i32 3, i32 7>
|
|
store <2 x i32*> %strided.v1, <2 x i32*>* %ptr1
|
|
store <2 x i32*> %strided.v3, <2 x i32*>* %ptr2
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_ptrvec_factor2:
|
|
; NEON: st2 { v0.2d, v1.2d }, [x0]
|
|
; NONEON-LABEL: store_ptrvec_factor2:
|
|
; NONEON-NOT: st2
|
|
define void @store_ptrvec_factor2(i32** %ptr, <2 x i32*> %v0, <2 x i32*> %v1) {
|
|
%base = bitcast i32** %ptr to <4 x i32*>*
|
|
%interleaved.vec = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
|
|
store <4 x i32*> %interleaved.vec, <4 x i32*>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_ptrvec_factor3:
|
|
; NEON: st3 { v0.2d, v1.2d, v2.2d }, [x0]
|
|
; NONEON-LABEL: store_ptrvec_factor3:
|
|
; NONEON-NOT: st3
|
|
define void @store_ptrvec_factor3(i32** %ptr, <2 x i32*> %v0, <2 x i32*> %v1, <2 x i32*> %v2) {
|
|
%base = bitcast i32** %ptr to <6 x i32*>*
|
|
%v0_v1 = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%v2_u = shufflevector <2 x i32*> %v2, <2 x i32*> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
|
|
%interleaved.vec = shufflevector <4 x i32*> %v0_v1, <4 x i32*> %v2_u, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>
|
|
store <6 x i32*> %interleaved.vec, <6 x i32*>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_ptrvec_factor4:
|
|
; NEON: st4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
|
|
; NONEON-LABEL: store_ptrvec_factor4:
|
|
; NONEON-NOT: st4
|
|
define void @store_ptrvec_factor4(i32* %ptr, <2 x i32*> %v0, <2 x i32*> %v1, <2 x i32*> %v2, <2 x i32*> %v3) {
|
|
%base = bitcast i32* %ptr to <8 x i32*>*
|
|
%v0_v1 = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%v2_v3 = shufflevector <2 x i32*> %v2, <2 x i32*> %v3, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%interleaved.vec = shufflevector <4 x i32*> %v0_v1, <4 x i32*> %v2_v3, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
|
|
store <8 x i32*> %interleaved.vec, <8 x i32*>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; Following cases check that shuffle maskes with undef indices can be matched
|
|
; into ldN/stN instruction.
|
|
|
|
; NEON-LABEL: load_undef_mask_factor2:
|
|
; NEON: ld2 { v0.4s, v1.4s }, [x0]
|
|
; NONEON-LABEL: load_undef_mask_factor2:
|
|
; NONEON-NOT: ld2
|
|
define <4 x i32> @load_undef_mask_factor2(i32* %ptr) {
|
|
%base = bitcast i32* %ptr to <8 x i32>*
|
|
%wide.vec = load <8 x i32>, <8 x i32>* %base, align 4
|
|
%strided.v0 = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 undef, i32 2, i32 undef, i32 6>
|
|
%strided.v1 = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 undef, i32 3, i32 undef, i32 7>
|
|
%add = add nsw <4 x i32> %strided.v0, %strided.v1
|
|
ret <4 x i32> %add
|
|
}
|
|
|
|
; NEON-LABEL: load_undef_mask_factor3:
|
|
; NEON: ld3 { v0.4s, v1.4s, v2.4s }, [x0]
|
|
; NONEON-LABEL: load_undef_mask_factor3:
|
|
; NONEON-NOT: ld3
|
|
define <4 x i32> @load_undef_mask_factor3(i32* %ptr) {
|
|
%base = bitcast i32* %ptr to <12 x i32>*
|
|
%wide.vec = load <12 x i32>, <12 x i32>* %base, align 4
|
|
%strided.v2 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
|
|
%strided.v1 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
|
|
%add = add nsw <4 x i32> %strided.v2, %strided.v1
|
|
ret <4 x i32> %add
|
|
}
|
|
|
|
; NEON-LABEL: load_undef_mask_factor4:
|
|
; NEON: ld4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
|
|
; NONEON-LABEL: load_undef_mask_factor4:
|
|
; NONEON-NOT: ld4
|
|
define <4 x i32> @load_undef_mask_factor4(i32* %ptr) {
|
|
%base = bitcast i32* %ptr to <16 x i32>*
|
|
%wide.vec = load <16 x i32>, <16 x i32>* %base, align 4
|
|
%strided.v0 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 undef, i32 undef>
|
|
%strided.v2 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 undef, i32 undef>
|
|
%add = add nsw <4 x i32> %strided.v0, %strided.v2
|
|
ret <4 x i32> %add
|
|
}
|
|
|
|
; NEON-LABEL: store_undef_mask_factor2:
|
|
; NEON: st2 { v0.4s, v1.4s }, [x0]
|
|
; NONEON-LABEL: store_undef_mask_factor2:
|
|
; NONEON-NOT: st2
|
|
define void @store_undef_mask_factor2(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1) {
|
|
%base = bitcast i32* %ptr to <8 x i32>*
|
|
%interleaved.vec = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 6, i32 3, i32 7>
|
|
store <8 x i32> %interleaved.vec, <8 x i32>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_undef_mask_factor3:
|
|
; NEON: st3 { v0.4s, v1.4s, v2.4s }, [x0]
|
|
; NONEON-LABEL: store_undef_mask_factor3:
|
|
; NONEON-NOT: st3
|
|
define void @store_undef_mask_factor3(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
|
|
%base = bitcast i32* %ptr to <12 x i32>*
|
|
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%v2_u = shufflevector <4 x i32> %v2, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
|
|
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_u, <12 x i32> <i32 0, i32 4, i32 undef, i32 1, i32 undef, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
|
|
store <12 x i32> %interleaved.vec, <12 x i32>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: store_undef_mask_factor4:
|
|
; NEON: st4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
|
|
; NONEON-LABEL: store_undef_mask_factor4:
|
|
; NONEON-NOT: st4
|
|
define void @store_undef_mask_factor4(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
|
|
%base = bitcast i32* %ptr to <16 x i32>*
|
|
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%v2_v3 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_v3, <16 x i32> <i32 0, i32 4, i32 8, i32 undef, i32 undef, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
|
|
store <16 x i32> %interleaved.vec, <16 x i32>* %base, align 4
|
|
ret void
|
|
}
|
|
|
|
; Check that we do something sane with illegal types.
|
|
|
|
; NEON-LABEL: load_illegal_factor2:
|
|
; NEON: BB#0:
|
|
; NEON-NEXT: ldr q[[V:[0-9]+]], [x0]
|
|
; NEON-NEXT: uzp1 v0.4s, v[[V]].4s, v{{.*}}.4s
|
|
; NEON-NEXT: ret
|
|
; NONEON-LABEL: load_illegal_factor2:
|
|
; NONEON: BB#0:
|
|
; NONEON-NEXT: ldr s0, [x0]
|
|
; NONEON-NEXT: ldr s1, [x0, #8]
|
|
; NONEON-NEXT: ret
|
|
define <3 x float> @load_illegal_factor2(<3 x float>* %p) nounwind {
|
|
%tmp1 = load <3 x float>, <3 x float>* %p, align 16
|
|
%tmp2 = shufflevector <3 x float> %tmp1, <3 x float> undef, <3 x i32> <i32 0, i32 2, i32 undef>
|
|
ret <3 x float> %tmp2
|
|
}
|
|
|
|
; NEON-LABEL: store_illegal_factor2:
|
|
; NEON: BB#0:
|
|
; NEON-NEXT: uzp1 v0.4s, v0.4s, v{{.*}}.4s
|
|
; NEON-NEXT: st1 { v0.d }[0], [x0]
|
|
; NEON-NEXT: ret
|
|
; NONEON-LABEL: store_illegal_factor2:
|
|
; NONEON: BB#0:
|
|
; NONEON-NEXT: fmov w[[ELT2:[0-9]+]], s2
|
|
; NONEON-NEXT: fmov w[[RES:[0-9]+]], s0
|
|
; NONEON-NEXT: bfi x[[RES]], x[[ELT2]], #32, #32
|
|
; NONEON-NEXT: str x[[RES]], [x0]
|
|
; NONEON-NEXT: ret
|
|
define void @store_illegal_factor2(<3 x float>* %p, <3 x float> %v) nounwind {
|
|
%tmp1 = shufflevector <3 x float> %v, <3 x float> undef, <3 x i32> <i32 0, i32 2, i32 undef>
|
|
store <3 x float> %tmp1, <3 x float>* %p, align 16
|
|
ret void
|
|
}
|
|
|
|
; NEON-LABEL: load_factor2_with_extract_user:
|
|
; NEON: ld2 { v0.4s, v1.4s }, [x0]
|
|
; NEON: mov w0, v0.s[1]
|
|
; NONEON-LABEL: load_factor2_with_extract_user:
|
|
; NONEON-NOT: ld2
|
|
define i32 @load_factor2_with_extract_user(<8 x i32>* %a) {
|
|
%1 = load <8 x i32>, <8 x i32>* %a, align 8
|
|
%2 = shufflevector <8 x i32> %1, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%3 = extractelement <8 x i32> %1, i32 2
|
|
ret i32 %3
|
|
}
|