6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-08-21 18:29:46 +00:00
Code Issues Projects Releases Wiki Activity
a6367d9136
llvm-6502/test/CodeGen/ARM/arm-interleaved-accesses.ll
Hao Liu 5be64c403b [ARM] Lower interleaved memory accesses to vldN/vstN intrinsics. 
This patch also adds a function to calculate the cost of interleaved memory accesses.

E.g. Lower an interleaved load:
        %wide.vec = load <8 x i32>, <8 x i32>* %ptr, align 4
        %v0 = shuffle %wide.vec, undef, <0, 2, 4, 6>
        %v1 = shuffle %wide.vec, undef, <1, 3, 5, 7>
     into:
        %vld2 = { <4 x i32>, <4 x i32> } call llvm.arm.neon.vld2(%ptr, 4)
        %vec0 = extractelement { <4 x i32>, <4 x i32> } %vld2, i32 0
        %vec1 = extractelement { <4 x i32>, <4 x i32> } %vld2, i32 1

E.g. Lower an interleaved store:
        %i.vec = shuffle <8 x i32> %v0, <8 x i32> %v1, <0, 4, 8, 1, 5, 9, 2, 6, 10, 3, 7, 11>
        store <12 x i32> %i.vec, <12 x i32>* %ptr, align 4
     into:
        %sub.v0 = shuffle <8 x i32> %v0, <8 x i32> v1, <0, 1, 2, 3>
        %sub.v1 = shuffle <8 x i32> %v0, <8 x i32> v1, <4, 5, 6, 7>
        %sub.v2 = shuffle <8 x i32> %v0, <8 x i32> v1, <8, 9, 10, 11>
        call void llvm.arm.neon.vst3(%ptr, %sub.v0, %sub.v1, %sub.v2, 4)

Differential Revision: http://reviews.llvm.org/D10533


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240755 91177308-0d34-0410-b5e6-96231b3b80d8
2015-06-26 02:45:36 +00:00

205 lines
10 KiB
LLVM
Raw Blame History

; RUN: llc -mtriple=arm-eabi -mattr=+neon -lower-interleaved-accesses=true < %s | FileCheck %s
; CHECK-LABEL: load_factor2:
; CHECK: vld2.8 {d16, d17}, [r0]
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
}
; CHECK-LABEL: load_factor3:
; CHECK: vld3.32 {d16, d17, d18}, [r0]
define <2 x i32> @load_factor3(i32* %ptr) {
%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>
%strided.v1 = shufflevector <6 x i32> %wide.vec, <6 x i32> undef, <2 x i32> <i32 1, i32 4>
%add = add nsw <2 x i32> %strided.v2, %strided.v1
ret <2 x i32> %add
}
; CHECK-LABEL: load_factor4:
; CHECK: vld4.32 {d16, d18, d20, d22}, [r0]!
; CHECK: vld4.32 {d17, d19, d21, d23}, [r0]
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
}
; CHECK-LABEL: store_factor2:
; CHECK: vst2.8 {d16, d17}, [r0]
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
}
; CHECK-LABEL: store_factor3:
; CHECK: vst3.32 {d16, d18, d20}, [r0]!
; CHECK: vst3.32 {d17, d19, d21}, [r0]
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
}
; CHECK-LABEL: store_factor4:
; CHECK: vst4.32 {d16, d18, d20, d22}, [r0]!
; CHECK: vst4.32 {d17, d19, d21, d23}, [r0]
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.
; CHECK-LABEL: load_ptrvec_factor2:
; CHECK: vld2.32 {d16, d17}, [r0]
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
}
; CHECK-LABEL: load_ptrvec_factor3:
; CHECK: vld3.32 {d16, d17, d18}, [r0]
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
}
; CHECK-LABEL: load_ptrvec_factor4:
; CHECK: vld4.32 {d16, d17, d18, d19}, [r0]
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
}
; CHECK-LABEL: store_ptrvec_factor2:
; CHECK: vst2.32 {d16, d17}, [r0]
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
}
; CHECK-LABEL: store_ptrvec_factor3:
; CHECK: vst3.32 {d16, d17, d18}, [r0]
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
}
; CHECK-LABEL: store_ptrvec_factor4:
; CHECK: vst4.32 {d16, d17, d18, d19}, [r0]
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.
; CHECK-LABEL: load_undef_mask_factor2:
; CHECK: vld2.32 {d16, d17, d18, d19}, [r0]
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
}
; CHECK-LABEL: load_undef_mask_factor3:
; CHECK: vld3.32 {d16, d18, d20}, [r0]!
; CHECK: vld3.32 {d17, d19, d21}, [r0]
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
}
; CHECK-LABEL: load_undef_mask_factor4:
; CHECK: vld4.32 {d16, d18, d20, d22}, [r0]!
; CHECK: vld4.32 {d17, d19, d21, d23}, [r0]
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
}
; CHECK-LABEL: store_undef_mask_factor2:
; CHECK: vst2.32 {d16, d17, d18, d19}, [r0]
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
}
; CHECK-LABEL: store_undef_mask_factor3:
; CHECK: vst3.32 {d16, d18, d20}, [r0]!
; CHECK: vst3.32 {d17, d19, d21}, [r0]
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
}
; CHECK-LABEL: store_undef_mask_factor4:
; CHECK: vst4.32 {d16, d18, d20, d22}, [r0]!
; CHECK: vst4.32 {d17, d19, d21, d23}, [r0]
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
}
Reference in New Issue View Git Blame Copy Permalink