This is an archive of the discontinued LLVM Phabricator instance.

Differential D153863

[RISCV] Add tests for stores of vector.interleave2
ClosedPublic

Authored by luke on Jun 27 2023, 5:48 AM.

Details

Reviewers
craig.topper
reames
kito-cheng
CarolineConcatto
Commits
rGd914686da25d: [RISCV] Add tests for stores of vector.interleave2

Diff Detail

Event Timeline

luke created this revision.Jun 27 2023, 5:48 AM
Herald added a project: Restricted Project. · View Herald TranscriptJun 27 2023, 5:48 AM
Herald added subscribers: jobnoorman, asb, pmatos and 26 others. · View Herald Transcript
luke requested review of this revision.Jun 27 2023, 5:48 AM
Herald added a project: Restricted Project. · View Herald TranscriptJun 27 2023, 5:48 AM
Herald added subscribers: llvm-commits, wangpc, eopXD, MaskRay. · View Herald Transcript
luke added a child revision: D153864: [RISCV] Lower interleave2 intrinsics to vsseg2.Jun 27 2023, 5:52 AM
luke updated this revision to Diff 534956.Jun 27 2023, 6:43 AM

Rename fixed vector test file to be more consistent with other tests

luke updated this revision to Diff 534973.Jun 27 2023, 7:28 AM

Add test for LMUL=4

Harbormaster completed remote builds in B241479: Diff 534973.Jun 27 2023, 8:31 AM
craig.topper added inline comments.Jun 27 2023, 9:52 AM
llvm/test/CodeGen/RISCV/rvv/fixed-vector-interleave-store.ll
27

IR is typically indented 2 spaces I think.

63

Missing CHECK lines

151

Missing CHECK lines

luke updated this revision to Diff 535039.Jun 27 2023, 10:07 AM

Fix indentation and missing check lines

craig.topper accepted this revision.Jun 27 2023, 10:31 AM

LGTM

This revision is now accepted and ready to land.Jun 27 2023, 10:31 AM
Harbormaster completed remote builds in B241530: Diff 535039.Jun 27 2023, 12:24 PM
Closed by commit rGd914686da25d: [RISCV] Add tests for stores of vector.interleave2 (authored by luke). · Explain WhyJul 5 2023, 11:24 AM
This revision was automatically updated to reflect the committed changes.
luke added a commit: rGd914686da25d: [RISCV] Add tests for stores of vector.interleave2.

Revision Contents

PathSize
llvm/
test/
CodeGen/
RISCV/
rvv/
207 lines
271 lines

Diff 535039

llvm/test/CodeGen/RISCV/rvv/fixed-vector-interleave-store.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s -check-prefixes=CHECK,RV32
; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s -check-prefixes=CHECK,RV64
; Integers
define void @vector_interleave_store_v32i1_v16i1(<16 x i1> %a, <16 x i1> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v32i1_v16i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vslideup.vi v0, v8, 2
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
; CHECK-NEXT: vsetivli zero, 16, e8, m2, ta, ma
; CHECK-NEXT: vslidedown.vi v10, v8, 16
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v12, v8, v10
; CHECK-NEXT: li a2, -1
; CHECK-NEXT: vwmaccu.vx v12, a2, v10
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, ma
; CHECK-NEXT: vmsne.vi v8, v12, 0
; CHECK-NEXT: vsm.v v8, (a0)
; CHECK-NEXT: ret
%res = call <32 x i1> @llvm.experimental.vector.interleave2.v32i1(<16 x i1> %a, <16 x i1> %b)
store <32 x i1> %res, ptr %p
craig.topperUnsubmitted
Not Done
ReplyInline Actions

IR is typically indented 2 spaces I think.

craig.topper: IR is typically indented 2 spaces I think.
ret void
}
define void @vector_interleave_store_v16i16_v8i16(<8 x i16> %a, <8 x i16> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v16i16_v8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma
; CHECK-NEXT: vse16.v v10, (a0)
; CHECK-NEXT: ret
%res = call <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16> %a, <8 x i16> %b)
store <16 x i16> %res, ptr %p
ret void
}
define void @vector_interleave_store_v8i32_v4i32(<4 x i32> %a, <4 x i32> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v8i32_v4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT: vse32.v v10, (a0)
; CHECK-NEXT: ret
%res = call <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32> %a, <4 x i32> %b)
store <8 x i32> %res, ptr %p
ret void
}
define void @vector_interleave_store_v4i64_v2i64(<2 x i64> %a, <2 x i64> %b, ptr %p) {
; RV32-LABEL: vector_interleave_store_v4i64_v2i64:
; RV32: # %bb.0:
craig.topperUnsubmitted
Not Done
ReplyInline Actions

Missing CHECK lines

craig.topper: Missing CHECK lines
; RV32-NEXT: vmv1r.v v10, v9
; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; RV32-NEXT: lui a1, %hi(.LCPI3_0)
; RV32-NEXT: addi a1, a1, %lo(.LCPI3_0)
; RV32-NEXT: vle16.v v12, (a1)
; RV32-NEXT: vslideup.vi v8, v10, 2
; RV32-NEXT: vrgatherei16.vv v10, v8, v12
; RV32-NEXT: vse64.v v10, (a0)
; RV32-NEXT: ret
;
; RV64-LABEL: vector_interleave_store_v4i64_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v10, v9
; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; RV64-NEXT: lui a1, %hi(.LCPI3_0)
; RV64-NEXT: addi a1, a1, %lo(.LCPI3_0)
; RV64-NEXT: vle64.v v12, (a1)
; RV64-NEXT: vslideup.vi v8, v10, 2
; RV64-NEXT: vrgather.vv v10, v8, v12
; RV64-NEXT: vse64.v v10, (a0)
; RV64-NEXT: ret
%res = call <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64> %a, <2 x i64> %b)
store <4 x i64> %res, ptr %p
ret void
}
declare <32 x i1> @llvm.experimental.vector.interleave2.v32i1(<16 x i1>, <16 x i1>)
declare <16 x i16> @llvm.experimental.vector.interleave2.v16i16(<8 x i16>, <8 x i16>)
declare <8 x i32> @llvm.experimental.vector.interleave2.v8i32(<4 x i32>, <4 x i32>)
declare <4 x i64> @llvm.experimental.vector.interleave2.v4i64(<2 x i64>, <2 x i64>)
; Floats
define void @vector_interleave_store_v4f16_v2f16(<2 x half> %a, <2 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v4f16_v2f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vse16.v v10, (a0)
; CHECK-NEXT: ret
%res = call <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half> %a, <2 x half> %b)
store <4 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_v8f16_v4f16(<4 x half> %a, <4 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v8f16_v4f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vse16.v v10, (a0)
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half> %a, <4 x half> %b)
store <8 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_v4f32_v2f32(<2 x float> %a, <2 x float> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v4f32_v2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vse32.v v10, (a0)
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.experimental.vector.interleave2.v4f32(<2 x float> %a, <2 x float> %b)
store <4 x float> %res, ptr %p
ret void
}
define void @vector_interleave_store_v16f16_v8f16(<8 x half> %a, <8 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v16f16_v8f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, ma
; CHECK-NEXT: vse16.v v10, (a0)
; CHECK-NEXT: ret
craig.topperUnsubmitted
Not Done
ReplyInline Actions

Missing CHECK lines

craig.topper: Missing CHECK lines
%res = call <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half> %a, <8 x half> %b)
store <16 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_v8f32_v4f32(<4 x float> %a, <4 x float> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_v8f32_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT: vse32.v v10, (a0)
; CHECK-NEXT: ret
%res = call <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float> %a, <4 x float> %b)
store <8 x float> %res, ptr %p
ret void
}
define void @vector_interleave_store_v4f64_v2f64(<2 x double> %a, <2 x double> %b, ptr %p) {
; RV32-LABEL: vector_interleave_store_v4f64_v2f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v10, v9
; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; RV32-NEXT: lui a1, %hi(.LCPI9_0)
; RV32-NEXT: addi a1, a1, %lo(.LCPI9_0)
; RV32-NEXT: vle16.v v12, (a1)
; RV32-NEXT: vslideup.vi v8, v10, 2
; RV32-NEXT: vrgatherei16.vv v10, v8, v12
; RV32-NEXT: vse64.v v10, (a0)
; RV32-NEXT: ret
;
; RV64-LABEL: vector_interleave_store_v4f64_v2f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v10, v9
; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; RV64-NEXT: lui a1, %hi(.LCPI9_0)
; RV64-NEXT: addi a1, a1, %lo(.LCPI9_0)
; RV64-NEXT: vle64.v v12, (a1)
; RV64-NEXT: vslideup.vi v8, v10, 2
; RV64-NEXT: vrgather.vv v10, v8, v12
; RV64-NEXT: vse64.v v10, (a0)
; RV64-NEXT: ret
%res = call <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double> %a, <2 x double> %b)
store <4 x double> %res, ptr %p
ret void
}
declare <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half>, <2 x half>)
declare <8 x half> @llvm.experimental.vector.interleave2.v8f16(<4 x half>, <4 x half>)
declare <4 x float> @llvm.experimental.vector.interleave2.v4f32(<2 x float>, <2 x float>)
declare <16 x half> @llvm.experimental.vector.interleave2.v16f16(<8 x half>, <8 x half>)
declare <8 x float> @llvm.experimental.vector.interleave2.v8f32(<4 x float>, <4 x float>)
declare <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double>, <2 x double>)

llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll

  • This file was added.
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s
; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zfh,+experimental-zvfh | FileCheck %s
; Integers
define void @vector_interleave_store_nxv32i1_nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv32i1_nxv16i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vmv1r.v v9, v0
; CHECK-NEXT: vsetvli a1, zero, e8, m2, ta, ma
; CHECK-NEXT: vmv.v.i v10, 0
; CHECK-NEXT: vmv1r.v v0, v8
; CHECK-NEXT: vmerge.vim v12, v10, 1, v0
; CHECK-NEXT: vmv1r.v v0, v9
; CHECK-NEXT: vmerge.vim v8, v10, 1, v0
; CHECK-NEXT: vwaddu.vv v16, v8, v12
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v16, a1, v12
; CHECK-NEXT: vmsne.vi v8, v18, 0
; CHECK-NEXT: vmsne.vi v9, v16, 0
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: add a2, a1, a1
; CHECK-NEXT: vsetvli zero, a2, e8, mf2, tu, ma
; CHECK-NEXT: vslideup.vx v9, v8, a1
; CHECK-NEXT: vsetvli a1, zero, e8, m4, ta, ma
; CHECK-NEXT: vsm.v v9, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 32 x i1> @llvm.experimental.vector.interleave2.nxv32i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b)
store <vscale x 32 x i1> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv16i16_nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv16i16_nxv8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT: vwaddu.vv v12, v8, v10
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v12, a1, v10
; CHECK-NEXT: vs4r.v v12, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 16 x i16> @llvm.experimental.vector.interleave2.nxv16i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
store <vscale x 16 x i16> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv8i32_nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv8i32_nxv4i32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma
; CHECK-NEXT: vwaddu.vv v12, v8, v10
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v12, a1, v10
; CHECK-NEXT: vs4r.v v12, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 8 x i32> @llvm.experimental.vector.interleave2.nxv8i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
store <vscale x 8 x i32> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv4i64_nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv4i64_nxv2i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, mu
; CHECK-NEXT: vid.v v12
; CHECK-NEXT: vsrl.vi v13, v12, 1
; CHECK-NEXT: vand.vi v12, v12, 1
; CHECK-NEXT: vmsne.vi v0, v12, 0
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: vadd.vx v13, v13, a1, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, ma
; CHECK-NEXT: vrgatherei16.vv v16, v8, v13
; CHECK-NEXT: vs4r.v v16, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 4 x i64> @llvm.experimental.vector.interleave2.nxv4i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
store <vscale x 4 x i64> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv8i64_nxv4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv8i64_nxv4i64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, mu
; CHECK-NEXT: vid.v v16
; CHECK-NEXT: vand.vi v18, v16, 1
; CHECK-NEXT: vmsne.vi v0, v18, 0
; CHECK-NEXT: vsrl.vi v16, v16, 1
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 1
; CHECK-NEXT: vadd.vx v16, v16, a1, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; CHECK-NEXT: vrgatherei16.vv v24, v8, v16
; CHECK-NEXT: vs8r.v v24, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 8 x i64> @llvm.experimental.vector.interleave2.nxv8i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b)
store <vscale x 8 x i64> %res, ptr %p
ret void
}
; This shouldn't be lowered to a vsseg because EMUL * NFIELDS >= 8
define void @vector_interleave_store_nxv16i64_nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv16i64_nxv8i64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: sub sp, sp, a1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, mu
; CHECK-NEXT: vid.v v24
; CHECK-NEXT: vsrl.vi v2, v24, 1
; CHECK-NEXT: vand.vi v24, v24, 1
; CHECK-NEXT: vmsne.vi v0, v24, 0
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a2, a1, 1
; CHECK-NEXT: csrr a3, vlenb
; CHECK-NEXT: slli a3, a3, 3
; CHECK-NEXT: add a3, sp, a3
; CHECK-NEXT: addi a3, a3, 16
; CHECK-NEXT: vl8r.v v8, (a3) # Unknown-size Folded Reload
; CHECK-NEXT: vadd.vx v2, v2, a2, v0.t
; CHECK-NEXT: vmv4r.v v12, v16
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma
; CHECK-NEXT: vrgatherei16.vv v24, v8, v2
; CHECK-NEXT: addi a2, sp, 16
; CHECK-NEXT: vs8r.v v24, (a2) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: slli a2, a2, 3
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
; CHECK-NEXT: vl8r.v v8, (a2) # Unknown-size Folded Reload
; CHECK-NEXT: vmv4r.v v16, v12
; CHECK-NEXT: vrgatherei16.vv v8, v16, v2
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, a0, a1
; CHECK-NEXT: vs8r.v v8, (a1)
; CHECK-NEXT: addi a1, sp, 16
; CHECK-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vs8r.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%res = call <vscale x 16 x i64> @llvm.experimental.vector.interleave2.nxv16i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b)
store <vscale x 16 x i64> %res, ptr %p
ret void
}
declare <vscale x 32 x i1> @llvm.experimental.vector.interleave2.nxv32i1(<vscale x 16 x i1>, <vscale x 16 x i1>)
declare <vscale x 16 x i16> @llvm.experimental.vector.interleave2.nxv16i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 8 x i32> @llvm.experimental.vector.interleave2.nxv8i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 4 x i64> @llvm.experimental.vector.interleave2.nxv4i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 8 x i64> @llvm.experimental.vector.interleave2.nxv8i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
declare <vscale x 16 x i64> @llvm.experimental.vector.interleave2.nxv16i64(<vscale x 8 x i64>, <vscale x 8 x i64>)
; Floats
define void @vector_interleave_store_nxv4f16_nxv2f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv4f16_nxv2f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: vsetvli a2, zero, e16, m1, ta, ma
; CHECK-NEXT: vslidedown.vx v8, v10, a1
; CHECK-NEXT: add a2, a1, a1
; CHECK-NEXT: vsetvli zero, a2, e16, m1, tu, ma
; CHECK-NEXT: vslideup.vx v10, v8, a1
; CHECK-NEXT: vs1r.v v10, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.experimental.vector.interleave2.nxv4f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b)
store <vscale x 4 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv8f16_nxv4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv8f16_nxv4f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vs2r.v v10, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.experimental.vector.interleave2.nxv8f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b)
store <vscale x 8 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv4f32_nxv2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv4f32_nxv2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, ma
; CHECK-NEXT: vwaddu.vv v10, v8, v9
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v10, a1, v9
; CHECK-NEXT: vs2r.v v10, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.experimental.vector.interleave2.nxv4f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b)
store <vscale x 4 x float> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv16f16_nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv16f16_nxv8f16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT: vwaddu.vv v12, v8, v10
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v12, a1, v10
; CHECK-NEXT: vs4r.v v12, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 16 x half> @llvm.experimental.vector.interleave2.nxv16f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b)
store <vscale x 16 x half> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv8f32_nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv8f32_nxv4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma
; CHECK-NEXT: vwaddu.vv v12, v8, v10
; CHECK-NEXT: li a1, -1
; CHECK-NEXT: vwmaccu.vx v12, a1, v10
; CHECK-NEXT: vs4r.v v12, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 8 x float> @llvm.experimental.vector.interleave2.nxv8f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b)
store <vscale x 8 x float> %res, ptr %p
ret void
}
define void @vector_interleave_store_nxv4f64_nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, ptr %p) {
; CHECK-LABEL: vector_interleave_store_nxv4f64_nxv2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e16, m1, ta, mu
; CHECK-NEXT: vid.v v12
; CHECK-NEXT: vsrl.vi v13, v12, 1
; CHECK-NEXT: vand.vi v12, v12, 1
; CHECK-NEXT: vmsne.vi v0, v12, 0
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a1, a1, 2
; CHECK-NEXT: vadd.vx v13, v13, a1, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, ma
; CHECK-NEXT: vrgatherei16.vv v16, v8, v13
; CHECK-NEXT: vs4r.v v16, (a0)
; CHECK-NEXT: ret
%res = call <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b)
store <vscale x 4 x double> %res, ptr %p
ret void
}
declare <vscale x 4 x half> @llvm.experimental.vector.interleave2.nxv4f16(<vscale x 2 x half>, <vscale x 2 x half>)
declare <vscale x 8 x half> @llvm.experimental.vector.interleave2.nxv8f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 4 x float> @llvm.experimental.vector.interleave2.nxv4f32(<vscale x 2 x float>, <vscale x 2 x float>)
declare <vscale x 16 x half> @llvm.experimental.vector.interleave2.nxv16f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x float> @llvm.experimental.vector.interleave2.nxv8f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x double> @llvm.experimental.vector.interleave2.nxv4f64(<vscale x 2 x double>, <vscale x 2 x double>)