; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -riscv-v-vector-bits-min=128 \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV32
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -riscv-v-vector-bits-min=128 \
; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=RV64
declare <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*>, <2 x i1>, i32)
define <2 x i8> @vpgather_v2i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x i8> %v
}
define <2 x i16> @vpgather_v2i8_sextload_v2i16(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_sextload_v2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; RV32-NEXT: vsext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_sextload_v2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; RV64-NEXT: vsext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i8> %v to <2 x i16>
ret <2 x i16> %ev
}
define <2 x i16> @vpgather_v2i8_zextload_v2i16(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_zextload_v2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; RV32-NEXT: vzext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_zextload_v2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; RV64-NEXT: vzext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i8> %v to <2 x i16>
ret <2 x i16> %ev
}
define <2 x i32> @vpgather_v2i8_sextload_v2i32(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_sextload_v2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV32-NEXT: vsext.vf4 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_sextload_v2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV64-NEXT: vsext.vf4 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i8> %v to <2 x i32>
ret <2 x i32> %ev
}
define <2 x i32> @vpgather_v2i8_zextload_v2i32(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_zextload_v2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV32-NEXT: vzext.vf4 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_zextload_v2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV64-NEXT: vzext.vf4 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i8> %v to <2 x i32>
ret <2 x i32> %ev
}
define <2 x i64> @vpgather_v2i8_sextload_v2i64(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_sextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vsext.vf8 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_sextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vsext.vf8 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i8> %v to <2 x i64>
ret <2 x i64> %ev
}
define <2 x i64> @vpgather_v2i8_zextload_v2i64(<2 x i8*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i8_zextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vzext.vf8 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i8_zextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf8, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vzext.vf8 v8, v9
; RV64-NEXT: ret
%v = call <2 x i8> @llvm.vp.gather.v2i8.v2p0i8(<2 x i8*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i8> %v to <2 x i64>
ret <2 x i64> %ev
}
declare <3 x i8> @llvm.vp.gather.v3i8.v3p0i8(<3 x i8*>, <3 x i1>, i32)
define <3 x i8> @vpgather_v3i8(<3 x i8*> %ptrs, <3 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v3i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v3i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%v = call <3 x i8> @llvm.vp.gather.v3i8.v3p0i8(<3 x i8*> %ptrs, <3 x i1> %m, i32 %evl)
ret <3 x i8> %v
}
define <3 x i8> @vpgather_truemask_v3i8(<3 x i8*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v3i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v3i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <3 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <3 x i1> %mhead, <3 x i1> poison, <3 x i32> zeroinitializer
%v = call <3 x i8> @llvm.vp.gather.v3i8.v3p0i8(<3 x i8*> %ptrs, <3 x i1> %mtrue, i32 %evl)
ret <3 x i8> %v
}
declare <4 x i8> @llvm.vp.gather.v4i8.v4p0i8(<4 x i8*>, <4 x i1>, i32)
define <4 x i8> @vpgather_v4i8(<4 x i8*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%v = call <4 x i8> @llvm.vp.gather.v4i8.v4p0i8(<4 x i8*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x i8> %v
}
define <4 x i8> @vpgather_truemask_v4i8(<4 x i8*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf4, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x i8> @llvm.vp.gather.v4i8.v4p0i8(<4 x i8*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x i8> %v
}
declare <8 x i8> @llvm.vp.gather.v8i8.v8p0i8(<8 x i8*>, <8 x i1>, i32)
define <8 x i8> @vpgather_v8i8(<8 x i8*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e8, mf2, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e8, mf2, ta, mu
; RV64-NEXT: vluxei64.v v12, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v12
; RV64-NEXT: ret
%v = call <8 x i8> @llvm.vp.gather.v8i8.v8p0i8(<8 x i8*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i8> %v
}
define <8 x i8> @vpgather_baseidx_v8i8(i8* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsetvli zero, a1, e8, mf2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsetvli zero, a1, e8, mf2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i8, i8* %base, <8 x i8> %idxs
%v = call <8 x i8> @llvm.vp.gather.v8i8.v8p0i8(<8 x i8*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i8> %v
}
declare <32 x i8> @llvm.vp.gather.v32i8.v32p0i8(<32 x i8*>, <32 x i1>, i32)
define <32 x i8> @vpgather_baseidx_v32i8(i8* %base, <32 x i8> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v32i8:
; RV32: # %bb.0:
; RV32-NEXT: li a2, 32
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: vsext.vf4 v16, v8
; RV32-NEXT: vsetvli zero, a1, e8, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v32i8:
; RV64: # %bb.0:
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vmv1r.v v10, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: bltu a1, a3, .LBB13_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB13_2:
; RV64-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV64-NEXT: vslidedown.vi v12, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v10, 2
; RV64-NEXT: vsetvli zero, a2, e8, m1, ta, mu
; RV64-NEXT: vluxei64.v v12, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB13_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB13_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf8 v16, v8
; RV64-NEXT: vsetvli zero, a1, e8, m1, ta, mu
; RV64-NEXT: vmv1r.v v0, v10
; RV64-NEXT: vluxei64.v v8, (a0), v16, v0.t
; RV64-NEXT: li a0, 32
; RV64-NEXT: vsetvli zero, a0, e8, m2, tu, mu
; RV64-NEXT: vslideup.vi v8, v12, 16
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i8, i8* %base, <32 x i8> %idxs
%v = call <32 x i8> @llvm.vp.gather.v32i8.v32p0i8(<32 x i8*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x i8> %v
}
declare <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*>, <2 x i1>, i32)
define <2 x i16> @vpgather_v2i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v9
; RV64-NEXT: ret
%v = call <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x i16> %v
}
define <2 x i32> @vpgather_v2i16_sextload_v2i32(<2 x i16*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i16_sextload_v2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV32-NEXT: vsext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i16_sextload_v2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV64-NEXT: vsext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i16> %v to <2 x i32>
ret <2 x i32> %ev
}
define <2 x i32> @vpgather_v2i16_zextload_v2i32(<2 x i16*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i16_zextload_v2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV32-NEXT: vzext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i16_zextload_v2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; RV64-NEXT: vzext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i16> %v to <2 x i32>
ret <2 x i32> %ev
}
define <2 x i64> @vpgather_v2i16_sextload_v2i64(<2 x i16*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i16_sextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vsext.vf4 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i16_sextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vsext.vf4 v8, v9
; RV64-NEXT: ret
%v = call <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i16> %v to <2 x i64>
ret <2 x i64> %ev
}
define <2 x i64> @vpgather_v2i16_zextload_v2i64(<2 x i16*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i16_zextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vzext.vf4 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i16_zextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vzext.vf4 v8, v9
; RV64-NEXT: ret
%v = call <2 x i16> @llvm.vp.gather.v2i16.v2p0i16(<2 x i16*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i16> %v to <2 x i64>
ret <2 x i64> %ev
}
declare <4 x i16> @llvm.vp.gather.v4i16.v4p0i16(<4 x i16*>, <4 x i1>, i32)
define <4 x i16> @vpgather_v4i16(<4 x i16*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%v = call <4 x i16> @llvm.vp.gather.v4i16.v4p0i16(<4 x i16*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x i16> %v
}
define <4 x i16> @vpgather_truemask_v4i16(<4 x i16*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x i16> @llvm.vp.gather.v4i16.v4p0i16(<4 x i16*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x i16> %v
}
declare <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*>, <8 x i1>, i32)
define <8 x i16> @vpgather_v8i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v12, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v12
; RV64-NEXT: ret
%v = call <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i16> %v
}
define <8 x i16> @vpgather_baseidx_v8i8_v8i16(i16* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i16, i16* %base, <8 x i8> %idxs
%v = call <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i16> %v
}
define <8 x i16> @vpgather_baseidx_sext_v8i8_v8i16(i16* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i16>
%ptrs = getelementptr inbounds i16, i16* %base, <8 x i16> %eidxs
%v = call <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i16> %v
}
define <8 x i16> @vpgather_baseidx_zext_v8i8_v8i16(i16* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i16>
%ptrs = getelementptr inbounds i16, i16* %base, <8 x i16> %eidxs
%v = call <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i16> %v
}
define <8 x i16> @vpgather_baseidx_v8i16(i16* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i16, i16* %base, <8 x i16> %idxs
%v = call <8 x i16> @llvm.vp.gather.v8i16.v8p0i16(<8 x i16*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i16> %v
}
declare <2 x i32> @llvm.vp.gather.v2i32.v2p0i32(<2 x i32*>, <2 x i1>, i32)
define <2 x i32> @vpgather_v2i32(<2 x i32*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v9
; RV64-NEXT: ret
%v = call <2 x i32> @llvm.vp.gather.v2i32.v2p0i32(<2 x i32*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x i32> %v
}
define <2 x i64> @vpgather_v2i32_sextload_v2i64(<2 x i32*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i32_sextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vsext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i32_sextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vsext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i32> @llvm.vp.gather.v2i32.v2p0i32(<2 x i32*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = sext <2 x i32> %v to <2 x i64>
ret <2 x i64> %ev
}
define <2 x i64> @vpgather_v2i32_zextload_v2i64(<2 x i32*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i32_zextload_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT: vzext.vf2 v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i32_zextload_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; RV64-NEXT: vzext.vf2 v8, v9
; RV64-NEXT: ret
%v = call <2 x i32> @llvm.vp.gather.v2i32.v2p0i32(<2 x i32*> %ptrs, <2 x i1> %m, i32 %evl)
%ev = zext <2 x i32> %v to <2 x i64>
ret <2 x i64> %ev
}
declare <4 x i32> @llvm.vp.gather.v4i32.v4p0i32(<4 x i32*>, <4 x i1>, i32)
define <4 x i32> @vpgather_v4i32(<4 x i32*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v10
; RV64-NEXT: ret
%v = call <4 x i32> @llvm.vp.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x i32> %v
}
define <4 x i32> @vpgather_truemask_v4i32(<4 x i32*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv.v.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x i32> @llvm.vp.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x i32> %v
}
declare <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*>, <8 x i1>, i32)
define <8 x i32> @vpgather_v8i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v12, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v12
; RV64-NEXT: ret
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_v8i8_v8i32(i32* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i8> %idxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_sext_v8i8_v8i32(i32* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i32>
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i32> %eidxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_zext_v8i8_v8i32(i32* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i32>
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i32> %eidxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_v8i16_v8i32(i32* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i16_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i16_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i16> %idxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_sext_v8i16_v8i32(i32* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i16_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i16_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i16> %idxs to <8 x i32>
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i32> %eidxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_zext_v8i16_v8i32(i32* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i16_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i16_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i16> %idxs to <8 x i32>
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i32> %eidxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
define <8 x i32> @vpgather_baseidx_v8i32(i32* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsll.vi v8, v8, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i32, i32* %base, <8 x i32> %idxs
%v = call <8 x i32> @llvm.vp.gather.v8i32.v8p0i32(<8 x i32*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i32> %v
}
declare <2 x i64> @llvm.vp.gather.v2i64.v2p0i64(<2 x i64*>, <2 x i1>, i32)
define <2 x i64> @vpgather_v2i64(<2 x i64*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <2 x i64> @llvm.vp.gather.v2i64.v2p0i64(<2 x i64*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x i64> %v
}
declare <4 x i64> @llvm.vp.gather.v4i64.v4p0i64(<4 x i64*>, <4 x i1>, i32)
define <4 x i64> @vpgather_v4i64(<4 x i64*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <4 x i64> @llvm.vp.gather.v4i64.v4p0i64(<4 x i64*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x i64> %v
}
define <4 x i64> @vpgather_truemask_v4i64(<4 x i64*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x i64> @llvm.vp.gather.v4i64.v4p0i64(<4 x i64*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x i64> %v
}
declare <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*>, <8 x i1>, i32)
define <8 x i64> @vpgather_v8i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v12, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v12
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_v8i8_v8i64(i64* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v12, v10, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i8> %idxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_sext_v8i8_v8i64(i64* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf8 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_zext_v8i8_v8i64(i64* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf8 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_v8i16_v8i64(i64* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i16_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v12, v10, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i16_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i16> %idxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_sext_v8i16_v8i64(i64* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i16_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf4 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i16_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i16> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_zext_v8i16_v8i64(i64* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i16_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf4 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i16_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i16> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_v8i32_v8i64(i64* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i32_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsll.vi v12, v8, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i32_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i32> %idxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_sext_v8i32_v8i64(i64* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i32_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf2 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i32_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i32> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_zext_v8i32_v8i64(i64* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i32_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf2 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i32_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i32> %idxs to <8 x i64>
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %eidxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
define <8 x i64> @vpgather_baseidx_v8i64(i64* %base, <8 x i64> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsll.vi v8, v8, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsll.vi v8, v8, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds i64, i64* %base, <8 x i64> %idxs
%v = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x i64> %v
}
declare <2 x half> @llvm.vp.gather.v2f16.v2p0f16(<2 x half*>, <2 x i1>, i32)
define <2 x half> @vpgather_v2f16(<2 x half*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v9
; RV64-NEXT: ret
%v = call <2 x half> @llvm.vp.gather.v2f16.v2p0f16(<2 x half*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x half> %v
}
declare <4 x half> @llvm.vp.gather.v4f16.v4p0f16(<4 x half*>, <4 x i1>, i32)
define <4 x half> @vpgather_v4f16(<4 x half*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%v = call <4 x half> @llvm.vp.gather.v4f16.v4p0f16(<4 x half*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x half> %v
}
define <4 x half> @vpgather_truemask_v4f16(<4 x half*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8
; RV32-NEXT: vmv1r.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv1r.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x half> @llvm.vp.gather.v4f16.v4p0f16(<4 x half*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x half> %v
}
declare <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*>, <8 x i1>, i32)
define <8 x half> @vpgather_v8f16(<8 x half*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v12, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v12
; RV64-NEXT: ret
%v = call <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
}
define <8 x half> @vpgather_baseidx_v8i8_v8f16(half* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds half, half* %base, <8 x i8> %idxs
%v = call <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
}
define <8 x half> @vpgather_baseidx_sext_v8i8_v8f16(half* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i16>
%ptrs = getelementptr inbounds half, half* %base, <8 x i16> %eidxs
%v = call <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
}
define <8 x half> @vpgather_baseidx_zext_v8i8_v8f16(half* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf4 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i16>
%ptrs = getelementptr inbounds half, half* %base, <8 x i16> %eidxs
%v = call <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
}
define <8 x half> @vpgather_baseidx_v8f16(half* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8f16:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vadd.vv v10, v10, v10
; RV32-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v10, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8f16:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vadd.vv v12, v12, v12
; RV64-NEXT: vsetvli zero, a1, e16, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds half, half* %base, <8 x i16> %idxs
%v = call <8 x half> @llvm.vp.gather.v8f16.v8p0f16(<8 x half*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
}
declare <2 x float> @llvm.vp.gather.v2f32.v2p0f32(<2 x float*>, <2 x i1>, i32)
define <2 x float> @vpgather_v2f32(<2 x float*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; RV64-NEXT: vluxei64.v v9, (zero), v8, v0.t
; RV64-NEXT: vmv1r.v v8, v9
; RV64-NEXT: ret
%v = call <2 x float> @llvm.vp.gather.v2f32.v2p0f32(<2 x float*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x float> %v
}
declare <4 x float> @llvm.vp.gather.v4f32.v4p0f32(<4 x float*>, <4 x i1>, i32)
define <4 x float> @vpgather_v4f32(<4 x float*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v10
; RV64-NEXT: ret
%v = call <4 x float> @llvm.vp.gather.v4f32.v4p0f32(<4 x float*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x float> %v
}
define <4 x float> @vpgather_truemask_v4f32(<4 x float*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; RV64-NEXT: vluxei64.v v10, (zero), v8
; RV64-NEXT: vmv.v.v v8, v10
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x float> @llvm.vp.gather.v4f32.v4p0f32(<4 x float*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x float> %v
}
declare <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*>, <8 x i1>, i32)
define <8 x float> @vpgather_v8f32(<8 x float*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (zero), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v12, (zero), v8, v0.t
; RV64-NEXT: vmv.v.v v8, v12
; RV64-NEXT: ret
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_v8i8_v8f32(float* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, float* %base, <8 x i8> %idxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_sext_v8i8_v8f32(float* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i32>
%ptrs = getelementptr inbounds float, float* %base, <8 x i32> %eidxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_zext_v8i8_v8f32(float* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf4 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i32>
%ptrs = getelementptr inbounds float, float* %base, <8 x i32> %eidxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_v8i16_v8f32(float* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i16_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i16_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, float* %base, <8 x i16> %idxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_sext_v8i16_v8f32(float* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i16_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i16_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i16> %idxs to <8 x i32>
%ptrs = getelementptr inbounds float, float* %base, <8 x i32> %eidxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_zext_v8i16_v8f32(float* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i16_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vzext.vf2 v10, v8
; RV32-NEXT: vsll.vi v8, v10, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i16_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf4 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i16> %idxs to <8 x i32>
%ptrs = getelementptr inbounds float, float* %base, <8 x i32> %eidxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
define <8 x float> @vpgather_baseidx_v8f32(float* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8f32:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsll.vi v8, v8, 2
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v8, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8f32:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v12, v12, 2
; RV64-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v12, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds float, float* %base, <8 x i32> %idxs
%v = call <8 x float> @llvm.vp.gather.v8f32.v8p0f32(<8 x float*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
}
declare <2 x double> @llvm.vp.gather.v2f64.v2p0f64(<2 x double*>, <2 x i1>, i32)
define <2 x double> @vpgather_v2f64(<2 x double*> %ptrs, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v2f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; RV32-NEXT: vluxei32.v v9, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v9
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v2f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <2 x double> @llvm.vp.gather.v2f64.v2p0f64(<2 x double*> %ptrs, <2 x i1> %m, i32 %evl)
ret <2 x double> %v
}
declare <4 x double> @llvm.vp.gather.v4f64.v4p0f64(<4 x double*>, <4 x i1>, i32)
define <4 x double> @vpgather_v4f64(<4 x double*> %ptrs, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v4f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v4f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <4 x double> @llvm.vp.gather.v4f64.v4p0f64(<4 x double*> %ptrs, <4 x i1> %m, i32 %evl)
ret <4 x double> %v
}
define <4 x double> @vpgather_truemask_v4f64(<4 x double*> %ptrs, i32 zeroext %evl) {
; RV32-LABEL: vpgather_truemask_v4f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV32-NEXT: vluxei32.v v10, (zero), v8
; RV32-NEXT: vmv.v.v v8, v10
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_truemask_v4f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8
; RV64-NEXT: ret
%mhead = insertelement <4 x i1> poison, i1 1, i32 0
%mtrue = shufflevector <4 x i1> %mhead, <4 x i1> poison, <4 x i32> zeroinitializer
%v = call <4 x double> @llvm.vp.gather.v4f64.v4p0f64(<4 x double*> %ptrs, <4 x i1> %mtrue, i32 %evl)
ret <4 x double> %v
}
declare <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*>, <8 x i1>, i32)
define <8 x double> @vpgather_v8f64(<8 x double*> %ptrs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v12, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v12
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_v8i8_v8f64(double* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i8_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf4 v10, v8
; RV32-NEXT: vsll.vi v12, v10, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i8_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <8 x i8> %idxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_sext_v8i8_v8f64(double* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i8_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf8 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i8_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i8> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_zext_v8i8_v8f64(double* %base, <8 x i8> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i8_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf8 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i8_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf8 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i8> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_v8i16_v8f64(double* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i16_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsext.vf2 v10, v8
; RV32-NEXT: vsll.vi v12, v10, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i16_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <8 x i16> %idxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_sext_v8i16_v8f64(double* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i16_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf4 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i16_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i16> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_zext_v8i16_v8f64(double* %base, <8 x i16> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i16_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf4 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i16_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf4 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i16> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_v8i32_v8f64(double* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8i32_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; RV32-NEXT: vsll.vi v12, v8, 3
; RV32-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8i32_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <8 x i32> %idxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_sext_v8i32_v8f64(double* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v8i32_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsext.vf2 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v8i32_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <8 x i32> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_zext_v8i32_v8f64(double* %base, <8 x i32> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v8i32_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vzext.vf2 v12, v8
; RV32-NEXT: vsll.vi v8, v12, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v8i32_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vzext.vf2 v12, v8
; RV64-NEXT: vsll.vi v8, v12, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <8 x i32> %idxs to <8 x i64>
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %eidxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
define <8 x double> @vpgather_baseidx_v8f64(double* %base, <8 x i64> %idxs, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v8f64:
; RV32: # %bb.0:
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vsll.vi v8, v8, 3
; RV32-NEXT: vsetvli zero, a1, e32, m2, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v8
; RV32-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v12, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v8f64:
; RV64: # %bb.0:
; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV64-NEXT: vsll.vi v8, v8, 3
; RV64-NEXT: vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <8 x i64> %idxs
%v = call <8 x double> @llvm.vp.gather.v8f64.v8p0f64(<8 x double*> %ptrs, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
}
declare <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*>, <32 x i1>, i32)
define <32 x double> @vpgather_v32f64(<32 x double*> %ptrs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: addi a2, a0, -16
; RV32-NEXT: vmv1r.v v1, v0
; RV32-NEXT: li a1, 0
; RV32-NEXT: bltu a0, a2, .LBB86_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a1, a2
; RV32-NEXT: .LBB86_2:
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v8, 16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v1, 2
; RV32-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (zero), v24, v0.t
; RV32-NEXT: li a1, 16
; RV32-NEXT: bltu a0, a1, .LBB86_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a0, 16
; RV32-NEXT: .LBB86_4:
; RV32-NEXT: vsetvli zero, a0, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: vluxei32.v v24, (zero), v8, v0.t
; RV32-NEXT: vmv.v.v v8, v24
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: addi a2, a0, -16
; RV64-NEXT: vmv1r.v v24, v0
; RV64-NEXT: li a1, 0
; RV64-NEXT: bltu a0, a2, .LBB86_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a1, a2
; RV64-NEXT: .LBB86_2:
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v24, 2
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (zero), v16, v0.t
; RV64-NEXT: li a1, 16
; RV64-NEXT: bltu a0, a1, .LBB86_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a0, 16
; RV64-NEXT: .LBB86_4:
; RV64-NEXT: vsetvli zero, a0, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v24
; RV64-NEXT: vluxei64.v v8, (zero), v8, v0.t
; RV64-NEXT: ret
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_v32i8_v32f64(double* %base, <32 x i8> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v32i8_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: li a3, 16
; RV32-NEXT: mv a2, a1
; RV32-NEXT: bltu a1, a3, .LBB87_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: li a2, 16
; RV32-NEXT: .LBB87_2:
; RV32-NEXT: li a3, 32
; RV32-NEXT: vsetvli zero, a3, e32, m8, ta, mu
; RV32-NEXT: vsext.vf4 v16, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: li a2, 0
; RV32-NEXT: bltu a1, a3, .LBB87_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB87_4:
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v0, 2
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v16, 16
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v24, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v32i8_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vmv1r.v v10, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: bltu a1, a3, .LBB87_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB87_2:
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v10, 2
; RV64-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV64-NEXT: vslidedown.vi v12, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB87_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB87_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf8 v24, v8
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v10
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <32 x i8> %idxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_sext_v32i8_v32f64(double* %base, <32 x i8> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v32i8_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v10, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV32-NEXT: vslidedown.vi v12, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vsext.vf8 v16, v12
; RV32-NEXT: bltu a1, a3, .LBB88_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB88_2:
; RV32-NEXT: vsext.vf8 v24, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v10, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v12, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB88_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB88_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v24, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v24
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v10
; RV32-NEXT: vluxei32.v v8, (a0), v4, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v32i8_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v10, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV64-NEXT: vslidedown.vi v12, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vsext.vf8 v16, v12
; RV64-NEXT: bltu a1, a3, .LBB88_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB88_2:
; RV64-NEXT: vsext.vf8 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v10, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB88_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB88_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v10
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = sext <32 x i8> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_zext_v32i8_v32f64(double* %base, <32 x i8> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v32i8_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v10, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV32-NEXT: vslidedown.vi v12, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vzext.vf8 v16, v12
; RV32-NEXT: bltu a1, a3, .LBB89_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB89_2:
; RV32-NEXT: vzext.vf8 v24, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v12, v16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v10, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v12, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB89_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB89_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v24, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v24
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v10
; RV32-NEXT: vluxei32.v v8, (a0), v4, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v32i8_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v10, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e8, m2, ta, mu
; RV64-NEXT: vslidedown.vi v12, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vzext.vf8 v16, v12
; RV64-NEXT: bltu a1, a3, .LBB89_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB89_2:
; RV64-NEXT: vzext.vf8 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v10, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB89_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB89_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v10
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = zext <32 x i8> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_v32i16_v32f64(double* %base, <32 x i16> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v32i16_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: li a3, 16
; RV32-NEXT: mv a2, a1
; RV32-NEXT: bltu a1, a3, .LBB90_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: li a2, 16
; RV32-NEXT: .LBB90_2:
; RV32-NEXT: li a3, 32
; RV32-NEXT: vsetvli zero, a3, e32, m8, ta, mu
; RV32-NEXT: vsext.vf2 v16, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: li a2, 0
; RV32-NEXT: bltu a1, a3, .LBB90_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB90_4:
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v0, 2
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v16, 16
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v24, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v32i16_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vmv1r.v v12, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: bltu a1, a3, .LBB90_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB90_2:
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v12, 2
; RV64-NEXT: vsetivli zero, 16, e16, m4, ta, mu
; RV64-NEXT: vslidedown.vi v16, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf4 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB90_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB90_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf4 v24, v8
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v12
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <32 x i16> %idxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_sext_v32i16_v32f64(double* %base, <32 x i16> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v32i16_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v12, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e16, m4, ta, mu
; RV32-NEXT: vslidedown.vi v24, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vsext.vf4 v16, v24
; RV32-NEXT: bltu a1, a3, .LBB91_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB91_2:
; RV32-NEXT: vsext.vf4 v24, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v8, v16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v12, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v8, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB91_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB91_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v24, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v24
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v12
; RV32-NEXT: vluxei32.v v8, (a0), v4, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v32i16_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v12, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e16, m4, ta, mu
; RV64-NEXT: vslidedown.vi v24, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vsext.vf4 v16, v24
; RV64-NEXT: bltu a1, a3, .LBB91_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB91_2:
; RV64-NEXT: vsext.vf4 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v12, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB91_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB91_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v12
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = sext <32 x i16> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_zext_v32i16_v32f64(double* %base, <32 x i16> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v32i16_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v12, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e16, m4, ta, mu
; RV32-NEXT: vslidedown.vi v24, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vzext.vf4 v16, v24
; RV32-NEXT: bltu a1, a3, .LBB92_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB92_2:
; RV32-NEXT: vzext.vf4 v24, v8
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v8, v16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v12, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v8, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB92_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB92_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v24, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v24
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v12
; RV32-NEXT: vluxei32.v v8, (a0), v4, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v32i16_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v12, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e16, m4, ta, mu
; RV64-NEXT: vslidedown.vi v24, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vzext.vf4 v16, v24
; RV64-NEXT: bltu a1, a3, .LBB92_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB92_2:
; RV64-NEXT: vzext.vf4 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v12, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB92_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB92_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v24, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v12
; RV64-NEXT: vluxei64.v v8, (a0), v24, v0.t
; RV64-NEXT: ret
%eidxs = zext <32 x i16> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_v32i32_v32f64(double* %base, <32 x i32> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v32i32_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: li a3, 16
; RV32-NEXT: mv a2, a1
; RV32-NEXT: bltu a1, a3, .LBB93_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: li a2, 16
; RV32-NEXT: .LBB93_2:
; RV32-NEXT: li a3, 32
; RV32-NEXT: vsetvli zero, a3, e32, m8, ta, mu
; RV32-NEXT: vsll.vi v16, v8, 3
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v8, (a0), v16, v0.t
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: li a2, 0
; RV32-NEXT: bltu a1, a3, .LBB93_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB93_4:
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v16, 16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v0, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v24, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v32i32_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vmv1r.v v1, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: bltu a1, a3, .LBB93_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB93_2:
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v1, 2
; RV64-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV64-NEXT: vslidedown.vi v16, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf2 v24, v16
; RV64-NEXT: vsll.vi v16, v24, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB93_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB93_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsext.vf2 v24, v8
; RV64-NEXT: vsll.vi v8, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v1
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <32 x i32> %idxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_sext_v32i32_v32f64(double* %base, <32 x i32> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_sext_v32i32_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v1, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vsext.vf2 v16, v24
; RV32-NEXT: bltu a1, a3, .LBB94_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB94_2:
; RV32-NEXT: vsext.vf2 v24, v8
; RV32-NEXT: vsll.vi v8, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v8
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v1, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v4, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB94_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB94_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v8, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v24, v8
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: vluxei32.v v8, (a0), v24, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_sext_v32i32_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v1, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV64-NEXT: vslidedown.vi v24, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vsext.vf2 v16, v24
; RV64-NEXT: bltu a1, a3, .LBB94_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB94_2:
; RV64-NEXT: vsext.vf2 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v1, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v8, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v8, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB94_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB94_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v8, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v1
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = sext <32 x i32> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_zext_v32i32_v32f64(double* %base, <32 x i32> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_zext_v32i32_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: vmv1r.v v1, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV32-NEXT: vslidedown.vi v24, v8, 16
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vzext.vf2 v16, v24
; RV32-NEXT: bltu a1, a3, .LBB95_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB95_2:
; RV32-NEXT: vzext.vf2 v24, v8
; RV32-NEXT: vsll.vi v8, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v4, v8
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v1, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v4, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB95_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB95_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v8, v24, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v24, v8
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: vluxei32.v v8, (a0), v24, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_zext_v32i32_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: vmv1r.v v1, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: vsetivli zero, 16, e32, m8, ta, mu
; RV64-NEXT: vslidedown.vi v24, v8, 16
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vzext.vf2 v16, v24
; RV64-NEXT: bltu a1, a3, .LBB95_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB95_2:
; RV64-NEXT: vzext.vf2 v24, v8
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v1, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v8, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v8, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB95_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB95_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v8, v24, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v1
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%eidxs = zext <32 x i32> %idxs to <32 x i64>
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %eidxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}
define <32 x double> @vpgather_baseidx_v32f64(double* %base, <32 x i64> %idxs, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vpgather_baseidx_v32f64:
; RV32: # %bb.0:
; RV32-NEXT: addi a3, a1, -16
; RV32-NEXT: vmv1r.v v24, v0
; RV32-NEXT: li a2, 0
; RV32-NEXT: bltu a1, a3, .LBB96_2
; RV32-NEXT: # %bb.1:
; RV32-NEXT: mv a2, a3
; RV32-NEXT: .LBB96_2:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v16, v16, 3
; RV32-NEXT: vsetvli zero, a2, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v28, v16
; RV32-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT: vslidedown.vi v0, v24, 2
; RV32-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT: vluxei32.v v16, (a0), v28, v0.t
; RV32-NEXT: li a2, 16
; RV32-NEXT: bltu a1, a2, .LBB96_4
; RV32-NEXT: # %bb.3:
; RV32-NEXT: li a1, 16
; RV32-NEXT: .LBB96_4:
; RV32-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT: vsll.vi v8, v8, 3
; RV32-NEXT: vsetvli zero, a1, e32, m4, ta, mu
; RV32-NEXT: vncvt.x.x.w v28, v8
; RV32-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; RV32-NEXT: vmv1r.v v0, v24
; RV32-NEXT: vluxei32.v v8, (a0), v28, v0.t
; RV32-NEXT: ret
;
; RV64-LABEL: vpgather_baseidx_v32f64:
; RV64: # %bb.0:
; RV64-NEXT: addi a3, a1, -16
; RV64-NEXT: vmv1r.v v24, v0
; RV64-NEXT: li a2, 0
; RV64-NEXT: bltu a1, a3, .LBB96_2
; RV64-NEXT: # %bb.1:
; RV64-NEXT: mv a2, a3
; RV64-NEXT: .LBB96_2:
; RV64-NEXT: vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT: vslidedown.vi v0, v24, 2
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v16, v16, 3
; RV64-NEXT: vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT: vluxei64.v v16, (a0), v16, v0.t
; RV64-NEXT: li a2, 16
; RV64-NEXT: bltu a1, a2, .LBB96_4
; RV64-NEXT: # %bb.3:
; RV64-NEXT: li a1, 16
; RV64-NEXT: .LBB96_4:
; RV64-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT: vsll.vi v8, v8, 3
; RV64-NEXT: vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT: vmv1r.v v0, v24
; RV64-NEXT: vluxei64.v v8, (a0), v8, v0.t
; RV64-NEXT: ret
%ptrs = getelementptr inbounds double, double* %base, <32 x i64> %idxs
%v = call <32 x double> @llvm.vp.gather.v32f64.v32p0f64(<32 x double*> %ptrs, <32 x i1> %m, i32 %evl)
ret <32 x double> %v
}