[llvm] [RISCV] Add LLVM IR intrinsicis vrgatherei16/vslideup/vslidedown support for Zvfbfmin (PR #146312)
Jim Lin via llvm-commits
llvm-commits at lists.llvm.org
Sun Jun 29 23:11:25 PDT 2025
https://github.com/tclin914 created https://github.com/llvm/llvm-project/pull/146312
This patch add LLVM IR intrinsicis vrgatherei16/vslideup/vslidedown support for Zvfbfmin.
>From 9062987d3181b2c006a3c847a6d871eba78a99da Mon Sep 17 00:00:00 2001
From: Jim Lin <jim at andestech.com>
Date: Mon, 30 Jun 2025 13:18:03 +0800
Subject: [PATCH] [RISCV] Add LLVM IR intrinsicis
vrgatherei16/vslideup/vslidedown support for Zvfbfmin
This patch add LLVM IR intrinsicis vrgatherei16/vslideup/vslidedown
support for Zvfbfmin.
---
.../Target/RISCV/RISCVInstrInfoVPseudos.td | 5 +
llvm/test/CodeGen/RISCV/rvv/vrgatherei16.ll | 293 ++++++++++++-
llvm/test/CodeGen/RISCV/rvv/vslidedown.ll | 414 +++++++++++++++++-
llvm/test/CodeGen/RISCV/rvv/vslideup.ll | 414 +++++++++++++++++-
4 files changed, 1120 insertions(+), 6 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
index 9c03c7c83af04..1c9242ddad56f 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -7419,6 +7419,9 @@ defm : VPatTernaryV_VX_VI<"int_riscv_vslidedown", "PseudoVSLIDEDOWN", AllFloatVe
defm : VPatBinaryV_VX<"int_riscv_vfslide1up", "PseudoVFSLIDE1UP", AllFloatVectors>;
defm : VPatBinaryV_VX<"int_riscv_vfslide1down", "PseudoVFSLIDE1DOWN", AllFloatVectors>;
+defm : VPatTernaryV_VX_VI<"int_riscv_vslideup", "PseudoVSLIDEUP", AllBFloatVectors, uimm5>;
+defm : VPatTernaryV_VX_VI<"int_riscv_vslidedown", "PseudoVSLIDEDOWN", AllBFloatVectors, uimm5>;
+
//===----------------------------------------------------------------------===//
// 16.4. Vector Register Gather Instructions
//===----------------------------------------------------------------------===//
@@ -7433,6 +7436,8 @@ defm : VPatBinaryV_VV_VX_VI_INT<"int_riscv_vrgather", "PseudoVRGATHER",
AllBFloatVectors, uimm5>;
defm : VPatBinaryV_VV_INT_EEW<"int_riscv_vrgatherei16_vv", "PseudoVRGATHEREI16",
eew=16, vtilist=AllFloatVectors>;
+defm : VPatBinaryV_VV_INT_EEW<"int_riscv_vrgatherei16_vv", "PseudoVRGATHEREI16",
+ eew=16, vtilist=AllBFloatVectors>;
//===----------------------------------------------------------------------===//
// 16.5. Vector Compress Instruction
//===----------------------------------------------------------------------===//
diff --git a/llvm/test/CodeGen/RISCV/rvv/vrgatherei16.ll b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16.ll
index 75c00e406b4f1..168b5eeb5592b 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vrgatherei16.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vrgatherei16.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
-; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
declare <vscale x 1 x i8> @llvm.riscv.vrgatherei16.vv.nxv1i8(
@@ -1449,3 +1449,292 @@ entry:
ret <vscale x 8 x double> %a
}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x i16>,
+ iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vrgatherei16_vv_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v10, v8, v9
+; CHECK-NEXT: vmv1r.v v8, v10
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv1bf16(
+ <vscale x 1 x bfloat> undef,
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x i16>,
+ <vscale x 1 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, <vscale x 1 x i16> %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v9, v10, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ <vscale x 1 x i16> %2,
+ <vscale x 1 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x i16>,
+ iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vrgatherei16_vv_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v10, v8, v9
+; CHECK-NEXT: vmv1r.v v8, v10
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv2bf16(
+ <vscale x 2 x bfloat> undef,
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x i16>,
+ <vscale x 2 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, <vscale x 2 x i16> %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v9, v10, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ <vscale x 2 x i16> %2,
+ <vscale x 2 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x i16>,
+ iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vrgatherei16_vv_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v10, v8, v9
+; CHECK-NEXT: vmv.v.v v8, v10
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv4bf16(
+ <vscale x 4 x bfloat> undef,
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x i16>,
+ <vscale x 4 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, <vscale x 4 x i16> %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v9, v10, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ <vscale x 4 x i16> %2,
+ <vscale x 4 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x i16>,
+ iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vrgatherei16_vv_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v12, v8, v10
+; CHECK-NEXT: vmv.v.v v8, v12
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv8bf16(
+ <vscale x 8 x bfloat> undef,
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x i16>,
+ <vscale x 8 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, <vscale x 8 x i16> %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v10, v12, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ <vscale x 8 x i16> %2,
+ <vscale x 8 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x i16>,
+ iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vrgatherei16_vv_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v16, v8, v12
+; CHECK-NEXT: vmv.v.v v8, v16
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv16bf16(
+ <vscale x 16 x bfloat> undef,
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x i16>,
+ <vscale x 16 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, <vscale x 16 x i16> %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v12, v16, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ <vscale x 16 x i16> %2,
+ <vscale x 16 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+declare <vscale x 32 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv32bf16(
+ <vscale x 32 x bfloat>,
+ <vscale x 32 x bfloat>,
+ <vscale x 32 x i16>,
+ iXLen);
+
+define <vscale x 32 x bfloat> @intrinsic_vrgatherei16_vv_nxv32bf16_nxv32bf16(<vscale x 32 x bfloat> %0, <vscale x 32 x i16> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_vv_nxv32bf16_nxv32bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m8, ta, ma
+; CHECK-NEXT: vrgatherei16.vv v24, v8, v16
+; CHECK-NEXT: vmv.v.v v8, v24
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 32 x bfloat> @llvm.riscv.vrgatherei16.vv.nxv32bf16(
+ <vscale x 32 x bfloat> undef,
+ <vscale x 32 x bfloat> %0,
+ <vscale x 32 x i16> %1,
+ iXLen %2)
+
+ ret <vscale x 32 x bfloat> %a
+}
+
+declare <vscale x 32 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv32bf16(
+ <vscale x 32 x bfloat>,
+ <vscale x 32 x bfloat>,
+ <vscale x 32 x i16>,
+ <vscale x 32 x i1>,
+ iXLen,
+ iXLen);
+
+define <vscale x 32 x bfloat> @intrinsic_vrgatherei16_mask_vv_nxv32bf16_nxv32bf16(<vscale x 32 x bfloat> %0, <vscale x 32 x bfloat> %1, <vscale x 32 x i16> %2, <vscale x 32 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vrgatherei16_mask_vv_nxv32bf16_nxv32bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vl8re16.v v24, (a0)
+; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, mu
+; CHECK-NEXT: vrgatherei16.vv v8, v16, v24, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 32 x bfloat> @llvm.riscv.vrgatherei16.vv.mask.nxv32bf16(
+ <vscale x 32 x bfloat> %0,
+ <vscale x 32 x bfloat> %1,
+ <vscale x 32 x i16> %2,
+ <vscale x 32 x i1> %3,
+ iXLen %4, iXLen 1)
+
+ ret <vscale x 32 x bfloat> %a
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/vslidedown.ll b/llvm/test/CodeGen/RISCV/rvv/vslidedown.ll
index f0f78c211c4a9..8b7a480afed72 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vslidedown.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vslidedown.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
-; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
declare <vscale x 1 x i8> @llvm.riscv.vslidedown.nxv1i8(
@@ -2463,3 +2463,413 @@ entry:
ret <vscale x 4 x double> %a
}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vslidedown.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vslidedown_vx_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vx_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT: vslidedown.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslidedown.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vslidedown.mask.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ iXLen,
+ <vscale x 1 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vslidedown_mask_vx_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vx_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf4, tu, mu
+; CHECK-NEXT: vslidedown.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslidedown.mask.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen %2,
+ <vscale x 1 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+define <vscale x 1 x bfloat> @intrinsic_vslidedown_vi_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vi_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT: vslidedown.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslidedown.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+define <vscale x 1 x bfloat> @intrinsic_vslidedown_mask_vi_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vi_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, tu, mu
+; CHECK-NEXT: vslidedown.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslidedown.mask.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen 9,
+ <vscale x 1 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vslidedown.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vslidedown_vx_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vx_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT: vslidedown.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslidedown.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vslidedown.mask.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ iXLen,
+ <vscale x 2 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vslidedown_mask_vx_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vx_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf2, tu, mu
+; CHECK-NEXT: vslidedown.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslidedown.mask.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen %2,
+ <vscale x 2 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+define <vscale x 2 x bfloat> @intrinsic_vslidedown_vi_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vi_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT: vslidedown.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslidedown.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+define <vscale x 2 x bfloat> @intrinsic_vslidedown_mask_vi_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vi_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, tu, mu
+; CHECK-NEXT: vslidedown.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslidedown.mask.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen 9,
+ <vscale x 2 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vslidedown.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vslidedown_vx_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vx_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vslidedown.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslidedown.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vslidedown.mask.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ iXLen,
+ <vscale x 4 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vslidedown_mask_vx_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vx_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, tu, mu
+; CHECK-NEXT: vslidedown.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslidedown.mask.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen %2,
+ <vscale x 4 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+define <vscale x 4 x bfloat> @intrinsic_vslidedown_vi_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vi_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT: vslidedown.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslidedown.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+define <vscale x 4 x bfloat> @intrinsic_vslidedown_mask_vi_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vi_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, tu, mu
+; CHECK-NEXT: vslidedown.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslidedown.mask.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen 9,
+ <vscale x 4 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vslidedown.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vslidedown_vx_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vx_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT: vslidedown.vx v8, v10, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslidedown.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vslidedown.mask.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ iXLen,
+ <vscale x 8 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vslidedown_mask_vx_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vx_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m2, tu, mu
+; CHECK-NEXT: vslidedown.vx v8, v10, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslidedown.mask.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen %2,
+ <vscale x 8 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+define <vscale x 8 x bfloat> @intrinsic_vslidedown_vi_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vi_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT: vslidedown.vi v8, v10, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslidedown.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+define <vscale x 8 x bfloat> @intrinsic_vslidedown_mask_vi_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vi_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, tu, mu
+; CHECK-NEXT: vslidedown.vi v8, v10, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslidedown.mask.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen 9,
+ <vscale x 8 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vslidedown.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vslidedown_vx_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vx_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT: vslidedown.vx v8, v12, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslidedown.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vslidedown.mask.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ iXLen,
+ <vscale x 16 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vslidedown_mask_vx_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vx_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m4, tu, mu
+; CHECK-NEXT: vslidedown.vx v8, v12, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslidedown.mask.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen %2,
+ <vscale x 16 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+define <vscale x 16 x bfloat> @intrinsic_vslidedown_vi_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_vi_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT: vslidedown.vi v8, v12, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslidedown.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+define <vscale x 16 x bfloat> @intrinsic_vslidedown_mask_vi_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslidedown_mask_vi_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, tu, mu
+; CHECK-NEXT: vslidedown.vi v8, v12, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslidedown.mask.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen 9,
+ <vscale x 16 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 16 x bfloat> %a
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/vslideup.ll b/llvm/test/CodeGen/RISCV/rvv/vslideup.ll
index 8e3c05611bc71..d4ad50dbd4d53 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vslideup.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vslideup.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
-; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin \
+; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+d,+zvfhmin,+zvfbfmin \
; RUN: -verify-machineinstrs | FileCheck %s
declare <vscale x 1 x i8> @llvm.riscv.vslideup.nxv1i8(
@@ -2463,3 +2463,413 @@ entry:
ret <vscale x 4 x double> %a
}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vslideup.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vslideup_vx_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vx_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf4, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslideup.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 1 x bfloat> @llvm.riscv.vslideup.mask.nxv1bf16(
+ <vscale x 1 x bfloat>,
+ <vscale x 1 x bfloat>,
+ iXLen,
+ <vscale x 1 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 1 x bfloat> @intrinsic_vslideup_mask_vx_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2, <vscale x 1 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vx_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf4, tu, mu
+; CHECK-NEXT: vslideup.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslideup.mask.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen %2,
+ <vscale x 1 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+define <vscale x 1 x bfloat> @intrinsic_vslideup_vi_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vi_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
+; CHECK-NEXT: vslideup.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslideup.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+define <vscale x 1 x bfloat> @intrinsic_vslideup_mask_vi_nxv1bf16_nxv1bf16(<vscale x 1 x bfloat> %0, <vscale x 1 x bfloat> %1, <vscale x 1 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vi_nxv1bf16_nxv1bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf4, tu, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 1 x bfloat> @llvm.riscv.vslideup.mask.nxv1bf16(
+ <vscale x 1 x bfloat> %0,
+ <vscale x 1 x bfloat> %1,
+ iXLen 9,
+ <vscale x 1 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 1 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vslideup.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vslideup_vx_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vx_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf2, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslideup.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 2 x bfloat> @llvm.riscv.vslideup.mask.nxv2bf16(
+ <vscale x 2 x bfloat>,
+ <vscale x 2 x bfloat>,
+ iXLen,
+ <vscale x 2 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 2 x bfloat> @intrinsic_vslideup_mask_vx_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2, <vscale x 2 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vx_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, mf2, tu, mu
+; CHECK-NEXT: vslideup.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslideup.mask.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen %2,
+ <vscale x 2 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+define <vscale x 2 x bfloat> @intrinsic_vslideup_vi_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vi_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
+; CHECK-NEXT: vslideup.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslideup.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+define <vscale x 2 x bfloat> @intrinsic_vslideup_mask_vi_nxv2bf16_nxv2bf16(<vscale x 2 x bfloat> %0, <vscale x 2 x bfloat> %1, <vscale x 2 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vi_nxv2bf16_nxv2bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, mf2, tu, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 2 x bfloat> @llvm.riscv.vslideup.mask.nxv2bf16(
+ <vscale x 2 x bfloat> %0,
+ <vscale x 2 x bfloat> %1,
+ iXLen 9,
+ <vscale x 2 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 2 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vslideup.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vslideup_vx_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vx_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v9, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslideup.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 4 x bfloat> @llvm.riscv.vslideup.mask.nxv4bf16(
+ <vscale x 4 x bfloat>,
+ <vscale x 4 x bfloat>,
+ iXLen,
+ <vscale x 4 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 4 x bfloat> @intrinsic_vslideup_mask_vx_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2, <vscale x 4 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vx_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m1, tu, mu
+; CHECK-NEXT: vslideup.vx v8, v9, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslideup.mask.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen %2,
+ <vscale x 4 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+define <vscale x 4 x bfloat> @intrinsic_vslideup_vi_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vi_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
+; CHECK-NEXT: vslideup.vi v8, v9, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslideup.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+define <vscale x 4 x bfloat> @intrinsic_vslideup_mask_vi_nxv4bf16_nxv4bf16(<vscale x 4 x bfloat> %0, <vscale x 4 x bfloat> %1, <vscale x 4 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vi_nxv4bf16_nxv4bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m1, tu, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 4 x bfloat> @llvm.riscv.vslideup.mask.nxv4bf16(
+ <vscale x 4 x bfloat> %0,
+ <vscale x 4 x bfloat> %1,
+ iXLen 9,
+ <vscale x 4 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 4 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vslideup.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vslideup_vx_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vx_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m2, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v10, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslideup.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 8 x bfloat> @llvm.riscv.vslideup.mask.nxv8bf16(
+ <vscale x 8 x bfloat>,
+ <vscale x 8 x bfloat>,
+ iXLen,
+ <vscale x 8 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 8 x bfloat> @intrinsic_vslideup_mask_vx_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2, <vscale x 8 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vx_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m2, tu, mu
+; CHECK-NEXT: vslideup.vx v8, v10, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslideup.mask.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen %2,
+ <vscale x 8 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+define <vscale x 8 x bfloat> @intrinsic_vslideup_vi_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vi_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma
+; CHECK-NEXT: vslideup.vi v8, v10, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslideup.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+define <vscale x 8 x bfloat> @intrinsic_vslideup_mask_vi_nxv8bf16_nxv8bf16(<vscale x 8 x bfloat> %0, <vscale x 8 x bfloat> %1, <vscale x 8 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vi_nxv8bf16_nxv8bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m2, tu, mu
+; CHECK-NEXT: vslideup.vi v8, v10, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 8 x bfloat> @llvm.riscv.vslideup.mask.nxv8bf16(
+ <vscale x 8 x bfloat> %0,
+ <vscale x 8 x bfloat> %1,
+ iXLen 9,
+ <vscale x 8 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 8 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vslideup.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ iXLen,
+ iXLen,
+ iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vslideup_vx_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vx_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, ma
+; CHECK-NEXT: vslideup.vx v8, v12, a0
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslideup.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen %2,
+ iXLen %3,
+ iXLen 1)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+declare <vscale x 16 x bfloat> @llvm.riscv.vslideup.mask.nxv16bf16(
+ <vscale x 16 x bfloat>,
+ <vscale x 16 x bfloat>,
+ iXLen,
+ <vscale x 16 x i1>,
+ iXLen, iXLen);
+
+define <vscale x 16 x bfloat> @intrinsic_vslideup_mask_vx_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2, <vscale x 16 x i1> %3, iXLen %4) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vx_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a1, e16, m4, tu, mu
+; CHECK-NEXT: vslideup.vx v8, v12, a0, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslideup.mask.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen %2,
+ <vscale x 16 x i1> %3,
+ iXLen %4, iXLen 0)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+define <vscale x 16 x bfloat> @intrinsic_vslideup_vi_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, iXLen %2) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_vi_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, ma
+; CHECK-NEXT: vslideup.vi v8, v12, 9
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslideup.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen 9,
+ iXLen %2,
+ iXLen 1)
+
+ ret <vscale x 16 x bfloat> %a
+}
+
+define <vscale x 16 x bfloat> @intrinsic_vslideup_mask_vi_nxv16bf16_nxv16bf16(<vscale x 16 x bfloat> %0, <vscale x 16 x bfloat> %1, <vscale x 16 x i1> %2, iXLen %3) nounwind {
+; CHECK-LABEL: intrinsic_vslideup_mask_vi_nxv16bf16_nxv16bf16:
+; CHECK: # %bb.0: # %entry
+; CHECK-NEXT: vsetvli zero, a0, e16, m4, tu, mu
+; CHECK-NEXT: vslideup.vi v8, v12, 9, v0.t
+; CHECK-NEXT: ret
+entry:
+ %a = call <vscale x 16 x bfloat> @llvm.riscv.vslideup.mask.nxv16bf16(
+ <vscale x 16 x bfloat> %0,
+ <vscale x 16 x bfloat> %1,
+ iXLen 9,
+ <vscale x 16 x i1> %2,
+ iXLen %3, iXLen 0)
+
+ ret <vscale x 16 x bfloat> %a
+}
More information about the llvm-commits
mailing list