[llvm] [RISCV] Remove hasSideEffects=1 for vsetvli pseudos (PR #91319)
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Tue May 14 21:44:07 PDT 2024
https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/91319
>From 874215497e9d7d99af4149487f44572c21eee376 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 7 May 2024 18:32:42 +0800
Subject: [PATCH] [RISCV] Remove hasSideEffects=1 for vsetvli pseudos
In a similar vein to #90049, it looks like we currently model all of the effects of a vsetvli pseudo:
* VL and VTYPE are marked as defs
* VL preserving x0,x0 vsetvlis doesn't get emitted until RISCVInsertVSETVLI, and when they are they have implicit-defs on VL
* Regular vector pseudos are fully modelled too: Before RISCVInsertVSETVLI they can be moved between vsetvli pseudos because we will eventually insert vsetvlis to correct VL and VTYPE. Afterwards, they will have implicit-defs on VL and VTYPE.
I may be missing something but otherwise it seems ok to remove hasSideEffects=1. This gives us some improvements like sinking in vsetvli-insert-crossbb.ll.
We need to update RISCVDeadRegisterDefinitions to keep handling vsetvli pseudos since it only operates on instructions with unmodelled side effects.
---
.../RISCV/RISCVDeadRegisterDefinitions.cpp | 4 +-
.../Target/RISCV/RISCVInstrInfoVPseudos.td | 2 +-
.../CodeGen/RISCV/rvv/calling-conv-fastcc.ll | 38 +-
llvm/test/CodeGen/RISCV/rvv/calling-conv.ll | 8 +-
...d-vectors-fnearbyint-constrained-sdnode.ll | 24 +-
.../RISCV/rvv/fixed-vectors-fp2i-sat.ll | 24 +-
.../CodeGen/RISCV/rvv/fixed-vectors-i2fp.ll | 80 ++--
.../RISCV/rvv/fixed-vectors-int-buildvec.ll | 154 ++++----
...fixed-vectors-interleaved-access-zve32x.ll | 38 +-
.../CodeGen/RISCV/rvv/fixed-vectors-lrint.ll | 20 +-
.../RISCV/rvv/fixed-vectors-masked-gather.ll | 372 +++++++++---------
.../RISCV/rvv/fixed-vectors-masked-scatter.ll | 69 ++--
.../RISCV/rvv/fixed-vectors-nearbyint-vp.ll | 56 +--
.../RISCV/rvv/fixed-vectors-vselect.ll | 24 +-
.../CodeGen/RISCV/rvv/fixed-vectors-vwadd.ll | 8 +-
.../CodeGen/RISCV/rvv/fixed-vectors-vwaddu.ll | 8 +-
.../CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll | 2 +-
.../RISCV/rvv/fixed-vectors-vwmulsu.ll | 6 +-
.../CodeGen/RISCV/rvv/fixed-vectors-vwsub.ll | 8 +-
.../CodeGen/RISCV/rvv/fixed-vectors-vwsubu.ll | 8 +-
llvm/test/CodeGen/RISCV/rvv/fmaximum-vp.ll | 154 +++++---
llvm/test/CodeGen/RISCV/rvv/fminimum-vp.ll | 154 +++++---
.../rvv/fnearbyint-constrained-sdnode.ll | 30 +-
.../CodeGen/RISCV/rvv/fnearbyint-sdnode.ll | 30 +-
llvm/test/CodeGen/RISCV/rvv/fshr-fshl-vp.ll | 294 ++++++--------
llvm/test/CodeGen/RISCV/rvv/mgather-sdnode.ll | 19 +-
.../test/CodeGen/RISCV/rvv/mscatter-sdnode.ll | 2 +-
llvm/test/CodeGen/RISCV/rvv/nearbyint-vp.ll | 197 +++++-----
llvm/test/CodeGen/RISCV/rvv/setcc-fp-vp.ll | 268 ++++++-------
llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll | 40 +-
llvm/test/CodeGen/RISCV/rvv/vfma-vp.ll | 34 +-
llvm/test/CodeGen/RISCV/rvv/vfmuladd-vp.ll | 34 +-
llvm/test/CodeGen/RISCV/rvv/vpmerge-sdnode.ll | 14 +-
llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll | 6 +-
.../RISCV/rvv/vsetvli-insert-crossbb.ll | 39 +-
.../CodeGen/RISCV/rvv/vsetvli-regression.ll | 5 +-
36 files changed, 1107 insertions(+), 1166 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVDeadRegisterDefinitions.cpp b/llvm/lib/Target/RISCV/RISCVDeadRegisterDefinitions.cpp
index 5e6b7891449fe..7de48d8218f06 100644
--- a/llvm/lib/Target/RISCV/RISCVDeadRegisterDefinitions.cpp
+++ b/llvm/lib/Target/RISCV/RISCVDeadRegisterDefinitions.cpp
@@ -72,7 +72,9 @@ bool RISCVDeadRegisterDefinitions::runOnMachineFunction(MachineFunction &MF) {
// are reserved for HINT instructions.
const MCInstrDesc &Desc = MI.getDesc();
if (!Desc.mayLoad() && !Desc.mayStore() &&
- !Desc.hasUnmodeledSideEffects())
+ !Desc.hasUnmodeledSideEffects() &&
+ MI.getOpcode() != RISCV::PseudoVSETVLI &&
+ MI.getOpcode() != RISCV::PseudoVSETIVLI)
continue;
// For PseudoVSETVLIX0, Rd = X0 has special meaning.
if (MI.getOpcode() == RISCV::PseudoVSETVLIX0)
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
index 4adc26f628914..317a6d7d4c52f 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -6181,7 +6181,7 @@ let hasSideEffects = 0, mayLoad = 0, mayStore = 0, Size = 0,
//===----------------------------------------------------------------------===//
// Pseudos.
-let hasSideEffects = 1, mayLoad = 0, mayStore = 0, Defs = [VL, VTYPE] in {
+let hasSideEffects = 0, mayLoad = 0, mayStore = 0, Defs = [VL, VTYPE] in {
// Due to rs1=X0 having special meaning, we need a GPRNoX0 register class for
// the when we aren't using one of the special X0 encodings. Otherwise it could
// be accidentally be made X0 by MachineIR optimizations. To satisfy the
diff --git a/llvm/test/CodeGen/RISCV/rvv/calling-conv-fastcc.ll b/llvm/test/CodeGen/RISCV/rvv/calling-conv-fastcc.ll
index 187f758b78020..0a7fa38b0c8ab 100644
--- a/llvm/test/CodeGen/RISCV/rvv/calling-conv-fastcc.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/calling-conv-fastcc.ll
@@ -236,11 +236,12 @@ define fastcc <vscale x 32 x i32> @ret_nxv32i32_param_nxv32i32_nxv32i32_nxv32i32
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 4
+; CHECK-NEXT: li a3, 24
+; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 3
+; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
@@ -248,29 +249,40 @@ define fastcc <vscale x 32 x i32> @ret_nxv32i32_param_nxv32i32_nxv32i32_nxv32i32
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a3, a2, a1
-; CHECK-NEXT: vl8re32.v v8, (a3)
-; CHECK-NEXT: addi a3, sp, 16
-; CHECK-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: add a1, a0, a1
-; CHECK-NEXT: vl8re32.v v0, (a0)
; CHECK-NEXT: vl8re32.v v8, (a1)
-; CHECK-NEXT: vl8re32.v v16, (a2)
+; CHECK-NEXT: csrr a1, vlenb
+; CHECK-NEXT: slli a1, a1, 3
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: addi a1, a1, 16
+; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re32.v v0, (a0)
; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT: vl8re32.v v8, (a3)
+; CHECK-NEXT: addi a0, sp, 16
+; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re32.v v16, (a2)
; CHECK-NEXT: vadd.vv v0, v24, v0
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vadd.vv v8, v24, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vadd.vv v24, v24, v8
; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vadd.vv v8, v8, v24
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vadd.vv v8, v24, v8
; CHECK-NEXT: vadd.vv v24, v0, v16
; CHECK-NEXT: vadd.vx v16, v8, a4
; CHECK-NEXT: vadd.vx v8, v24, a4
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a1, 24
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/calling-conv.ll b/llvm/test/CodeGen/RISCV/rvv/calling-conv.ll
index 647d3158b6167..fa62143546df6 100644
--- a/llvm/test/CodeGen/RISCV/rvv/calling-conv.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/calling-conv.ll
@@ -39,11 +39,11 @@ define <vscale x 32 x i32> @caller_scalable_vector_split_indirect(<vscale x 32 x
; RV32-NEXT: vs8r.v v8, (a0)
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: slli a1, a1, 3
-; RV32-NEXT: add a0, a0, a1
-; RV32-NEXT: vs8r.v v16, (a0)
+; RV32-NEXT: add a1, a0, a1
; RV32-NEXT: vsetvli a0, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.i v8, 0
; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vs8r.v v16, (a1)
; RV32-NEXT: vmv.v.i v16, 0
; RV32-NEXT: call callee_scalable_vector_split_indirect
; RV32-NEXT: addi sp, s0, -144
@@ -70,11 +70,11 @@ define <vscale x 32 x i32> @caller_scalable_vector_split_indirect(<vscale x 32 x
; RV64-NEXT: vs8r.v v8, (a0)
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: slli a1, a1, 3
-; RV64-NEXT: add a0, a0, a1
-; RV64-NEXT: vs8r.v v16, (a0)
+; RV64-NEXT: add a1, a0, a1
; RV64-NEXT: vsetvli a0, zero, e32, m8, ta, ma
; RV64-NEXT: vmv.v.i v8, 0
; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vs8r.v v16, (a1)
; RV64-NEXT: vmv.v.i v16, 0
; RV64-NEXT: call callee_scalable_vector_split_indirect
; RV64-NEXT: addi sp, s0, -144
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fnearbyint-constrained-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fnearbyint-constrained-sdnode.ll
index 1b50214bbf164..9e9a8b8a4b644 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fnearbyint-constrained-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fnearbyint-constrained-sdnode.ll
@@ -19,9 +19,9 @@ define <2 x half> @nearbyint_v2f16(<2 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <2 x half> @llvm.experimental.constrained.nearbyint.v2f16(<2 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <2 x half> %r
@@ -42,9 +42,9 @@ define <4 x half> @nearbyint_v4f16(<4 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <4 x half> @llvm.experimental.constrained.nearbyint.v4f16(<4 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <4 x half> %r
@@ -65,9 +65,9 @@ define <8 x half> @nearbyint_v8f16(<8 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <8 x half> @llvm.experimental.constrained.nearbyint.v8f16(<8 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <8 x half> %r
@@ -88,9 +88,9 @@ define <16 x half> @nearbyint_v16f16(<16 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <16 x half> @llvm.experimental.constrained.nearbyint.v16f16(<16 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <16 x half> %r
@@ -112,9 +112,9 @@ define <32 x half> @nearbyint_v32f16(<32 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <32 x half> @llvm.experimental.constrained.nearbyint.v32f16(<32 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <32 x half> %r
@@ -135,9 +135,9 @@ define <2 x float> @nearbyint_v2f32(<2 x float> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <2 x float> @llvm.experimental.constrained.nearbyint.v2f32(<2 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <2 x float> %r
@@ -158,9 +158,9 @@ define <4 x float> @nearbyint_v4f32(<4 x float> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <4 x float> @llvm.experimental.constrained.nearbyint.v4f32(<4 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <4 x float> %r
@@ -181,9 +181,9 @@ define <8 x float> @nearbyint_v8f32(<8 x float> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <8 x float> @llvm.experimental.constrained.nearbyint.v8f32(<8 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <8 x float> %r
@@ -204,9 +204,9 @@ define <16 x float> @nearbyint_v16f32(<16 x float> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <16 x float> @llvm.experimental.constrained.nearbyint.v16f32(<16 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <16 x float> %r
@@ -227,9 +227,9 @@ define <2 x double> @nearbyint_v2f64(<2 x double> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <2 x double> %r
@@ -250,9 +250,9 @@ define <4 x double> @nearbyint_v4f64(<4 x double> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(<4 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <4 x double> %r
@@ -273,9 +273,9 @@ define <8 x double> @nearbyint_v8f64(<8 x double> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <8 x double> @llvm.experimental.constrained.nearbyint.v8f64(<8 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <8 x double> %r
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
index a8e4af2d7368e..6320b07125bb0 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp2i-sat.ll
@@ -359,13 +359,13 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
; RV32-NEXT: feq.d a0, fa3, fa3
; RV32-NEXT: fmax.d fa3, fa3, fa5
; RV32-NEXT: fmin.d fa3, fa3, fa4
-; RV32-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; RV32-NEXT: fld fa2, 40(sp)
; RV32-NEXT: fcvt.w.d a2, fa3, rtz
+; RV32-NEXT: fld fa3, 40(sp)
; RV32-NEXT: neg a0, a0
; RV32-NEXT: and a0, a0, a2
-; RV32-NEXT: feq.d a2, fa2, fa2
-; RV32-NEXT: fmax.d fa3, fa2, fa5
+; RV32-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
+; RV32-NEXT: feq.d a2, fa3, fa3
+; RV32-NEXT: fmax.d fa3, fa3, fa5
; RV32-NEXT: fmin.d fa3, fa3, fa4
; RV32-NEXT: fcvt.w.d a3, fa3, rtz
; RV32-NEXT: fld fa3, 32(sp)
@@ -460,13 +460,13 @@ define void @fp2si_v8f64_v8i8(ptr %x, ptr %y) {
; RV64-NEXT: feq.d a0, fa3, fa3
; RV64-NEXT: fmax.d fa3, fa3, fa5
; RV64-NEXT: fmin.d fa3, fa3, fa4
-; RV64-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; RV64-NEXT: fld fa2, 40(sp)
; RV64-NEXT: fcvt.l.d a2, fa3, rtz
+; RV64-NEXT: fld fa3, 40(sp)
; RV64-NEXT: neg a0, a0
; RV64-NEXT: and a0, a0, a2
-; RV64-NEXT: feq.d a2, fa2, fa2
-; RV64-NEXT: fmax.d fa3, fa2, fa5
+; RV64-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
+; RV64-NEXT: feq.d a2, fa3, fa3
+; RV64-NEXT: fmax.d fa3, fa3, fa5
; RV64-NEXT: fmin.d fa3, fa3, fa4
; RV64-NEXT: fcvt.l.d a3, fa3, rtz
; RV64-NEXT: fld fa3, 32(sp)
@@ -557,7 +557,6 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
; RV32-NEXT: vslidedown.vi v8, v8, 3
; RV32-NEXT: vfmv.f.s fa4, v8
; RV32-NEXT: fmax.d fa4, fa4, fa3
-; RV32-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; RV32-NEXT: fld fa2, 40(sp)
; RV32-NEXT: fmin.d fa4, fa4, fa5
; RV32-NEXT: fcvt.wu.d a0, fa4, rtz
@@ -566,9 +565,10 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
; RV32-NEXT: fmin.d fa2, fa2, fa5
; RV32-NEXT: fcvt.wu.d a2, fa2, rtz
; RV32-NEXT: fmax.d fa4, fa4, fa3
-; RV32-NEXT: fld fa2, 48(sp)
; RV32-NEXT: fmin.d fa4, fa4, fa5
+; RV32-NEXT: fld fa2, 48(sp)
; RV32-NEXT: fcvt.wu.d a3, fa4, rtz
+; RV32-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; RV32-NEXT: vslide1down.vx v8, v10, a0
; RV32-NEXT: fmax.d fa4, fa2, fa3
; RV32-NEXT: fmin.d fa4, fa4, fa5
@@ -633,7 +633,6 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
; RV64-NEXT: vslidedown.vi v8, v8, 3
; RV64-NEXT: vfmv.f.s fa4, v8
; RV64-NEXT: fmax.d fa4, fa4, fa3
-; RV64-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; RV64-NEXT: fld fa2, 40(sp)
; RV64-NEXT: fmin.d fa4, fa4, fa5
; RV64-NEXT: fcvt.lu.d a0, fa4, rtz
@@ -642,9 +641,10 @@ define void @fp2ui_v8f64_v8i8(ptr %x, ptr %y) {
; RV64-NEXT: fmin.d fa2, fa2, fa5
; RV64-NEXT: fcvt.lu.d a2, fa2, rtz
; RV64-NEXT: fmax.d fa4, fa4, fa3
-; RV64-NEXT: fld fa2, 48(sp)
; RV64-NEXT: fmin.d fa4, fa4, fa5
+; RV64-NEXT: fld fa2, 48(sp)
; RV64-NEXT: fcvt.lu.d a3, fa4, rtz
+; RV64-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; RV64-NEXT: vslide1down.vx v8, v10, a0
; RV64-NEXT: fmax.d fa4, fa2, fa3
; RV64-NEXT: fmin.d fa4, fa4, fa5
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-i2fp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-i2fp.ll
index 6ffa6ac250ed7..9c76b83d0974a 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-i2fp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-i2fp.ll
@@ -132,12 +132,12 @@ define <3 x float> @si2fp_v3i1_v3f32(<3 x i1> %x) {
define <3 x float> @si2fp_v3i7_v3f32(<3 x i7> %x) {
; ZVFH32-LABEL: si2fp_v3i7_v3f32:
; ZVFH32: # %bb.0:
-; ZVFH32-NEXT: lw a1, 4(a0)
-; ZVFH32-NEXT: lw a2, 0(a0)
-; ZVFH32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH32-NEXT: lw a1, 0(a0)
+; ZVFH32-NEXT: lw a2, 4(a0)
; ZVFH32-NEXT: lw a0, 8(a0)
-; ZVFH32-NEXT: vmv.v.x v8, a2
-; ZVFH32-NEXT: vslide1down.vx v8, v8, a1
+; ZVFH32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH32-NEXT: vmv.v.x v8, a1
+; ZVFH32-NEXT: vslide1down.vx v8, v8, a2
; ZVFH32-NEXT: vslide1down.vx v8, v8, a0
; ZVFH32-NEXT: vslidedown.vi v8, v8, 1
; ZVFH32-NEXT: vadd.vv v8, v8, v8
@@ -149,12 +149,12 @@ define <3 x float> @si2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFH64-LABEL: si2fp_v3i7_v3f32:
; ZVFH64: # %bb.0:
-; ZVFH64-NEXT: ld a1, 8(a0)
-; ZVFH64-NEXT: ld a2, 0(a0)
-; ZVFH64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH64-NEXT: ld a1, 0(a0)
+; ZVFH64-NEXT: ld a2, 8(a0)
; ZVFH64-NEXT: ld a0, 16(a0)
-; ZVFH64-NEXT: vmv.v.x v8, a2
-; ZVFH64-NEXT: vslide1down.vx v8, v8, a1
+; ZVFH64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH64-NEXT: vmv.v.x v8, a1
+; ZVFH64-NEXT: vslide1down.vx v8, v8, a2
; ZVFH64-NEXT: vslide1down.vx v8, v8, a0
; ZVFH64-NEXT: vslidedown.vi v8, v8, 1
; ZVFH64-NEXT: vadd.vv v8, v8, v8
@@ -166,12 +166,12 @@ define <3 x float> @si2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFHMIN32-LABEL: si2fp_v3i7_v3f32:
; ZVFHMIN32: # %bb.0:
-; ZVFHMIN32-NEXT: lw a1, 4(a0)
-; ZVFHMIN32-NEXT: lw a2, 0(a0)
-; ZVFHMIN32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN32-NEXT: lw a1, 0(a0)
+; ZVFHMIN32-NEXT: lw a2, 4(a0)
; ZVFHMIN32-NEXT: lw a0, 8(a0)
-; ZVFHMIN32-NEXT: vmv.v.x v8, a2
-; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a1
+; ZVFHMIN32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN32-NEXT: vmv.v.x v8, a1
+; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a2
; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a0
; ZVFHMIN32-NEXT: vslidedown.vi v8, v8, 1
; ZVFHMIN32-NEXT: vadd.vv v8, v8, v8
@@ -183,12 +183,12 @@ define <3 x float> @si2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFHMIN64-LABEL: si2fp_v3i7_v3f32:
; ZVFHMIN64: # %bb.0:
-; ZVFHMIN64-NEXT: ld a1, 8(a0)
-; ZVFHMIN64-NEXT: ld a2, 0(a0)
-; ZVFHMIN64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN64-NEXT: ld a1, 0(a0)
+; ZVFHMIN64-NEXT: ld a2, 8(a0)
; ZVFHMIN64-NEXT: ld a0, 16(a0)
-; ZVFHMIN64-NEXT: vmv.v.x v8, a2
-; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a1
+; ZVFHMIN64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN64-NEXT: vmv.v.x v8, a1
+; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a2
; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a0
; ZVFHMIN64-NEXT: vslidedown.vi v8, v8, 1
; ZVFHMIN64-NEXT: vadd.vv v8, v8, v8
@@ -205,12 +205,12 @@ define <3 x float> @si2fp_v3i7_v3f32(<3 x i7> %x) {
define <3 x float> @ui2fp_v3i7_v3f32(<3 x i7> %x) {
; ZVFH32-LABEL: ui2fp_v3i7_v3f32:
; ZVFH32: # %bb.0:
-; ZVFH32-NEXT: lw a1, 4(a0)
-; ZVFH32-NEXT: lw a2, 0(a0)
-; ZVFH32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH32-NEXT: lw a1, 0(a0)
+; ZVFH32-NEXT: lw a2, 4(a0)
; ZVFH32-NEXT: lw a0, 8(a0)
-; ZVFH32-NEXT: vmv.v.x v8, a2
-; ZVFH32-NEXT: vslide1down.vx v8, v8, a1
+; ZVFH32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH32-NEXT: vmv.v.x v8, a1
+; ZVFH32-NEXT: vslide1down.vx v8, v8, a2
; ZVFH32-NEXT: vslide1down.vx v8, v8, a0
; ZVFH32-NEXT: vslidedown.vi v8, v8, 1
; ZVFH32-NEXT: li a0, 127
@@ -222,12 +222,12 @@ define <3 x float> @ui2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFH64-LABEL: ui2fp_v3i7_v3f32:
; ZVFH64: # %bb.0:
-; ZVFH64-NEXT: ld a1, 8(a0)
-; ZVFH64-NEXT: ld a2, 0(a0)
-; ZVFH64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH64-NEXT: ld a1, 0(a0)
+; ZVFH64-NEXT: ld a2, 8(a0)
; ZVFH64-NEXT: ld a0, 16(a0)
-; ZVFH64-NEXT: vmv.v.x v8, a2
-; ZVFH64-NEXT: vslide1down.vx v8, v8, a1
+; ZVFH64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFH64-NEXT: vmv.v.x v8, a1
+; ZVFH64-NEXT: vslide1down.vx v8, v8, a2
; ZVFH64-NEXT: vslide1down.vx v8, v8, a0
; ZVFH64-NEXT: vslidedown.vi v8, v8, 1
; ZVFH64-NEXT: li a0, 127
@@ -239,12 +239,12 @@ define <3 x float> @ui2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFHMIN32-LABEL: ui2fp_v3i7_v3f32:
; ZVFHMIN32: # %bb.0:
-; ZVFHMIN32-NEXT: lw a1, 4(a0)
-; ZVFHMIN32-NEXT: lw a2, 0(a0)
-; ZVFHMIN32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN32-NEXT: lw a1, 0(a0)
+; ZVFHMIN32-NEXT: lw a2, 4(a0)
; ZVFHMIN32-NEXT: lw a0, 8(a0)
-; ZVFHMIN32-NEXT: vmv.v.x v8, a2
-; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a1
+; ZVFHMIN32-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN32-NEXT: vmv.v.x v8, a1
+; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a2
; ZVFHMIN32-NEXT: vslide1down.vx v8, v8, a0
; ZVFHMIN32-NEXT: vslidedown.vi v8, v8, 1
; ZVFHMIN32-NEXT: li a0, 127
@@ -256,12 +256,12 @@ define <3 x float> @ui2fp_v3i7_v3f32(<3 x i7> %x) {
;
; ZVFHMIN64-LABEL: ui2fp_v3i7_v3f32:
; ZVFHMIN64: # %bb.0:
-; ZVFHMIN64-NEXT: ld a1, 8(a0)
-; ZVFHMIN64-NEXT: ld a2, 0(a0)
-; ZVFHMIN64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN64-NEXT: ld a1, 0(a0)
+; ZVFHMIN64-NEXT: ld a2, 8(a0)
; ZVFHMIN64-NEXT: ld a0, 16(a0)
-; ZVFHMIN64-NEXT: vmv.v.x v8, a2
-; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a1
+; ZVFHMIN64-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
+; ZVFHMIN64-NEXT: vmv.v.x v8, a1
+; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a2
; ZVFHMIN64-NEXT: vslide1down.vx v8, v8, a0
; ZVFHMIN64-NEXT: vslidedown.vi v8, v8, 1
; ZVFHMIN64-NEXT: li a0, 127
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
index 592ce6fc5be0b..4f4f0a09de748 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-buildvec.ll
@@ -1183,38 +1183,38 @@ define <8 x i64> @v8xi64_exact_undef_prefix(i64 %a, i64 %b, i64 %c, i64 %d) vsca
define <16 x i8> @buildvec_v16i8_loads_contigous(ptr %p) {
; CHECK-LABEL: buildvec_v16i8_loads_contigous:
; CHECK: # %bb.0:
-; CHECK-NEXT: lbu a1, 1(a0)
-; CHECK-NEXT: lbu a2, 2(a0)
-; CHECK-NEXT: lbu a3, 3(a0)
-; CHECK-NEXT: lbu a4, 4(a0)
-; CHECK-NEXT: lbu a5, 5(a0)
-; CHECK-NEXT: lbu a6, 6(a0)
-; CHECK-NEXT: lbu a7, 7(a0)
-; CHECK-NEXT: lbu t0, 9(a0)
-; CHECK-NEXT: lbu t1, 10(a0)
-; CHECK-NEXT: lbu t2, 11(a0)
-; CHECK-NEXT: lbu t3, 12(a0)
-; CHECK-NEXT: lbu t4, 13(a0)
-; CHECK-NEXT: lbu t5, 14(a0)
-; CHECK-NEXT: lbu t6, 15(a0)
+; CHECK-NEXT: addi a1, a0, 8
+; CHECK-NEXT: lbu a2, 1(a0)
+; CHECK-NEXT: lbu a3, 2(a0)
+; CHECK-NEXT: lbu a4, 3(a0)
+; CHECK-NEXT: lbu a5, 4(a0)
+; CHECK-NEXT: lbu a6, 5(a0)
+; CHECK-NEXT: lbu a7, 6(a0)
+; CHECK-NEXT: lbu t0, 7(a0)
+; CHECK-NEXT: lbu t1, 9(a0)
+; CHECK-NEXT: lbu t2, 10(a0)
+; CHECK-NEXT: lbu t3, 11(a0)
+; CHECK-NEXT: lbu t4, 12(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a0), zero
-; CHECK-NEXT: addi a0, a0, 8
-; CHECK-NEXT: vslide1down.vx v8, v8, a1
+; CHECK-NEXT: lbu t5, 13(a0)
+; CHECK-NEXT: lbu t6, 14(a0)
+; CHECK-NEXT: lbu a0, 15(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a2
; CHECK-NEXT: vslide1down.vx v8, v8, a3
; CHECK-NEXT: vslide1down.vx v8, v8, a4
-; CHECK-NEXT: vlse8.v v9, (a0), zero
; CHECK-NEXT: vslide1down.vx v8, v8, a5
+; CHECK-NEXT: vlse8.v v9, (a1), zero
; CHECK-NEXT: vslide1down.vx v8, v8, a6
-; CHECK-NEXT: vslide1down.vx v10, v8, a7
-; CHECK-NEXT: vslide1down.vx v8, v9, t0
-; CHECK-NEXT: vslide1down.vx v8, v8, t1
+; CHECK-NEXT: vslide1down.vx v8, v8, a7
+; CHECK-NEXT: vslide1down.vx v10, v8, t0
+; CHECK-NEXT: vslide1down.vx v8, v9, t1
; CHECK-NEXT: vslide1down.vx v8, v8, t2
; CHECK-NEXT: vslide1down.vx v8, v8, t3
; CHECK-NEXT: vslide1down.vx v8, v8, t4
; CHECK-NEXT: vslide1down.vx v8, v8, t5
; CHECK-NEXT: vslide1down.vx v8, v8, t6
+; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: li a0, 255
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
@@ -1277,38 +1277,38 @@ define <16 x i8> @buildvec_v16i8_loads_contigous(ptr %p) {
define <16 x i8> @buildvec_v16i8_loads_gather(ptr %p) {
; CHECK-LABEL: buildvec_v16i8_loads_gather:
; CHECK: # %bb.0:
-; CHECK-NEXT: lbu a1, 1(a0)
-; CHECK-NEXT: lbu a2, 22(a0)
-; CHECK-NEXT: lbu a3, 31(a0)
-; CHECK-NEXT: lbu a4, 44(a0)
-; CHECK-NEXT: lbu a5, 55(a0)
-; CHECK-NEXT: lbu a6, 623(a0)
-; CHECK-NEXT: lbu a7, 75(a0)
-; CHECK-NEXT: lbu t0, 93(a0)
-; CHECK-NEXT: lbu t1, 105(a0)
-; CHECK-NEXT: lbu t2, 161(a0)
-; CHECK-NEXT: lbu t3, 124(a0)
-; CHECK-NEXT: lbu t4, 163(a0)
-; CHECK-NEXT: lbu t5, 144(a0)
-; CHECK-NEXT: lbu t6, 154(a0)
+; CHECK-NEXT: addi a1, a0, 82
+; CHECK-NEXT: lbu a2, 1(a0)
+; CHECK-NEXT: lbu a3, 22(a0)
+; CHECK-NEXT: lbu a4, 31(a0)
+; CHECK-NEXT: lbu a5, 44(a0)
+; CHECK-NEXT: lbu a6, 55(a0)
+; CHECK-NEXT: lbu a7, 623(a0)
+; CHECK-NEXT: lbu t0, 75(a0)
+; CHECK-NEXT: lbu t1, 93(a0)
+; CHECK-NEXT: lbu t2, 105(a0)
+; CHECK-NEXT: lbu t3, 161(a0)
+; CHECK-NEXT: lbu t4, 124(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a0), zero
-; CHECK-NEXT: addi a0, a0, 82
-; CHECK-NEXT: vslide1down.vx v8, v8, a1
+; CHECK-NEXT: lbu t5, 163(a0)
+; CHECK-NEXT: lbu t6, 144(a0)
+; CHECK-NEXT: lbu a0, 154(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a2
; CHECK-NEXT: vslide1down.vx v8, v8, a3
; CHECK-NEXT: vslide1down.vx v8, v8, a4
-; CHECK-NEXT: vlse8.v v9, (a0), zero
; CHECK-NEXT: vslide1down.vx v8, v8, a5
+; CHECK-NEXT: vlse8.v v9, (a1), zero
; CHECK-NEXT: vslide1down.vx v8, v8, a6
-; CHECK-NEXT: vslide1down.vx v10, v8, a7
-; CHECK-NEXT: vslide1down.vx v8, v9, t0
-; CHECK-NEXT: vslide1down.vx v8, v8, t1
+; CHECK-NEXT: vslide1down.vx v8, v8, a7
+; CHECK-NEXT: vslide1down.vx v10, v8, t0
+; CHECK-NEXT: vslide1down.vx v8, v9, t1
; CHECK-NEXT: vslide1down.vx v8, v8, t2
; CHECK-NEXT: vslide1down.vx v8, v8, t3
; CHECK-NEXT: vslide1down.vx v8, v8, t4
; CHECK-NEXT: vslide1down.vx v8, v8, t5
; CHECK-NEXT: vslide1down.vx v8, v8, t6
+; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: li a0, 255
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
@@ -1375,17 +1375,17 @@ define <16 x i8> @buildvec_v16i8_undef_low_half(ptr %p) {
; CHECK-NEXT: lbu a3, 105(a0)
; CHECK-NEXT: lbu a4, 161(a0)
; CHECK-NEXT: lbu a5, 124(a0)
-; CHECK-NEXT: lbu a6, 163(a0)
-; CHECK-NEXT: lbu a7, 144(a0)
-; CHECK-NEXT: lbu a0, 154(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a1), zero
+; CHECK-NEXT: lbu a1, 163(a0)
+; CHECK-NEXT: lbu a6, 144(a0)
+; CHECK-NEXT: lbu a0, 154(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a2
; CHECK-NEXT: vslide1down.vx v8, v8, a3
; CHECK-NEXT: vslide1down.vx v8, v8, a4
; CHECK-NEXT: vslide1down.vx v8, v8, a5
+; CHECK-NEXT: vslide1down.vx v8, v8, a1
; CHECK-NEXT: vslide1down.vx v8, v8, a6
-; CHECK-NEXT: vslide1down.vx v8, v8, a7
; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: ret
%p9 = getelementptr i8, ptr %p, i32 82
@@ -1424,18 +1424,18 @@ define <16 x i8> @buildvec_v16i8_undef_high_half(ptr %p) {
; CHECK-NEXT: lbu a2, 22(a0)
; CHECK-NEXT: lbu a3, 31(a0)
; CHECK-NEXT: lbu a4, 44(a0)
-; CHECK-NEXT: lbu a5, 55(a0)
-; CHECK-NEXT: lbu a6, 623(a0)
-; CHECK-NEXT: lbu a7, 75(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a0), zero
+; CHECK-NEXT: lbu a5, 55(a0)
+; CHECK-NEXT: lbu a6, 623(a0)
+; CHECK-NEXT: lbu a0, 75(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a1
; CHECK-NEXT: vslide1down.vx v8, v8, a2
; CHECK-NEXT: vslide1down.vx v8, v8, a3
; CHECK-NEXT: vslide1down.vx v8, v8, a4
; CHECK-NEXT: vslide1down.vx v8, v8, a5
; CHECK-NEXT: vslide1down.vx v8, v8, a6
-; CHECK-NEXT: vslide1down.vx v8, v8, a7
+; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: vslidedown.vi v8, v8, 8
; CHECK-NEXT: ret
%p2 = getelementptr i8, ptr %p, i32 1
@@ -1470,24 +1470,24 @@ define <16 x i8> @buildvec_v16i8_undef_edges(ptr %p) {
; CHECK-LABEL: buildvec_v16i8_undef_edges:
; CHECK: # %bb.0:
; CHECK-NEXT: addi a1, a0, 31
-; CHECK-NEXT: lbu a2, 44(a0)
-; CHECK-NEXT: lbu a3, 55(a0)
-; CHECK-NEXT: lbu a4, 623(a0)
-; CHECK-NEXT: lbu a5, 75(a0)
-; CHECK-NEXT: lbu a6, 93(a0)
-; CHECK-NEXT: lbu a7, 105(a0)
-; CHECK-NEXT: lbu t0, 161(a0)
+; CHECK-NEXT: addi a2, a0, 82
+; CHECK-NEXT: lbu a3, 44(a0)
+; CHECK-NEXT: lbu a4, 55(a0)
+; CHECK-NEXT: lbu a5, 623(a0)
+; CHECK-NEXT: lbu a6, 75(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a1), zero
-; CHECK-NEXT: addi a0, a0, 82
-; CHECK-NEXT: vslide1down.vx v8, v8, a2
-; CHECK-NEXT: vlse8.v v9, (a0), zero
+; CHECK-NEXT: lbu a1, 93(a0)
+; CHECK-NEXT: lbu a7, 105(a0)
+; CHECK-NEXT: lbu a0, 161(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a3
+; CHECK-NEXT: vlse8.v v9, (a2), zero
; CHECK-NEXT: vslide1down.vx v8, v8, a4
-; CHECK-NEXT: vslide1down.vx v10, v8, a5
-; CHECK-NEXT: vslide1down.vx v8, v9, a6
+; CHECK-NEXT: vslide1down.vx v8, v8, a5
+; CHECK-NEXT: vslide1down.vx v10, v8, a6
+; CHECK-NEXT: vslide1down.vx v8, v9, a1
; CHECK-NEXT: vslide1down.vx v8, v8, a7
-; CHECK-NEXT: vslide1down.vx v8, v8, t0
+; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: vslidedown.vi v8, v8, 4
; CHECK-NEXT: li a0, 255
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
@@ -1530,30 +1530,30 @@ define <16 x i8> @buildvec_v16i8_undef_edges(ptr %p) {
define <16 x i8> @buildvec_v16i8_loads_undef_scattered(ptr %p) {
; CHECK-LABEL: buildvec_v16i8_loads_undef_scattered:
; CHECK: # %bb.0:
-; CHECK-NEXT: lbu a1, 1(a0)
-; CHECK-NEXT: lbu a2, 44(a0)
-; CHECK-NEXT: lbu a3, 55(a0)
-; CHECK-NEXT: lbu a4, 75(a0)
-; CHECK-NEXT: lbu a5, 93(a0)
-; CHECK-NEXT: lbu a6, 124(a0)
-; CHECK-NEXT: lbu a7, 144(a0)
-; CHECK-NEXT: lbu t0, 154(a0)
+; CHECK-NEXT: addi a1, a0, 82
+; CHECK-NEXT: lbu a2, 1(a0)
+; CHECK-NEXT: lbu a3, 44(a0)
+; CHECK-NEXT: lbu a4, 55(a0)
+; CHECK-NEXT: lbu a5, 75(a0)
+; CHECK-NEXT: lbu a6, 93(a0)
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT: vlse8.v v8, (a0), zero
-; CHECK-NEXT: addi a0, a0, 82
-; CHECK-NEXT: vslide1down.vx v8, v8, a1
-; CHECK-NEXT: vslidedown.vi v8, v8, 2
+; CHECK-NEXT: lbu a7, 124(a0)
+; CHECK-NEXT: lbu t0, 144(a0)
+; CHECK-NEXT: lbu a0, 154(a0)
; CHECK-NEXT: vslide1down.vx v8, v8, a2
-; CHECK-NEXT: vlse8.v v9, (a0), zero
+; CHECK-NEXT: vslidedown.vi v8, v8, 2
; CHECK-NEXT: vslide1down.vx v8, v8, a3
+; CHECK-NEXT: vlse8.v v9, (a1), zero
+; CHECK-NEXT: vslide1down.vx v8, v8, a4
; CHECK-NEXT: vslidedown.vi v8, v8, 1
-; CHECK-NEXT: vslide1down.vx v10, v8, a4
-; CHECK-NEXT: vslide1down.vx v8, v9, a5
+; CHECK-NEXT: vslide1down.vx v10, v8, a5
+; CHECK-NEXT: vslide1down.vx v8, v9, a6
; CHECK-NEXT: vslidedown.vi v8, v8, 2
-; CHECK-NEXT: vslide1down.vx v8, v8, a6
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vslide1down.vx v8, v8, a7
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vslide1down.vx v8, v8, t0
+; CHECK-NEXT: vslide1down.vx v8, v8, a0
; CHECK-NEXT: li a0, 255
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access-zve32x.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access-zve32x.ll
index 8acc70faaa1fc..eb95d86e34045 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access-zve32x.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access-zve32x.ll
@@ -7,25 +7,23 @@
define <4 x i1> @load_large_vector(ptr %p) {
; ZVE32X-LABEL: load_large_vector:
; ZVE32X: # %bb.0:
-; ZVE32X-NEXT: ld a1, 80(a0)
-; ZVE32X-NEXT: ld a2, 72(a0)
-; ZVE32X-NEXT: ld a3, 56(a0)
-; ZVE32X-NEXT: ld a4, 32(a0)
-; ZVE32X-NEXT: ld a5, 24(a0)
-; ZVE32X-NEXT: ld a6, 48(a0)
-; ZVE32X-NEXT: ld a7, 8(a0)
-; ZVE32X-NEXT: ld a0, 0(a0)
-; ZVE32X-NEXT: xor a4, a5, a4
-; ZVE32X-NEXT: snez a4, a4
+; ZVE32X-NEXT: ld a1, 56(a0)
+; ZVE32X-NEXT: ld a2, 32(a0)
+; ZVE32X-NEXT: ld a3, 24(a0)
+; ZVE32X-NEXT: ld a4, 48(a0)
+; ZVE32X-NEXT: ld a5, 8(a0)
+; ZVE32X-NEXT: ld a6, 0(a0)
+; ZVE32X-NEXT: xor a2, a3, a2
+; ZVE32X-NEXT: snez a2, a2
; ZVE32X-NEXT: vsetivli zero, 1, e8, mf4, ta, ma
-; ZVE32X-NEXT: vmv.s.x v8, a4
+; ZVE32X-NEXT: vmv.s.x v8, a2
; ZVE32X-NEXT: vand.vi v8, v8, 1
; ZVE32X-NEXT: vmsne.vi v0, v8, 0
; ZVE32X-NEXT: vmv.s.x v8, zero
; ZVE32X-NEXT: vmerge.vim v9, v8, 1, v0
-; ZVE32X-NEXT: xor a0, a0, a7
-; ZVE32X-NEXT: snez a0, a0
-; ZVE32X-NEXT: vmv.s.x v10, a0
+; ZVE32X-NEXT: xor a2, a6, a5
+; ZVE32X-NEXT: snez a2, a2
+; ZVE32X-NEXT: vmv.s.x v10, a2
; ZVE32X-NEXT: vand.vi v10, v10, 1
; ZVE32X-NEXT: vmsne.vi v0, v10, 0
; ZVE32X-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
@@ -35,21 +33,23 @@ define <4 x i1> @load_large_vector(ptr %p) {
; ZVE32X-NEXT: vslideup.vi v11, v9, 1
; ZVE32X-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; ZVE32X-NEXT: vmsne.vi v0, v11, 0
+; ZVE32X-NEXT: ld a2, 80(a0)
; ZVE32X-NEXT: vmerge.vim v9, v10, 1, v0
-; ZVE32X-NEXT: xor a0, a6, a3
-; ZVE32X-NEXT: snez a0, a0
-; ZVE32X-NEXT: vmv.s.x v11, a0
+; ZVE32X-NEXT: xor a1, a4, a1
+; ZVE32X-NEXT: snez a1, a1
+; ZVE32X-NEXT: vmv.s.x v11, a1
; ZVE32X-NEXT: vsetivli zero, 1, e8, mf4, ta, ma
; ZVE32X-NEXT: vand.vi v11, v11, 1
; ZVE32X-NEXT: vmsne.vi v0, v11, 0
+; ZVE32X-NEXT: ld a0, 72(a0)
; ZVE32X-NEXT: vmerge.vim v11, v8, 1, v0
; ZVE32X-NEXT: vsetivli zero, 3, e8, mf4, tu, ma
; ZVE32X-NEXT: vslideup.vi v9, v11, 2
; ZVE32X-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; ZVE32X-NEXT: vmsne.vi v0, v9, 0
; ZVE32X-NEXT: vmerge.vim v9, v10, 1, v0
-; ZVE32X-NEXT: xor a1, a2, a1
-; ZVE32X-NEXT: snez a0, a1
+; ZVE32X-NEXT: xor a0, a0, a2
+; ZVE32X-NEXT: snez a0, a0
; ZVE32X-NEXT: vmv.s.x v10, a0
; ZVE32X-NEXT: vsetivli zero, 1, e8, mf4, ta, ma
; ZVE32X-NEXT: vand.vi v10, v10, 1
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-lrint.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-lrint.ll
index 35baa6808db60..e2075e074179c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-lrint.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-lrint.ll
@@ -812,14 +812,14 @@ define <8 x iXLen> @lrint_v8f64(<8 x double> %x) {
; RV32-NEXT: vslide1down.vx v10, v10, a0
; RV32-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; RV32-NEXT: vslidedown.vi v8, v8, 3
-; RV32-NEXT: vfmv.f.s fa5, v8
-; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
-; RV32-NEXT: fld fa4, 32(sp)
+; RV32-NEXT: fld fa5, 32(sp)
+; RV32-NEXT: vfmv.f.s fa4, v8
; RV32-NEXT: fld fa3, 40(sp)
-; RV32-NEXT: fcvt.w.d a0, fa5
+; RV32-NEXT: fcvt.w.d a0, fa4
+; RV32-NEXT: fcvt.w.d a1, fa5
; RV32-NEXT: fld fa5, 48(sp)
-; RV32-NEXT: fcvt.w.d a1, fa4
; RV32-NEXT: fcvt.w.d a2, fa3
+; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV32-NEXT: vslide1down.vx v8, v10, a0
; RV32-NEXT: fcvt.w.d a0, fa5
; RV32-NEXT: fld fa5, 56(sp)
@@ -865,14 +865,14 @@ define <8 x iXLen> @lrint_v8f64(<8 x double> %x) {
; RV64-i32-NEXT: vslide1down.vx v10, v10, a0
; RV64-i32-NEXT: vsetivli zero, 1, e64, m2, ta, ma
; RV64-i32-NEXT: vslidedown.vi v8, v8, 3
-; RV64-i32-NEXT: vfmv.f.s fa5, v8
-; RV64-i32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
-; RV64-i32-NEXT: fld fa4, 32(sp)
+; RV64-i32-NEXT: fld fa5, 32(sp)
+; RV64-i32-NEXT: vfmv.f.s fa4, v8
; RV64-i32-NEXT: fld fa3, 40(sp)
-; RV64-i32-NEXT: fcvt.l.d a0, fa5
+; RV64-i32-NEXT: fcvt.l.d a0, fa4
+; RV64-i32-NEXT: fcvt.l.d a1, fa5
; RV64-i32-NEXT: fld fa5, 48(sp)
-; RV64-i32-NEXT: fcvt.l.d a1, fa4
; RV64-i32-NEXT: fcvt.l.d a2, fa3
+; RV64-i32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV64-i32-NEXT: vslide1down.vx v8, v10, a0
; RV64-i32-NEXT: fcvt.l.d a0, fa5
; RV64-i32-NEXT: fld fa5, 56(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll
index f42f32e246585..08cad29ab1b88 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-gather.ll
@@ -519,17 +519,17 @@ define <4 x i8> @mgather_truemask_v4i8(<4 x ptr> %ptrs, <4 x i8> %passthru) {
; RV64ZVE32F-LABEL: mgather_truemask_v4i8:
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: ld a1, 8(a0)
-; RV64ZVE32F-NEXT: ld a2, 16(a0)
+; RV64ZVE32F-NEXT: ld a2, 0(a0)
; RV64ZVE32F-NEXT: ld a3, 24(a0)
-; RV64ZVE32F-NEXT: ld a0, 0(a0)
+; RV64ZVE32F-NEXT: ld a0, 16(a0)
; RV64ZVE32F-NEXT: lbu a1, 0(a1)
-; RV64ZVE32F-NEXT: lbu a2, 0(a2)
-; RV64ZVE32F-NEXT: lbu a3, 0(a3)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
-; RV64ZVE32F-NEXT: vlse8.v v8, (a0), zero
+; RV64ZVE32F-NEXT: vlse8.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lbu a0, 0(a0)
+; RV64ZVE32F-NEXT: lbu a2, 0(a3)
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
; RV64ZVE32F-NEXT: ret
%v = call <4 x i8> @llvm.masked.gather.v4i8.v4p0(<4 x ptr> %ptrs, i32 1, <4 x i1> splat (i1 1), <4 x i8> %passthru)
ret <4 x i8> %v
@@ -1208,17 +1208,17 @@ define <4 x i16> @mgather_truemask_v4i16(<4 x ptr> %ptrs, <4 x i16> %passthru) {
; RV64ZVE32F-LABEL: mgather_truemask_v4i16:
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: ld a1, 8(a0)
-; RV64ZVE32F-NEXT: ld a2, 16(a0)
+; RV64ZVE32F-NEXT: ld a2, 0(a0)
; RV64ZVE32F-NEXT: ld a3, 24(a0)
-; RV64ZVE32F-NEXT: ld a0, 0(a0)
+; RV64ZVE32F-NEXT: ld a0, 16(a0)
; RV64ZVE32F-NEXT: lh a1, 0(a1)
-; RV64ZVE32F-NEXT: lh a2, 0(a2)
-; RV64ZVE32F-NEXT: lh a3, 0(a3)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
-; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lh a0, 0(a0)
+; RV64ZVE32F-NEXT: lh a2, 0(a3)
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
; RV64ZVE32F-NEXT: ret
%v = call <4 x i16> @llvm.masked.gather.v4i16.v4p0(<4 x ptr> %ptrs, i32 2, <4 x i1> splat (i1 1), <4 x i16> %passthru)
ret <4 x i16> %v
@@ -2257,17 +2257,17 @@ define <4 x i32> @mgather_truemask_v4i32(<4 x ptr> %ptrs, <4 x i32> %passthru) {
; RV64ZVE32F-LABEL: mgather_truemask_v4i32:
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: ld a1, 8(a0)
-; RV64ZVE32F-NEXT: ld a2, 16(a0)
+; RV64ZVE32F-NEXT: ld a2, 0(a0)
; RV64ZVE32F-NEXT: ld a3, 24(a0)
-; RV64ZVE32F-NEXT: ld a0, 0(a0)
+; RV64ZVE32F-NEXT: ld a0, 16(a0)
; RV64ZVE32F-NEXT: lw a1, 0(a1)
-; RV64ZVE32F-NEXT: lw a2, 0(a2)
-; RV64ZVE32F-NEXT: lw a3, 0(a3)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma
-; RV64ZVE32F-NEXT: vlse32.v v8, (a0), zero
+; RV64ZVE32F-NEXT: vlse32.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lw a0, 0(a0)
+; RV64ZVE32F-NEXT: lw a2, 0(a3)
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
; RV64ZVE32F-NEXT: ret
%v = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> %ptrs, i32 4, <4 x i1> splat (i1 1), <4 x i32> %passthru)
ret <4 x i32> %v
@@ -6589,16 +6589,16 @@ define <8 x i64> @mgather_baseidx_v8i64(ptr %base, <8 x i64> %idxs, <8 x i1> %m,
; RV32ZVE32F-NEXT: lw a4, 56(a2)
; RV32ZVE32F-NEXT: lw a5, 48(a2)
; RV32ZVE32F-NEXT: lw a6, 40(a2)
-; RV32ZVE32F-NEXT: lw a7, 32(a2)
-; RV32ZVE32F-NEXT: lw t0, 24(a2)
-; RV32ZVE32F-NEXT: lw t1, 16(a2)
-; RV32ZVE32F-NEXT: lw t2, 8(a2)
+; RV32ZVE32F-NEXT: lw a7, 8(a2)
; RV32ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV32ZVE32F-NEXT: vlse32.v v8, (a2), zero
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t2
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t1
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t0
+; RV32ZVE32F-NEXT: lw t0, 16(a2)
+; RV32ZVE32F-NEXT: lw t1, 24(a2)
+; RV32ZVE32F-NEXT: lw a2, 32(a2)
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t0
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t1
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a2
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a6
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a5
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a4
@@ -7017,14 +7017,14 @@ define <4 x half> @mgather_truemask_v4f16(<4 x ptr> %ptrs, <4 x half> %passthru)
; RV64ZVE32F-LABEL: mgather_truemask_v4f16:
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: ld a1, 8(a0)
-; RV64ZVE32F-NEXT: ld a2, 16(a0)
+; RV64ZVE32F-NEXT: ld a2, 0(a0)
; RV64ZVE32F-NEXT: ld a3, 24(a0)
-; RV64ZVE32F-NEXT: ld a0, 0(a0)
+; RV64ZVE32F-NEXT: ld a0, 16(a0)
; RV64ZVE32F-NEXT: flh fa5, 0(a1)
-; RV64ZVE32F-NEXT: flh fa4, 0(a2)
-; RV64ZVE32F-NEXT: flh fa3, 0(a3)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
-; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: flh fa4, 0(a0)
+; RV64ZVE32F-NEXT: flh fa3, 0(a3)
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa5
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa4
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa3
@@ -7940,14 +7940,14 @@ define <4 x float> @mgather_truemask_v4f32(<4 x ptr> %ptrs, <4 x float> %passthr
; RV64ZVE32F-LABEL: mgather_truemask_v4f32:
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: ld a1, 8(a0)
-; RV64ZVE32F-NEXT: ld a2, 16(a0)
+; RV64ZVE32F-NEXT: ld a2, 0(a0)
; RV64ZVE32F-NEXT: ld a3, 24(a0)
-; RV64ZVE32F-NEXT: ld a0, 0(a0)
+; RV64ZVE32F-NEXT: ld a0, 16(a0)
; RV64ZVE32F-NEXT: flw fa5, 0(a1)
-; RV64ZVE32F-NEXT: flw fa4, 0(a2)
-; RV64ZVE32F-NEXT: flw fa3, 0(a3)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma
-; RV64ZVE32F-NEXT: vlse32.v v8, (a0), zero
+; RV64ZVE32F-NEXT: vlse32.v v8, (a2), zero
+; RV64ZVE32F-NEXT: flw fa4, 0(a0)
+; RV64ZVE32F-NEXT: flw fa3, 0(a3)
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa5
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa4
; RV64ZVE32F-NEXT: vfslide1down.vf v8, v8, fa3
@@ -11632,16 +11632,16 @@ define <8 x double> @mgather_baseidx_v8f64(ptr %base, <8 x i64> %idxs, <8 x i1>
; RV32ZVE32F-NEXT: lw a3, 56(a2)
; RV32ZVE32F-NEXT: lw a4, 48(a2)
; RV32ZVE32F-NEXT: lw a5, 40(a2)
-; RV32ZVE32F-NEXT: lw a6, 32(a2)
-; RV32ZVE32F-NEXT: lw a7, 24(a2)
-; RV32ZVE32F-NEXT: lw t0, 16(a2)
-; RV32ZVE32F-NEXT: lw t1, 8(a2)
+; RV32ZVE32F-NEXT: lw a6, 8(a2)
; RV32ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV32ZVE32F-NEXT: vlse32.v v8, (a2), zero
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t1
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t0
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV32ZVE32F-NEXT: lw a7, 16(a2)
+; RV32ZVE32F-NEXT: lw t0, 24(a2)
+; RV32ZVE32F-NEXT: lw a2, 32(a2)
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t0
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a2
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a5
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a4
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a3
@@ -12881,22 +12881,22 @@ define <8 x i16> @mgather_strided_2xSEW(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_strided_2xSEW:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 2(a0)
-; RV64ZVE32F-NEXT: lh a2, 8(a0)
-; RV64ZVE32F-NEXT: lh a3, 10(a0)
-; RV64ZVE32F-NEXT: lh a4, 18(a0)
-; RV64ZVE32F-NEXT: lh a5, 24(a0)
-; RV64ZVE32F-NEXT: lh a6, 26(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 16
+; RV64ZVE32F-NEXT: lh a2, 2(a0)
+; RV64ZVE32F-NEXT: lh a3, 8(a0)
+; RV64ZVE32F-NEXT: lh a4, 10(a0)
+; RV64ZVE32F-NEXT: lh a5, 18(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 16
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 24(a0)
+; RV64ZVE32F-NEXT: lh a0, 26(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -12925,23 +12925,23 @@ define <8 x i16> @mgather_strided_2xSEW_with_offset(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_strided_2xSEW_with_offset:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: addi a1, a0, 4
-; RV64ZVE32F-NEXT: lh a2, 6(a0)
-; RV64ZVE32F-NEXT: lh a3, 12(a0)
-; RV64ZVE32F-NEXT: lh a4, 14(a0)
-; RV64ZVE32F-NEXT: lh a5, 22(a0)
-; RV64ZVE32F-NEXT: lh a6, 28(a0)
-; RV64ZVE32F-NEXT: lh a7, 30(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 20
+; RV64ZVE32F-NEXT: addi a2, a0, 4
+; RV64ZVE32F-NEXT: lh a3, 6(a0)
+; RV64ZVE32F-NEXT: lh a4, 12(a0)
+; RV64ZVE32F-NEXT: lh a5, 14(a0)
+; RV64ZVE32F-NEXT: lh a6, 22(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; RV64ZVE32F-NEXT: vlse16.v v8, (a1), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 20
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lh a2, 28(a0)
+; RV64ZVE32F-NEXT: lh a0, 30(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -12970,23 +12970,23 @@ define <8 x i16> @mgather_reverse_unit_strided_2xSEW(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_reverse_unit_strided_2xSEW:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: addi a1, a0, 28
-; RV64ZVE32F-NEXT: lh a2, 30(a0)
-; RV64ZVE32F-NEXT: lh a3, 24(a0)
-; RV64ZVE32F-NEXT: lh a4, 26(a0)
-; RV64ZVE32F-NEXT: lh a5, 22(a0)
-; RV64ZVE32F-NEXT: lh a6, 16(a0)
-; RV64ZVE32F-NEXT: lh a7, 18(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 20
+; RV64ZVE32F-NEXT: addi a2, a0, 28
+; RV64ZVE32F-NEXT: lh a3, 30(a0)
+; RV64ZVE32F-NEXT: lh a4, 24(a0)
+; RV64ZVE32F-NEXT: lh a5, 26(a0)
+; RV64ZVE32F-NEXT: lh a6, 22(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; RV64ZVE32F-NEXT: vlse16.v v8, (a1), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 20
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lh a2, 16(a0)
+; RV64ZVE32F-NEXT: lh a0, 18(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13015,23 +13015,23 @@ define <8 x i16> @mgather_reverse_strided_2xSEW(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_reverse_strided_2xSEW:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: addi a1, a0, 28
-; RV64ZVE32F-NEXT: lh a2, 30(a0)
-; RV64ZVE32F-NEXT: lh a3, 20(a0)
-; RV64ZVE32F-NEXT: lh a4, 22(a0)
-; RV64ZVE32F-NEXT: lh a5, 14(a0)
-; RV64ZVE32F-NEXT: lh a6, 4(a0)
-; RV64ZVE32F-NEXT: lh a7, 6(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 12
+; RV64ZVE32F-NEXT: addi a2, a0, 28
+; RV64ZVE32F-NEXT: lh a3, 30(a0)
+; RV64ZVE32F-NEXT: lh a4, 20(a0)
+; RV64ZVE32F-NEXT: lh a5, 22(a0)
+; RV64ZVE32F-NEXT: lh a6, 14(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; RV64ZVE32F-NEXT: vlse16.v v8, (a1), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 12
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lh a2, 4(a0)
+; RV64ZVE32F-NEXT: lh a0, 6(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13059,22 +13059,22 @@ define <8 x i16> @mgather_gather_2xSEW(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_gather_2xSEW:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 2(a0)
-; RV64ZVE32F-NEXT: lh a2, 16(a0)
-; RV64ZVE32F-NEXT: lh a3, 18(a0)
-; RV64ZVE32F-NEXT: lh a4, 10(a0)
-; RV64ZVE32F-NEXT: lh a5, 4(a0)
-; RV64ZVE32F-NEXT: lh a6, 6(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 8
+; RV64ZVE32F-NEXT: lh a2, 2(a0)
+; RV64ZVE32F-NEXT: lh a3, 16(a0)
+; RV64ZVE32F-NEXT: lh a4, 18(a0)
+; RV64ZVE32F-NEXT: lh a5, 10(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 8
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 4(a0)
+; RV64ZVE32F-NEXT: lh a0, 6(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13105,22 +13105,22 @@ define <8 x i16> @mgather_gather_2xSEW_unaligned(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_gather_2xSEW_unaligned:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 2(a0)
-; RV64ZVE32F-NEXT: lh a2, 18(a0)
-; RV64ZVE32F-NEXT: lh a3, 20(a0)
-; RV64ZVE32F-NEXT: lh a4, 10(a0)
-; RV64ZVE32F-NEXT: lh a5, 4(a0)
-; RV64ZVE32F-NEXT: lh a6, 6(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 8
+; RV64ZVE32F-NEXT: lh a2, 2(a0)
+; RV64ZVE32F-NEXT: lh a3, 18(a0)
+; RV64ZVE32F-NEXT: lh a4, 20(a0)
+; RV64ZVE32F-NEXT: lh a5, 10(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 8
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 4(a0)
+; RV64ZVE32F-NEXT: lh a0, 6(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13152,22 +13152,22 @@ define <8 x i16> @mgather_gather_2xSEW_unaligned2(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_gather_2xSEW_unaligned2:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: addi a1, a0, 2
-; RV64ZVE32F-NEXT: lh a2, 4(a0)
-; RV64ZVE32F-NEXT: lh a3, 18(a0)
-; RV64ZVE32F-NEXT: lh a4, 20(a0)
-; RV64ZVE32F-NEXT: lh a5, 10(a0)
-; RV64ZVE32F-NEXT: lh a6, 6(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 8
+; RV64ZVE32F-NEXT: addi a2, a0, 2
+; RV64ZVE32F-NEXT: lh a3, 4(a0)
+; RV64ZVE32F-NEXT: lh a4, 18(a0)
+; RV64ZVE32F-NEXT: lh a5, 20(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; RV64ZVE32F-NEXT: vlse16.v v8, (a1), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 8
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
+; RV64ZVE32F-NEXT: vlse16.v v8, (a2), zero
+; RV64ZVE32F-NEXT: lh a2, 10(a0)
+; RV64ZVE32F-NEXT: lh a0, 6(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a2
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13202,22 +13202,22 @@ define <8 x i16> @mgather_gather_4xSEW(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_gather_4xSEW:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 2(a0)
-; RV64ZVE32F-NEXT: lh a2, 4(a0)
-; RV64ZVE32F-NEXT: lh a3, 6(a0)
-; RV64ZVE32F-NEXT: lh a4, 18(a0)
-; RV64ZVE32F-NEXT: lh a5, 20(a0)
-; RV64ZVE32F-NEXT: lh a6, 22(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 16
+; RV64ZVE32F-NEXT: lh a2, 2(a0)
+; RV64ZVE32F-NEXT: lh a3, 4(a0)
+; RV64ZVE32F-NEXT: lh a4, 6(a0)
+; RV64ZVE32F-NEXT: lh a5, 18(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 16
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 20(a0)
+; RV64ZVE32F-NEXT: lh a0, 22(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13249,22 +13249,22 @@ define <8 x i16> @mgather_gather_4xSEW_partial_align(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_gather_4xSEW_partial_align:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 2(a0)
-; RV64ZVE32F-NEXT: lh a2, 4(a0)
-; RV64ZVE32F-NEXT: lh a3, 6(a0)
-; RV64ZVE32F-NEXT: lh a4, 18(a0)
-; RV64ZVE32F-NEXT: lh a5, 20(a0)
-; RV64ZVE32F-NEXT: lh a6, 22(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 16
+; RV64ZVE32F-NEXT: lh a2, 2(a0)
+; RV64ZVE32F-NEXT: lh a3, 4(a0)
+; RV64ZVE32F-NEXT: lh a4, 6(a0)
+; RV64ZVE32F-NEXT: lh a5, 18(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 16
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 20(a0)
+; RV64ZVE32F-NEXT: lh a0, 22(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13305,22 +13305,22 @@ define <8 x i16> @mgather_shuffle_rotate(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_shuffle_rotate:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 10(a0)
-; RV64ZVE32F-NEXT: lh a2, 12(a0)
-; RV64ZVE32F-NEXT: lh a3, 14(a0)
-; RV64ZVE32F-NEXT: lh a4, 2(a0)
-; RV64ZVE32F-NEXT: lh a5, 4(a0)
-; RV64ZVE32F-NEXT: lh a6, 6(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 8
+; RV64ZVE32F-NEXT: lh a2, 10(a0)
+; RV64ZVE32F-NEXT: lh a3, 12(a0)
+; RV64ZVE32F-NEXT: lh a4, 14(a0)
+; RV64ZVE32F-NEXT: lh a5, 2(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 8
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a4
+; RV64ZVE32F-NEXT: lh a6, 4(a0)
+; RV64ZVE32F-NEXT: lh a0, 6(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
-; RV64ZVE32F-NEXT: vslide1down.vx v9, v9, a1
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vslide1down.vx v9, v9, a2
; RV64ZVE32F-NEXT: vslide1down.vx v9, v9, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v9, v9, a4
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v9, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13352,22 +13352,22 @@ define <8 x i16> @mgather_shuffle_vrgather(ptr %base) {
;
; RV64ZVE32F-LABEL: mgather_shuffle_vrgather:
; RV64ZVE32F: # %bb.0:
-; RV64ZVE32F-NEXT: lh a1, 4(a0)
-; RV64ZVE32F-NEXT: lh a2, 6(a0)
-; RV64ZVE32F-NEXT: lh a3, 2(a0)
-; RV64ZVE32F-NEXT: lh a4, 10(a0)
-; RV64ZVE32F-NEXT: lh a5, 12(a0)
-; RV64ZVE32F-NEXT: lh a6, 14(a0)
+; RV64ZVE32F-NEXT: addi a1, a0, 8
+; RV64ZVE32F-NEXT: lh a2, 4(a0)
+; RV64ZVE32F-NEXT: lh a3, 6(a0)
+; RV64ZVE32F-NEXT: lh a4, 2(a0)
+; RV64ZVE32F-NEXT: lh a5, 10(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; RV64ZVE32F-NEXT: vlse16.v v8, (a0), zero
-; RV64ZVE32F-NEXT: addi a0, a0, 8
-; RV64ZVE32F-NEXT: vlse16.v v9, (a0), zero
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
+; RV64ZVE32F-NEXT: lh a6, 12(a0)
+; RV64ZVE32F-NEXT: lh a0, 14(a0)
+; RV64ZVE32F-NEXT: vlse16.v v9, (a1), zero
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a3
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a4
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v10, v8, a4
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v9, a5
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: vmv.v.i v0, 15
; RV64ZVE32F-NEXT: vslidedown.vi v8, v10, 4, v0.t
; RV64ZVE32F-NEXT: ret
@@ -13853,12 +13853,12 @@ define <4 x i32> @masked_gather_widen_sew_negative_stride(ptr %base) {
; RV64ZVE32F: # %bb.0:
; RV64ZVE32F-NEXT: addi a1, a0, 136
; RV64ZVE32F-NEXT: lw a2, 140(a0)
-; RV64ZVE32F-NEXT: lw a3, 0(a0)
-; RV64ZVE32F-NEXT: lw a0, 4(a0)
; RV64ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; RV64ZVE32F-NEXT: vlse32.v v8, (a1), zero
+; RV64ZVE32F-NEXT: lw a1, 0(a0)
+; RV64ZVE32F-NEXT: lw a0, 4(a0)
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a2
-; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a3
+; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a1
; RV64ZVE32F-NEXT: vslide1down.vx v8, v8, a0
; RV64ZVE32F-NEXT: ret
%ptrs = getelementptr i32, ptr %base, <4 x i64> <i64 34, i64 35, i64 0, i64 1>
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
index aa815e18ac101..42e52436a7da0 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-masked-scatter.ll
@@ -5598,17 +5598,16 @@ define void @mscatter_baseidx_v8i64(<8 x i64> %val, ptr %base, <8 x i64> %idxs,
;
; RV32ZVE32F-LABEL: mscatter_baseidx_v8i64:
; RV32ZVE32F: # %bb.0:
-; RV32ZVE32F-NEXT: addi sp, sp, -48
-; RV32ZVE32F-NEXT: .cfi_def_cfa_offset 48
-; RV32ZVE32F-NEXT: sw s0, 44(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s1, 40(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s2, 36(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s3, 32(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s4, 28(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s5, 24(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s6, 20(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s7, 16(sp) # 4-byte Folded Spill
-; RV32ZVE32F-NEXT: sw s8, 12(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: addi sp, sp, -32
+; RV32ZVE32F-NEXT: .cfi_def_cfa_offset 32
+; RV32ZVE32F-NEXT: sw s0, 28(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s1, 24(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s2, 20(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s3, 16(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s4, 12(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s5, 8(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s6, 4(sp) # 4-byte Folded Spill
+; RV32ZVE32F-NEXT: sw s7, 0(sp) # 4-byte Folded Spill
; RV32ZVE32F-NEXT: .cfi_offset s0, -4
; RV32ZVE32F-NEXT: .cfi_offset s1, -8
; RV32ZVE32F-NEXT: .cfi_offset s2, -12
@@ -5617,7 +5616,6 @@ define void @mscatter_baseidx_v8i64(<8 x i64> %val, ptr %base, <8 x i64> %idxs,
; RV32ZVE32F-NEXT: .cfi_offset s5, -24
; RV32ZVE32F-NEXT: .cfi_offset s6, -28
; RV32ZVE32F-NEXT: .cfi_offset s7, -32
-; RV32ZVE32F-NEXT: .cfi_offset s8, -36
; RV32ZVE32F-NEXT: lw a3, 60(a0)
; RV32ZVE32F-NEXT: lw a4, 56(a0)
; RV32ZVE32F-NEXT: lw a5, 52(a0)
@@ -5635,16 +5633,16 @@ define void @mscatter_baseidx_v8i64(<8 x i64> %val, ptr %base, <8 x i64> %idxs,
; RV32ZVE32F-NEXT: lw s2, 56(a2)
; RV32ZVE32F-NEXT: lw s3, 48(a2)
; RV32ZVE32F-NEXT: lw s4, 40(a2)
-; RV32ZVE32F-NEXT: lw s5, 32(a2)
-; RV32ZVE32F-NEXT: lw s6, 24(a2)
-; RV32ZVE32F-NEXT: lw s7, 16(a2)
-; RV32ZVE32F-NEXT: lw s8, 8(a2)
+; RV32ZVE32F-NEXT: lw s5, 8(a2)
; RV32ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV32ZVE32F-NEXT: vlse32.v v8, (a2), zero
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s8
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s7
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s6
+; RV32ZVE32F-NEXT: lw s6, 16(a2)
+; RV32ZVE32F-NEXT: lw s7, 24(a2)
+; RV32ZVE32F-NEXT: lw a2, 32(a2)
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s5
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s6
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s7
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a2
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s4
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s3
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, s2
@@ -5682,16 +5680,15 @@ define void @mscatter_baseidx_v8i64(<8 x i64> %val, ptr %base, <8 x i64> %idxs,
; RV32ZVE32F-NEXT: sw a4, 0(a0)
; RV32ZVE32F-NEXT: sw a3, 4(a0)
; RV32ZVE32F-NEXT: .LBB51_9: # %else14
-; RV32ZVE32F-NEXT: lw s0, 44(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s1, 40(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s2, 36(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s3, 32(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s5, 24(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s6, 20(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s7, 16(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: lw s8, 12(sp) # 4-byte Folded Reload
-; RV32ZVE32F-NEXT: addi sp, sp, 48
+; RV32ZVE32F-NEXT: lw s0, 28(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s1, 24(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s2, 20(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s3, 16(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s4, 12(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s5, 8(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s6, 4(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: lw s7, 0(sp) # 4-byte Folded Reload
+; RV32ZVE32F-NEXT: addi sp, sp, 32
; RV32ZVE32F-NEXT: ret
; RV32ZVE32F-NEXT: .LBB51_10: # %cond.store
; RV32ZVE32F-NEXT: lw a2, 4(a0)
@@ -10227,16 +10224,16 @@ define void @mscatter_baseidx_v8f64(<8 x double> %val, ptr %base, <8 x i64> %idx
; RV32ZVE32F-NEXT: lw a2, 56(a1)
; RV32ZVE32F-NEXT: lw a3, 48(a1)
; RV32ZVE32F-NEXT: lw a4, 40(a1)
-; RV32ZVE32F-NEXT: lw a5, 32(a1)
-; RV32ZVE32F-NEXT: lw a6, 24(a1)
-; RV32ZVE32F-NEXT: lw a7, 16(a1)
-; RV32ZVE32F-NEXT: lw t0, 8(a1)
+; RV32ZVE32F-NEXT: lw a5, 8(a1)
; RV32ZVE32F-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; RV32ZVE32F-NEXT: vlse32.v v8, (a1), zero
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, t0
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a7
-; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV32ZVE32F-NEXT: lw a6, 16(a1)
+; RV32ZVE32F-NEXT: lw a7, 24(a1)
+; RV32ZVE32F-NEXT: lw a1, 32(a1)
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a5
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a6
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a7
+; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a1
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a4
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a3
; RV32ZVE32F-NEXT: vslide1down.vx v8, v8, a2
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-nearbyint-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-nearbyint-vp.ll
index 19f3d3ce19fa4..7be015e26b098 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-nearbyint-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-nearbyint-vp.ll
@@ -19,9 +19,9 @@ define <2 x half> @vp_nearbyint_v2f16(<2 x half> %va, <2 x i1> %m, i32 zeroext %
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.nearbyint.v2f16(<2 x half> %va, <2 x i1> %m, i32 %evl)
ret <2 x half> %v
@@ -38,9 +38,9 @@ define <2 x half> @vp_nearbyint_v2f16_unmasked(<2 x half> %va, i32 zeroext %evl)
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.nearbyint.v2f16(<2 x half> %va, <2 x i1> splat (i1 true), i32 %evl)
ret <2 x half> %v
@@ -61,9 +61,9 @@ define <4 x half> @vp_nearbyint_v4f16(<4 x half> %va, <4 x i1> %m, i32 zeroext %
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x half> @llvm.vp.nearbyint.v4f16(<4 x half> %va, <4 x i1> %m, i32 %evl)
ret <4 x half> %v
@@ -80,9 +80,9 @@ define <4 x half> @vp_nearbyint_v4f16_unmasked(<4 x half> %va, i32 zeroext %evl)
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x half> @llvm.vp.nearbyint.v4f16(<4 x half> %va, <4 x i1> splat (i1 true), i32 %evl)
ret <4 x half> %v
@@ -103,9 +103,9 @@ define <8 x half> @vp_nearbyint_v8f16(<8 x half> %va, <8 x i1> %m, i32 zeroext %
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x half> @llvm.vp.nearbyint.v8f16(<8 x half> %va, <8 x i1> %m, i32 %evl)
ret <8 x half> %v
@@ -122,9 +122,9 @@ define <8 x half> @vp_nearbyint_v8f16_unmasked(<8 x half> %va, i32 zeroext %evl)
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x half> @llvm.vp.nearbyint.v8f16(<8 x half> %va, <8 x i1> splat (i1 true), i32 %evl)
ret <8 x half> %v
@@ -147,9 +147,9 @@ define <16 x half> @vp_nearbyint_v16f16(<16 x half> %va, <16 x i1> %m, i32 zeroe
; CHECK-NEXT: vmv1r.v v0, v10
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x half> @llvm.vp.nearbyint.v16f16(<16 x half> %va, <16 x i1> %m, i32 %evl)
ret <16 x half> %v
@@ -166,9 +166,9 @@ define <16 x half> @vp_nearbyint_v16f16_unmasked(<16 x half> %va, i32 zeroext %e
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x half> @llvm.vp.nearbyint.v16f16(<16 x half> %va, <16 x i1> splat (i1 true), i32 %evl)
ret <16 x half> %v
@@ -189,9 +189,9 @@ define <2 x float> @vp_nearbyint_v2f32(<2 x float> %va, <2 x i1> %m, i32 zeroext
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x float> @llvm.vp.nearbyint.v2f32(<2 x float> %va, <2 x i1> %m, i32 %evl)
ret <2 x float> %v
@@ -208,9 +208,9 @@ define <2 x float> @vp_nearbyint_v2f32_unmasked(<2 x float> %va, i32 zeroext %ev
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x float> @llvm.vp.nearbyint.v2f32(<2 x float> %va, <2 x i1> splat (i1 true), i32 %evl)
ret <2 x float> %v
@@ -231,9 +231,9 @@ define <4 x float> @vp_nearbyint_v4f32(<4 x float> %va, <4 x i1> %m, i32 zeroext
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> %va, <4 x i1> %m, i32 %evl)
ret <4 x float> %v
@@ -250,9 +250,9 @@ define <4 x float> @vp_nearbyint_v4f32_unmasked(<4 x float> %va, i32 zeroext %ev
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> %va, <4 x i1> splat (i1 true), i32 %evl)
ret <4 x float> %v
@@ -275,9 +275,9 @@ define <8 x float> @vp_nearbyint_v8f32(<8 x float> %va, <8 x i1> %m, i32 zeroext
; CHECK-NEXT: vmv1r.v v0, v10
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x float> @llvm.vp.nearbyint.v8f32(<8 x float> %va, <8 x i1> %m, i32 %evl)
ret <8 x float> %v
@@ -294,9 +294,9 @@ define <8 x float> @vp_nearbyint_v8f32_unmasked(<8 x float> %va, i32 zeroext %ev
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x float> @llvm.vp.nearbyint.v8f32(<8 x float> %va, <8 x i1> splat (i1 true), i32 %evl)
ret <8 x float> %v
@@ -319,9 +319,9 @@ define <16 x float> @vp_nearbyint_v16f32(<16 x float> %va, <16 x i1> %m, i32 zer
; CHECK-NEXT: vmv1r.v v0, v12
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x float> @llvm.vp.nearbyint.v16f32(<16 x float> %va, <16 x i1> %m, i32 %evl)
ret <16 x float> %v
@@ -338,9 +338,9 @@ define <16 x float> @vp_nearbyint_v16f32_unmasked(<16 x float> %va, i32 zeroext
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x float> @llvm.vp.nearbyint.v16f32(<16 x float> %va, <16 x i1> splat (i1 true), i32 %evl)
ret <16 x float> %v
@@ -361,9 +361,9 @@ define <2 x double> @vp_nearbyint_v2f64(<2 x double> %va, <2 x i1> %m, i32 zeroe
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x double> @llvm.vp.nearbyint.v2f64(<2 x double> %va, <2 x i1> %m, i32 %evl)
ret <2 x double> %v
@@ -380,9 +380,9 @@ define <2 x double> @vp_nearbyint_v2f64_unmasked(<2 x double> %va, i32 zeroext %
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <2 x double> @llvm.vp.nearbyint.v2f64(<2 x double> %va, <2 x i1> splat (i1 true), i32 %evl)
ret <2 x double> %v
@@ -405,9 +405,9 @@ define <4 x double> @vp_nearbyint_v4f64(<4 x double> %va, <4 x i1> %m, i32 zeroe
; CHECK-NEXT: vmv1r.v v0, v10
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x double> @llvm.vp.nearbyint.v4f64(<4 x double> %va, <4 x i1> %m, i32 %evl)
ret <4 x double> %v
@@ -424,9 +424,9 @@ define <4 x double> @vp_nearbyint_v4f64_unmasked(<4 x double> %va, i32 zeroext %
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <4 x double> @llvm.vp.nearbyint.v4f64(<4 x double> %va, <4 x i1> splat (i1 true), i32 %evl)
ret <4 x double> %v
@@ -449,9 +449,9 @@ define <8 x double> @vp_nearbyint_v8f64(<8 x double> %va, <8 x i1> %m, i32 zeroe
; CHECK-NEXT: vmv1r.v v0, v12
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x double> @llvm.vp.nearbyint.v8f64(<8 x double> %va, <8 x i1> %m, i32 %evl)
ret <8 x double> %v
@@ -468,9 +468,9 @@ define <8 x double> @vp_nearbyint_v8f64_unmasked(<8 x double> %va, i32 zeroext %
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <8 x double> @llvm.vp.nearbyint.v8f64(<8 x double> %va, <8 x i1> splat (i1 true), i32 %evl)
ret <8 x double> %v
@@ -493,9 +493,9 @@ define <15 x double> @vp_nearbyint_v15f64(<15 x double> %va, <15 x i1> %m, i32 z
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <15 x double> @llvm.vp.nearbyint.v15f64(<15 x double> %va, <15 x i1> %m, i32 %evl)
ret <15 x double> %v
@@ -512,9 +512,9 @@ define <15 x double> @vp_nearbyint_v15f64_unmasked(<15 x double> %va, i32 zeroex
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <15 x double> @llvm.vp.nearbyint.v15f64(<15 x double> %va, <15 x i1> splat (i1 true), i32 %evl)
ret <15 x double> %v
@@ -537,9 +537,9 @@ define <16 x double> @vp_nearbyint_v16f64(<16 x double> %va, <16 x i1> %m, i32 z
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x double> @llvm.vp.nearbyint.v16f64(<16 x double> %va, <16 x i1> %m, i32 %evl)
ret <16 x double> %v
@@ -556,9 +556,9 @@ define <16 x double> @vp_nearbyint_v16f64_unmasked(<16 x double> %va, i32 zeroex
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <16 x double> @llvm.vp.nearbyint.v16f64(<16 x double> %va, <16 x i1> splat (i1 true), i32 %evl)
ret <16 x double> %v
@@ -617,9 +617,9 @@ define <32 x double> @vp_nearbyint_v32f64(<32 x double> %va, <32 x i1> %m, i32 z
; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: vfcvt.x.f.v v16, v24, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v24, v16, v24, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vmv.v.v v16, v24
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
@@ -660,9 +660,9 @@ define <32 x double> @vp_nearbyint_v32f64_unmasked(<32 x double> %va, i32 zeroex
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v24, v16, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v16, v24, v16, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <32 x double> @llvm.vp.nearbyint.v32f64(<32 x double> %va, <32 x i1> splat (i1 true), i32 %evl)
ret <32 x double> %v
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vselect.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vselect.ll
index 7dcd4c4199827..ed2ed2a2ebfaa 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vselect.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vselect.ll
@@ -5,8 +5,8 @@
define void @vselect_vv_v6i32(ptr %a, ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vv_v6i32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a2, 0(a2)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a1)
; RV32-NEXT: slli a1, a2, 30
; RV32-NEXT: srli a1, a1, 31
@@ -35,8 +35,8 @@ define void @vselect_vv_v6i32(ptr %a, ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vv_v6i32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a2, 0(a2)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a1)
; RV64-NEXT: slli a1, a2, 62
; RV64-NEXT: srli a1, a1, 63
@@ -73,8 +73,8 @@ define void @vselect_vv_v6i32(ptr %a, ptr %b, ptr %cc, ptr %z) {
define void @vselect_vx_v6i32(i32 %a, ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vx_v6i32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a2, 0(a2)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a1)
; RV32-NEXT: slli a1, a2, 30
; RV32-NEXT: srli a1, a1, 31
@@ -104,8 +104,8 @@ define void @vselect_vx_v6i32(i32 %a, ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vx_v6i32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a2, 0(a2)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a1)
; RV64-NEXT: slli a1, a2, 62
; RV64-NEXT: srli a1, a1, 63
@@ -144,8 +144,8 @@ define void @vselect_vx_v6i32(i32 %a, ptr %b, ptr %cc, ptr %z) {
define void @vselect_vi_v6i32(ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vi_v6i32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: slli a0, a1, 30
; RV32-NEXT: srli a0, a0, 31
@@ -175,8 +175,8 @@ define void @vselect_vi_v6i32(ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vi_v6i32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a1, 0(a1)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a0)
; RV64-NEXT: slli a0, a1, 62
; RV64-NEXT: srli a0, a0, 63
@@ -214,8 +214,8 @@ define void @vselect_vi_v6i32(ptr %b, ptr %cc, ptr %z) {
define void @vselect_vv_v6f32(ptr %a, ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vv_v6f32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a2, 0(a2)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a1)
; RV32-NEXT: slli a1, a2, 30
; RV32-NEXT: srli a1, a1, 31
@@ -244,8 +244,8 @@ define void @vselect_vv_v6f32(ptr %a, ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vv_v6f32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a2, 0(a2)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a1)
; RV64-NEXT: slli a1, a2, 62
; RV64-NEXT: srli a1, a1, 63
@@ -282,8 +282,8 @@ define void @vselect_vv_v6f32(ptr %a, ptr %b, ptr %cc, ptr %z) {
define void @vselect_vx_v6f32(float %a, ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vx_v6f32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: slli a0, a1, 30
; RV32-NEXT: srli a0, a0, 31
@@ -313,8 +313,8 @@ define void @vselect_vx_v6f32(float %a, ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vx_v6f32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a1, 0(a1)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a0)
; RV64-NEXT: slli a0, a1, 62
; RV64-NEXT: srli a0, a0, 63
@@ -353,8 +353,8 @@ define void @vselect_vx_v6f32(float %a, ptr %b, ptr %cc, ptr %z) {
define void @vselect_vfpzero_v6f32(ptr %b, ptr %cc, ptr %z) {
; RV32-LABEL: vselect_vfpzero_v6f32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: slli a0, a1, 30
; RV32-NEXT: srli a0, a0, 31
@@ -384,8 +384,8 @@ define void @vselect_vfpzero_v6f32(ptr %b, ptr %cc, ptr %z) {
;
; RV64-LABEL: vselect_vfpzero_v6f32:
; RV64: # %bb.0:
-; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: lbu a1, 0(a1)
+; RV64-NEXT: vsetivli zero, 6, e32, m2, ta, ma
; RV64-NEXT: vle32.v v8, (a0)
; RV64-NEXT: slli a0, a1, 62
; RV64-NEXT: srli a0, a0, 63
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwadd.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwadd.ll
index a4a5917fd4f9e..b1726be941e3e 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwadd.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwadd.ll
@@ -768,8 +768,8 @@ define <4 x i32> @vwadd_vx_v4i32_i32(ptr %x, ptr %y) {
define <2 x i64> @vwadd_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwadd_vx_v2i64_i8:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lb a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -796,8 +796,8 @@ define <2 x i64> @vwadd_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
define <2 x i64> @vwadd_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwadd_vx_v2i64_i16:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lh a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -824,8 +824,8 @@ define <2 x i64> @vwadd_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
define <2 x i64> @vwadd_vx_v2i64_i32(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwadd_vx_v2i64_i32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -853,9 +853,9 @@ define <2 x i64> @vwadd_vx_v2i64_i64(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwadd_vx_v2i64_i64:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a2, 4(a1)
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw a2, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwaddu.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwaddu.ll
index bc0bf5dd76ad4..f6d9695c51490 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwaddu.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwaddu.ll
@@ -769,8 +769,8 @@ define <2 x i64> @vwaddu_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwaddu_vx_v2i64_i8:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -801,8 +801,8 @@ define <2 x i64> @vwaddu_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwaddu_vx_v2i64_i16:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lhu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -833,8 +833,8 @@ define <2 x i64> @vwaddu_vx_v2i64_i32(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwaddu_vx_v2i64_i32:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -865,9 +865,9 @@ define <2 x i64> @vwaddu_vx_v2i64_i64(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwaddu_vx_v2i64_i64:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a2, 4(a1)
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw a2, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
index 2abd34f01c14c..c87584ab63513 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmul.ll
@@ -883,9 +883,9 @@ define <2 x i64> @vwmul_vx_v2i64_i64(ptr %x, ptr %y) {
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lw a2, 4(a1)
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: sw a2, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulsu.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulsu.ll
index 921037db2ea99..a56984577ea74 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulsu.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwmulsu.ll
@@ -793,8 +793,8 @@ define <2 x i64> @vwmulsu_vx_v2i64_i8(ptr %x, ptr %y) {
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -827,8 +827,8 @@ define <2 x i64> @vwmulsu_vx_v2i64_i16(ptr %x, ptr %y) {
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lhu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -861,8 +861,8 @@ define <2 x i64> @vwmulsu_vx_v2i64_i32(ptr %x, ptr %y) {
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v8, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsub.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsub.ll
index 154093d759d6d..2782a5fbb1eae 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsub.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsub.ll
@@ -769,8 +769,8 @@ define <4 x i32> @vwsub_vx_v4i32_i32(ptr %x, ptr %y) {
define <2 x i64> @vwsub_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsub_vx_v2i64_i8:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lb a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -798,8 +798,8 @@ define <2 x i64> @vwsub_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
define <2 x i64> @vwsub_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsub_vx_v2i64_i16:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lh a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -827,8 +827,8 @@ define <2 x i64> @vwsub_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
define <2 x i64> @vwsub_vx_v2i64_i32(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsub_vx_v2i64_i32:
; RV32: # %bb.0:
-; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: vmv.v.x v8, a1
; RV32-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
@@ -856,9 +856,9 @@ define <2 x i64> @vwsub_vx_v2i64_i64(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsub_vx_v2i64_i64:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a2, 4(a1)
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw a2, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsubu.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsubu.ll
index a084b5383b403..ccbc26c84d80d 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsubu.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vwsubu.ll
@@ -770,8 +770,8 @@ define <2 x i64> @vwsubu_vx_v2i64_i8(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsubu_vx_v2i64_i8:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lbu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -803,8 +803,8 @@ define <2 x i64> @vwsubu_vx_v2i64_i16(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsubu_vx_v2i64_i16:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lhu a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -836,8 +836,8 @@ define <2 x i64> @vwsubu_vx_v2i64_i32(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsubu_vx_v2i64_i32:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw zero, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
@@ -868,9 +868,9 @@ define <2 x i64> @vwsubu_vx_v2i64_i64(ptr %x, ptr %y) nounwind {
; RV32-LABEL: vwsubu_vx_v2i64_i64:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: lw a2, 4(a1)
; RV32-NEXT: lw a1, 0(a1)
+; RV32-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; RV32-NEXT: vle32.v v9, (a0)
; RV32-NEXT: sw a2, 12(sp)
; RV32-NEXT: sw a1, 8(sp)
diff --git a/llvm/test/CodeGen/RISCV/rvv/fmaximum-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fmaximum-vp.ll
index b78b8663eac90..02cfd3de6b4db 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fmaximum-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fmaximum-vp.ll
@@ -1012,77 +1012,99 @@ define <vscale x 16 x double> @vfmax_vv_nxv16f64(<vscale x 16 x double> %va, <vs
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 42
+; CHECK-NEXT: li a3, 36
; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x2a, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 42 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x24, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 36 * vlenb
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a3, a1, 3
; CHECK-NEXT: add a3, a0, a3
; CHECK-NEXT: vl8re64.v v24, (a3)
; CHECK-NEXT: csrr a3, vlenb
-; CHECK-NEXT: slli a3, a3, 4
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
; CHECK-NEXT: add a3, sp, a3
; CHECK-NEXT: addi a3, a3, 16
; CHECK-NEXT: vs8r.v v24, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: srli a3, a1, 3
; CHECK-NEXT: vsetvli a4, zero, e8, mf4, ta, ma
; CHECK-NEXT: csrr a4, vlenb
-; CHECK-NEXT: slli a4, a4, 5
+; CHECK-NEXT: li a5, 18
+; CHECK-NEXT: mul a4, a4, a5
; CHECK-NEXT: add a4, sp, a4
; CHECK-NEXT: addi a4, a4, 16
; CHECK-NEXT: vs1r.v v0, (a4) # Unknown-size Folded Spill
-; CHECK-NEXT: vslidedown.vx v24, v0, a3
+; CHECK-NEXT: vslidedown.vx v7, v0, a3
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs1r.v v7, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: sub a3, a2, a1
; CHECK-NEXT: sltu a4, a2, a3
; CHECK-NEXT: addi a4, a4, -1
; CHECK-NEXT: and a3, a4, a3
-; CHECK-NEXT: vl8re64.v v0, (a0)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a4, a0, 5
-; CHECK-NEXT: add a0, a4, a0
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v7, v24
-; CHECK-NEXT: vmv1r.v v0, v24
+; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: slli a3, a3, 1
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: vmfeq.vv v26, v16, v16, v0.t
; CHECK-NEXT: vmv1r.v v0, v26
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v24, v16, v24, v0
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 10
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs8r.v v24, (a3) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; CHECK-NEXT: vmfeq.vv v16, v24, v24, v0.t
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vs1r.v v16, (a3) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re64.v v0, (a0)
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a3, 19
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv8r.v v16, v8
; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmerge.vvm v16, v16, v24, v0
+; CHECK-NEXT: vl1r.v v0, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v7
-; CHECK-NEXT: vmfeq.vv v17, v24, v24, v0.t
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v8, v24, v8, v0
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a3, 24
-; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v17
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmerge.vvm v8, v24, v8, v0
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vl1r.v v0, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: li a3, 10
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vfmax.vv v8, v8, v16, v0.t
+; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vfmax.vv v8, v8, v24, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a3, 10
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
@@ -1092,49 +1114,63 @@ define <vscale x 16 x double> @vfmax_vv_nxv16f64(<vscale x 16 x double> %va, <vs
; CHECK-NEXT: .LBB28_2:
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl1r.v v7, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmv1r.v v0, v7
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 24
+; CHECK-NEXT: li a1, 18
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vl1r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vmfeq.vv v25, v16, v16, v0.t
; CHECK-NEXT: vmv1r.v v0, v25
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a1, a0, 5
-; CHECK-NEXT: add a0, a1, a0
+; CHECK-NEXT: li a1, 19
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmerge.vvm v24, v16, v8, v0
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v16, v16, v8, v0
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: slli a0, a0, 1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vmfeq.vv v25, v8, v8, v0.t
; CHECK-NEXT: vmv1r.v v0, v25
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vmerge.vvm v8, v8, v16, v0
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vfmax.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a1, 10
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 42
+; CHECK-NEXT: li a1, 36
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
@@ -1162,19 +1198,19 @@ define <vscale x 16 x double> @vfmax_vv_nxv16f64_unmasked(<vscale x 16 x double>
; CHECK-NEXT: slli a3, a1, 3
; CHECK-NEXT: add a3, a0, a3
; CHECK-NEXT: vl8re64.v v24, (a3)
+; CHECK-NEXT: sub a3, a2, a1
+; CHECK-NEXT: sltu a4, a2, a3
+; CHECK-NEXT: addi a4, a4, -1
+; CHECK-NEXT: and a3, a4, a3
+; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT: vmfeq.vv v0, v16, v16
+; CHECK-NEXT: vmfeq.vv v7, v24, v24
; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: sub a0, a2, a1
-; CHECK-NEXT: sltu a3, a2, a0
-; CHECK-NEXT: addi a3, a3, -1
-; CHECK-NEXT: and a0, a3, a0
-; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT: vmfeq.vv v0, v16, v16
-; CHECK-NEXT: vmfeq.vv v7, v24, v24
; CHECK-NEXT: vmerge.vvm v8, v16, v24, v0
; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: vmerge.vvm v16, v24, v16, v0
diff --git a/llvm/test/CodeGen/RISCV/rvv/fminimum-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fminimum-vp.ll
index 69c76152910e8..72a47ca2a6057 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fminimum-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fminimum-vp.ll
@@ -1012,77 +1012,99 @@ define <vscale x 16 x double> @vfmin_vv_nxv16f64(<vscale x 16 x double> %va, <vs
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 42
+; CHECK-NEXT: li a3, 36
; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x2a, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 42 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x24, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 36 * vlenb
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a3, a1, 3
; CHECK-NEXT: add a3, a0, a3
; CHECK-NEXT: vl8re64.v v24, (a3)
; CHECK-NEXT: csrr a3, vlenb
-; CHECK-NEXT: slli a3, a3, 4
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
; CHECK-NEXT: add a3, sp, a3
; CHECK-NEXT: addi a3, a3, 16
; CHECK-NEXT: vs8r.v v24, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: srli a3, a1, 3
; CHECK-NEXT: vsetvli a4, zero, e8, mf4, ta, ma
; CHECK-NEXT: csrr a4, vlenb
-; CHECK-NEXT: slli a4, a4, 5
+; CHECK-NEXT: li a5, 18
+; CHECK-NEXT: mul a4, a4, a5
; CHECK-NEXT: add a4, sp, a4
; CHECK-NEXT: addi a4, a4, 16
; CHECK-NEXT: vs1r.v v0, (a4) # Unknown-size Folded Spill
-; CHECK-NEXT: vslidedown.vx v24, v0, a3
+; CHECK-NEXT: vslidedown.vx v7, v0, a3
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs1r.v v7, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: sub a3, a2, a1
; CHECK-NEXT: sltu a4, a2, a3
; CHECK-NEXT: addi a4, a4, -1
; CHECK-NEXT: and a3, a4, a3
-; CHECK-NEXT: vl8re64.v v0, (a0)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a4, a0, 5
-; CHECK-NEXT: add a0, a4, a0
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v7, v24
-; CHECK-NEXT: vmv1r.v v0, v24
+; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: slli a3, a3, 1
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; CHECK-NEXT: vmfeq.vv v26, v16, v16, v0.t
; CHECK-NEXT: vmv1r.v v0, v26
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v24, v16, v24, v0
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 10
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vs8r.v v24, (a3) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: li a4, 27
+; CHECK-NEXT: mul a3, a3, a4
+; CHECK-NEXT: add a3, sp, a3
+; CHECK-NEXT: addi a3, a3, 16
+; CHECK-NEXT: vl8r.v v24, (a3) # Unknown-size Folded Reload
+; CHECK-NEXT: vmfeq.vv v16, v24, v24, v0.t
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vs1r.v v16, (a3) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re64.v v0, (a0)
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a3, 19
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv8r.v v16, v8
; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmerge.vvm v16, v16, v24, v0
+; CHECK-NEXT: vl1r.v v0, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v7
-; CHECK-NEXT: vmfeq.vv v17, v24, v24, v0.t
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v8, v24, v8, v0
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a3, 24
-; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v17
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmerge.vvm v8, v24, v8, v0
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vl1r.v v0, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: li a3, 10
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vfmin.vv v8, v8, v16, v0.t
+; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vfmin.vv v8, v8, v24, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a3, 10
+; CHECK-NEXT: mul a0, a0, a3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
@@ -1092,49 +1114,63 @@ define <vscale x 16 x double> @vfmin_vv_nxv16f64(<vscale x 16 x double> %va, <vs
; CHECK-NEXT: .LBB28_2:
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl1r.v v7, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmv1r.v v0, v7
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 24
+; CHECK-NEXT: li a1, 18
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vl1r.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vmfeq.vv v25, v16, v16, v0.t
; CHECK-NEXT: vmv1r.v v0, v25
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a1, a0, 5
-; CHECK-NEXT: add a0, a1, a0
+; CHECK-NEXT: li a1, 19
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmerge.vvm v24, v16, v8, v0
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmerge.vvm v16, v16, v8, v0
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: slli a0, a0, 1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: vmfeq.vv v25, v8, v8, v0.t
; CHECK-NEXT: vmv1r.v v0, v25
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: li a1, 27
+; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: add a0, sp, a0
+; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vmerge.vvm v8, v8, v16, v0
-; CHECK-NEXT: vmv1r.v v0, v7
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vfmin.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a1, 10
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 42
+; CHECK-NEXT: li a1, 36
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
@@ -1162,19 +1198,19 @@ define <vscale x 16 x double> @vfmin_vv_nxv16f64_unmasked(<vscale x 16 x double>
; CHECK-NEXT: slli a3, a1, 3
; CHECK-NEXT: add a3, a0, a3
; CHECK-NEXT: vl8re64.v v24, (a3)
+; CHECK-NEXT: sub a3, a2, a1
+; CHECK-NEXT: sltu a4, a2, a3
+; CHECK-NEXT: addi a4, a4, -1
+; CHECK-NEXT: and a3, a4, a3
+; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
+; CHECK-NEXT: vmfeq.vv v0, v16, v16
+; CHECK-NEXT: vmfeq.vv v7, v24, v24
; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: sub a0, a2, a1
-; CHECK-NEXT: sltu a3, a2, a0
-; CHECK-NEXT: addi a3, a3, -1
-; CHECK-NEXT: and a0, a3, a0
-; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT: vmfeq.vv v0, v16, v16
-; CHECK-NEXT: vmfeq.vv v7, v24, v24
; CHECK-NEXT: vmerge.vvm v8, v16, v24, v0
; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: vmerge.vvm v16, v24, v16, v0
diff --git a/llvm/test/CodeGen/RISCV/rvv/fnearbyint-constrained-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/fnearbyint-constrained-sdnode.ll
index f90237b8d7e95..f88a9b3081a1a 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fnearbyint-constrained-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fnearbyint-constrained-sdnode.ll
@@ -19,9 +19,9 @@ define <vscale x 1 x half> @nearbyint_nxv1f16(<vscale x 1 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 1 x half> @llvm.experimental.constrained.nearbyint.nxv1f16(<vscale x 1 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 1 x half> %r
@@ -42,9 +42,9 @@ define <vscale x 2 x half> @nearbyint_nxv2f16(<vscale x 2 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 2 x half> @llvm.experimental.constrained.nearbyint.nxv2f16(<vscale x 2 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 2 x half> %r
@@ -65,9 +65,9 @@ define <vscale x 4 x half> @nearbyint_nxv4f16(<vscale x 4 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 4 x half> @llvm.experimental.constrained.nearbyint.nxv4f16(<vscale x 4 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 4 x half> %r
@@ -88,9 +88,9 @@ define <vscale x 8 x half> @nearbyint_nxv8f16(<vscale x 8 x half> %v) strictfp {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.experimental.constrained.nearbyint.nxv8f16(<vscale x 8 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 8 x half> %r
@@ -111,9 +111,9 @@ define <vscale x 16 x half> @nearbyint_nxv16f16(<vscale x 16 x half> %v) strictf
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 16 x half> @llvm.experimental.constrained.nearbyint.nxv16f16(<vscale x 16 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 16 x half> %r
@@ -134,9 +134,9 @@ define <vscale x 32 x half> @nearbyint_nxv32f16(<vscale x 32 x half> %v) strictf
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 32 x half> @llvm.experimental.constrained.nearbyint.nxv32f16(<vscale x 32 x half> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 32 x half> %r
@@ -157,9 +157,9 @@ define <vscale x 1 x float> @nearbyint_nxv1f32(<vscale x 1 x float> %v) strictfp
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 1 x float> @llvm.experimental.constrained.nearbyint.nxv1f32(<vscale x 1 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 1 x float> %r
@@ -180,9 +180,9 @@ define <vscale x 2 x float> @nearbyint_nxv2f32(<vscale x 2 x float> %v) strictfp
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 2 x float> @llvm.experimental.constrained.nearbyint.nxv2f32(<vscale x 2 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 2 x float> %r
@@ -203,9 +203,9 @@ define <vscale x 4 x float> @nearbyint_nxv4f32(<vscale x 4 x float> %v) strictfp
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.experimental.constrained.nearbyint.nxv4f32(<vscale x 4 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 4 x float> %r
@@ -226,9 +226,9 @@ define <vscale x 8 x float> @nearbyint_nxv8f32(<vscale x 8 x float> %v) strictfp
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 8 x float> @llvm.experimental.constrained.nearbyint.nxv8f32(<vscale x 8 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 8 x float> %r
@@ -249,9 +249,9 @@ define <vscale x 16 x float> @nearbyint_nxv16f32(<vscale x 16 x float> %v) stric
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 16 x float> @llvm.experimental.constrained.nearbyint.nxv16f32(<vscale x 16 x float> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 16 x float> %r
@@ -272,9 +272,9 @@ define <vscale x 1 x double> @nearbyint_nxv1f64(<vscale x 1 x double> %v) strict
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 1 x double> @llvm.experimental.constrained.nearbyint.nxv1f64(<vscale x 1 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 1 x double> %r
@@ -295,9 +295,9 @@ define <vscale x 2 x double> @nearbyint_nxv2f64(<vscale x 2 x double> %v) strict
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.experimental.constrained.nearbyint.nxv2f64(<vscale x 2 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 2 x double> %r
@@ -318,9 +318,9 @@ define <vscale x 4 x double> @nearbyint_nxv4f64(<vscale x 4 x double> %v) strict
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 4 x double> @llvm.experimental.constrained.nearbyint.nxv4f64(<vscale x 4 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 4 x double> %r
@@ -341,9 +341,9 @@ define <vscale x 8 x double> @nearbyint_nxv8f64(<vscale x 8 x double> %v) strict
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%r = call <vscale x 8 x double> @llvm.experimental.constrained.nearbyint.nxv8f64(<vscale x 8 x double> %v, metadata !"round.dynamic", metadata !"fpexcept.strict")
ret <vscale x 8 x double> %r
diff --git a/llvm/test/CodeGen/RISCV/rvv/fnearbyint-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/fnearbyint-sdnode.ll
index 9aa356b9b65e0..9e14852305caa 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fnearbyint-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fnearbyint-sdnode.ll
@@ -15,9 +15,9 @@ define <vscale x 1 x half> @nearbyint_nxv1f16(<vscale x 1 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 1 x half> @llvm.nearbyint.nxv1f16(<vscale x 1 x half> %x)
ret <vscale x 1 x half> %a
@@ -35,9 +35,9 @@ define <vscale x 2 x half> @nearbyint_nxv2f16(<vscale x 2 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 2 x half> @llvm.nearbyint.nxv2f16(<vscale x 2 x half> %x)
ret <vscale x 2 x half> %a
@@ -55,9 +55,9 @@ define <vscale x 4 x half> @nearbyint_nxv4f16(<vscale x 4 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 4 x half> @llvm.nearbyint.nxv4f16(<vscale x 4 x half> %x)
ret <vscale x 4 x half> %a
@@ -75,9 +75,9 @@ define <vscale x 8 x half> @nearbyint_nxv8f16(<vscale x 8 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> %x)
ret <vscale x 8 x half> %a
@@ -95,9 +95,9 @@ define <vscale x 16 x half> @nearbyint_nxv16f16(<vscale x 16 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 16 x half> @llvm.nearbyint.nxv16f16(<vscale x 16 x half> %x)
ret <vscale x 16 x half> %a
@@ -115,9 +115,9 @@ define <vscale x 32 x half> @nearbyint_nxv32f16(<vscale x 32 x half> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e16, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 32 x half> @llvm.nearbyint.nxv32f16(<vscale x 32 x half> %x)
ret <vscale x 32 x half> %a
@@ -135,9 +135,9 @@ define <vscale x 1 x float> @nearbyint_nxv1f32(<vscale x 1 x float> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 1 x float> @llvm.nearbyint.nxv1f32(<vscale x 1 x float> %x)
ret <vscale x 1 x float> %a
@@ -155,9 +155,9 @@ define <vscale x 2 x float> @nearbyint_nxv2f32(<vscale x 2 x float> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 2 x float> @llvm.nearbyint.nxv2f32(<vscale x 2 x float> %x)
ret <vscale x 2 x float> %a
@@ -175,9 +175,9 @@ define <vscale x 4 x float> @nearbyint_nxv4f32(<vscale x 4 x float> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> %x)
ret <vscale x 4 x float> %a
@@ -195,9 +195,9 @@ define <vscale x 8 x float> @nearbyint_nxv8f32(<vscale x 8 x float> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 8 x float> @llvm.nearbyint.nxv8f32(<vscale x 8 x float> %x)
ret <vscale x 8 x float> %a
@@ -215,9 +215,9 @@ define <vscale x 16 x float> @nearbyint_nxv16f32(<vscale x 16 x float> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 16 x float> @llvm.nearbyint.nxv16f32(<vscale x 16 x float> %x)
ret <vscale x 16 x float> %a
@@ -235,9 +235,9 @@ define <vscale x 1 x double> @nearbyint_nxv1f64(<vscale x 1 x double> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 1 x double> @llvm.nearbyint.nxv1f64(<vscale x 1 x double> %x)
ret <vscale x 1 x double> %a
@@ -255,9 +255,9 @@ define <vscale x 2 x double> @nearbyint_nxv2f64(<vscale x 2 x double> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> %x)
ret <vscale x 2 x double> %a
@@ -275,9 +275,9 @@ define <vscale x 4 x double> @nearbyint_nxv4f64(<vscale x 4 x double> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> %x)
ret <vscale x 4 x double> %a
@@ -295,9 +295,9 @@ define <vscale x 8 x double> @nearbyint_nxv8f64(<vscale x 8 x double> %x) {
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%a = call <vscale x 8 x double> @llvm.nearbyint.nxv8f64(<vscale x 8 x double> %x)
ret <vscale x 8 x double> %a
diff --git a/llvm/test/CodeGen/RISCV/rvv/fshr-fshl-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fshr-fshl-vp.ll
index 277cd7dcdabce..249f765971b09 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fshr-fshl-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fshr-fshl-vp.ll
@@ -960,108 +960,87 @@ define <vscale x 16 x i64> @fshr_v16i64(<vscale x 16 x i64> %a, <vscale x 16 x i
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 56
+; CHECK-NEXT: li a3, 40
; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x38, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 56 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x28, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 40 * vlenb
; CHECK-NEXT: vmv1r.v v24, v0
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 24
-; CHECK-NEXT: mul a1, a1, a3
+; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 5
+; CHECK-NEXT: li a3, 24
+; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a3, vlenb
; CHECK-NEXT: slli a1, a3, 3
; CHECK-NEXT: add a5, a0, a1
+; CHECK-NEXT: srli a6, a3, 3
+; CHECK-NEXT: vsetvli a7, zero, e8, mf4, ta, ma
+; CHECK-NEXT: add a1, a2, a1
+; CHECK-NEXT: vl8re64.v v16, (a1)
+; CHECK-NEXT: csrr a1, vlenb
+; CHECK-NEXT: slli a1, a1, 3
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: addi a1, a1, 16
+; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT: sub a1, a4, a3
+; CHECK-NEXT: sltu a7, a4, a1
+; CHECK-NEXT: addi a7, a7, -1
+; CHECK-NEXT: and a7, a7, a1
+; CHECK-NEXT: li a1, 63
; CHECK-NEXT: vl8re64.v v8, (a5)
; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: slli a5, a5, 3
+; CHECK-NEXT: slli a5, a5, 5
; CHECK-NEXT: add a5, sp, a5
; CHECK-NEXT: addi a5, a5, 16
; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: srli a5, a3, 3
-; CHECK-NEXT: vsetvli a6, zero, e8, mf4, ta, ma
-; CHECK-NEXT: vslidedown.vx v0, v0, a5
-; CHECK-NEXT: add a5, a2, a1
-; CHECK-NEXT: sub a1, a4, a3
-; CHECK-NEXT: sltu a6, a4, a1
-; CHECK-NEXT: addi a6, a6, -1
-; CHECK-NEXT: and a6, a6, a1
-; CHECK-NEXT: li a1, 63
-; CHECK-NEXT: vl8re64.v v8, (a5)
+; CHECK-NEXT: vslidedown.vx v0, v0, a6
+; CHECK-NEXT: vsetvli zero, a7, e64, m8, ta, ma
+; CHECK-NEXT: vand.vx v8, v16, a1, v0.t
; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: li a7, 40
-; CHECK-NEXT: mul a5, a5, a7
+; CHECK-NEXT: slli a5, a5, 5
; CHECK-NEXT: add a5, sp, a5
; CHECK-NEXT: addi a5, a5, 16
+; CHECK-NEXT: vl8r.v v16, (a5) # Unknown-size Folded Reload
+; CHECK-NEXT: vsrl.vv v8, v16, v8, v0.t
+; CHECK-NEXT: addi a5, sp, 16
; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v16, (a0)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v16, (a2)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli zero, a6, e64, m8, ta, ma
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vsrl.vv v16, v16, v8, v0.t
+; CHECK-NEXT: csrr a5, vlenb
+; CHECK-NEXT: slli a5, a5, 3
+; CHECK-NEXT: add a5, sp, a5
+; CHECK-NEXT: addi a5, a5, 16
+; CHECK-NEXT: vl8r.v v8, (a5) # Unknown-size Folded Reload
+; CHECK-NEXT: vnot.v v8, v8, v0.t
+; CHECK-NEXT: vand.vx v16, v8, a1, v0.t
+; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re64.v v8, (a2)
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vnot.v v8, v8, v0.t
-; CHECK-NEXT: vand.vx v16, v8, a1, v0.t
+; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 24
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vsll.vi v8, v8, 1, v0.t
; CHECK-NEXT: vsll.vv v8, v8, v16, v0.t
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vor.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
@@ -1072,66 +1051,50 @@ define <vscale x 16 x i64> @fshr_v16i64(<vscale x 16 x i64> %a, <vscale x 16 x i
; CHECK-NEXT: vsetvli zero, a4, e64, m8, ta, ma
; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 24
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 24
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vsrl.vv v8, v8, v16, v0.t
+; CHECK-NEXT: vsrl.vv v8, v16, v8, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 24
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vnot.v v16, v8, v0.t
; CHECK-NEXT: vand.vx v16, v16, a1, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
+; CHECK-NEXT: li a1, 24
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vsll.vi v8, v8, 1, v0.t
; CHECK-NEXT: vsll.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 24
-; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vor.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 40
-; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 56
+; CHECK-NEXT: li a1, 40
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
@@ -1147,109 +1110,89 @@ define <vscale x 16 x i64> @fshl_v16i64(<vscale x 16 x i64> %a, <vscale x 16 x i
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 56
+; CHECK-NEXT: li a3, 40
; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x38, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 56 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x28, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 40 * vlenb
; CHECK-NEXT: vmv1r.v v24, v0
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 3
+; CHECK-NEXT: slli a1, a1, 5
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 5
+; CHECK-NEXT: li a3, 24
+; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a3, vlenb
-; CHECK-NEXT: slli a1, a3, 3
-; CHECK-NEXT: add a5, a0, a1
-; CHECK-NEXT: vl8re64.v v8, (a5)
-; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: slli a5, a5, 4
-; CHECK-NEXT: add a5, sp, a5
-; CHECK-NEXT: addi a5, a5, 16
-; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: srli a5, a3, 3
+; CHECK-NEXT: slli a5, a3, 3
+; CHECK-NEXT: srli a1, a3, 3
; CHECK-NEXT: vsetvli a6, zero, e8, mf4, ta, ma
-; CHECK-NEXT: vslidedown.vx v0, v0, a5
-; CHECK-NEXT: add a5, a2, a1
+; CHECK-NEXT: vslidedown.vx v0, v0, a1
+; CHECK-NEXT: add a1, a2, a5
+; CHECK-NEXT: vl8re64.v v8, (a1)
+; CHECK-NEXT: csrr a1, vlenb
+; CHECK-NEXT: slli a1, a1, 4
+; CHECK-NEXT: add a1, sp, a1
+; CHECK-NEXT: addi a1, a1, 16
+; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: sub a1, a4, a3
; CHECK-NEXT: sltu a6, a4, a1
; CHECK-NEXT: addi a6, a6, -1
; CHECK-NEXT: and a6, a6, a1
; CHECK-NEXT: li a1, 63
-; CHECK-NEXT: vl8re64.v v8, (a5)
-; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: li a7, 40
-; CHECK-NEXT: mul a5, a5, a7
-; CHECK-NEXT: add a5, sp, a5
-; CHECK-NEXT: addi a5, a5, 16
-; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v16, (a0)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a5, 24
-; CHECK-NEXT: mul a0, a0, a5
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v16, (a2)
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: vsetvli zero, a6, e64, m8, ta, ma
+; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
+; CHECK-NEXT: csrr a6, vlenb
+; CHECK-NEXT: slli a6, a6, 5
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: addi a6, a6, 16
+; CHECK-NEXT: vl8r.v v16, (a6) # Unknown-size Folded Reload
+; CHECK-NEXT: vsll.vv v8, v16, v8, v0.t
+; CHECK-NEXT: csrr a6, vlenb
+; CHECK-NEXT: slli a6, a6, 3
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: addi a6, a6, 16
+; CHECK-NEXT: vs8r.v v8, (a6) # Unknown-size Folded Spill
+; CHECK-NEXT: add a5, a0, a5
+; CHECK-NEXT: csrr a6, vlenb
+; CHECK-NEXT: slli a6, a6, 4
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: addi a6, a6, 16
+; CHECK-NEXT: vl8r.v v8, (a6) # Unknown-size Folded Reload
+; CHECK-NEXT: vnot.v v8, v8, v0.t
+; CHECK-NEXT: vl8re64.v v16, (a5)
+; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
+; CHECK-NEXT: addi a5, sp, 16
+; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re64.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
-; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vl8re64.v v8, (a2)
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
+; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: vsrl.vi v16, v16, 1, v0.t
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vsll.vv v16, v16, v8, v0.t
+; CHECK-NEXT: vsrl.vv v16, v16, v8, v0.t
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vnot.v v8, v8, v0.t
-; CHECK-NEXT: vand.vx v16, v8, a1, v0.t
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vsrl.vi v8, v8, 1, v0.t
-; CHECK-NEXT: vsrl.vv v8, v8, v16, v0.t
+; CHECK-NEXT: vor.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vor.vv v8, v16, v8, v0.t
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: bltu a4, a3, .LBB47_2
; CHECK-NEXT: # %bb.1:
@@ -1258,63 +1201,56 @@ define <vscale x 16 x i64> @fshl_v16i64(<vscale x 16 x i64> %a, <vscale x 16 x i
; CHECK-NEXT: vsetvli zero, a4, e64, m8, ta, ma
; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vand.vx v8, v8, a1, v0.t
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
+; CHECK-NEXT: li a2, 24
+; CHECK-NEXT: mul a0, a0, a2
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vsll.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: li a2, 24
+; CHECK-NEXT: mul a0, a0, a2
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vsll.vv v16, v16, v8, v0.t
+; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 5
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 48
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vnot.v v16, v8, v0.t
-; CHECK-NEXT: vand.vx v16, v16, a1, v0.t
+; CHECK-NEXT: vnot.v v8, v8, v0.t
+; CHECK-NEXT: vand.vx v16, v8, a1, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 24
-; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vsrl.vi v8, v8, 1, v0.t
; CHECK-NEXT: vsrl.vv v8, v8, v16, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
+; CHECK-NEXT: li a1, 24
+; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vor.vv v8, v16, v8, v0.t
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 40
-; CHECK-NEXT: mul a0, a0, a1
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 56
+; CHECK-NEXT: li a1, 40
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
diff --git a/llvm/test/CodeGen/RISCV/rvv/mgather-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/mgather-sdnode.ll
index e12f1cf7603b8..e260ae5344e44 100644
--- a/llvm/test/CodeGen/RISCV/rvv/mgather-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/mgather-sdnode.ll
@@ -1216,35 +1216,20 @@ define void @mgather_nxv16i64(<vscale x 8 x ptr> %ptrs0, <vscale x 8 x ptr> %ptr
;
; RV64-LABEL: mgather_nxv16i64:
; RV64: # %bb.0:
-; RV64-NEXT: addi sp, sp, -16
-; RV64-NEXT: .cfi_def_cfa_offset 16
-; RV64-NEXT: csrr a3, vlenb
-; RV64-NEXT: slli a3, a3, 3
-; RV64-NEXT: sub sp, sp, a3
-; RV64-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; RV64-NEXT: vl8re64.v v24, (a0)
-; RV64-NEXT: addi a0, sp, 16
-; RV64-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; RV64-NEXT: vmv8r.v v16, v8
-; RV64-NEXT: vl8re64.v v8, (a1)
; RV64-NEXT: vsetvli a0, zero, e64, m8, ta, mu
-; RV64-NEXT: vluxei64.v v24, (zero), v16, v0.t
+; RV64-NEXT: vluxei64.v v24, (zero), v8, v0.t
+; RV64-NEXT: vl8re64.v v8, (a1)
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: srli a1, a0, 3
; RV64-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
; RV64-NEXT: vslidedown.vx v0, v0, a1
; RV64-NEXT: vsetvli a1, zero, e64, m8, ta, mu
-; RV64-NEXT: addi a1, sp, 16
-; RV64-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; RV64-NEXT: vluxei64.v v8, (zero), v16, v0.t
; RV64-NEXT: slli a0, a0, 3
; RV64-NEXT: add a0, a2, a0
; RV64-NEXT: vs8r.v v8, (a0)
; RV64-NEXT: vs8r.v v24, (a2)
-; RV64-NEXT: csrr a0, vlenb
-; RV64-NEXT: slli a0, a0, 3
-; RV64-NEXT: add sp, sp, a0
-; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: ret
%p0 = call <vscale x 16 x ptr> @llvm.vector.insert.nxv8p0.nxv16p0(<vscale x 16 x ptr> undef, <vscale x 8 x ptr> %ptrs0, i64 0)
%p1 = call <vscale x 16 x ptr> @llvm.vector.insert.nxv8p0.nxv16p0(<vscale x 16 x ptr> %p0, <vscale x 8 x ptr> %ptrs1, i64 8)
diff --git a/llvm/test/CodeGen/RISCV/rvv/mscatter-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/mscatter-sdnode.ll
index 0e09f59b6a20f..fc8fdf4aaafe2 100644
--- a/llvm/test/CodeGen/RISCV/rvv/mscatter-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/mscatter-sdnode.ll
@@ -1714,8 +1714,8 @@ define void @mscatter_nxv16f64(<vscale x 8 x double> %val0, <vscale x 8 x double
; RV64-NEXT: vl8re64.v v24, (a0)
; RV64-NEXT: addi a0, sp, 16
; RV64-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; RV64-NEXT: vl8re64.v v16, (a1)
; RV64-NEXT: vsetvli a0, zero, e64, m8, ta, ma
+; RV64-NEXT: vl8re64.v v16, (a1)
; RV64-NEXT: vsoxei64.v v8, (zero), v24, v0.t
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: srli a0, a0, 3
diff --git a/llvm/test/CodeGen/RISCV/rvv/nearbyint-vp.ll b/llvm/test/CodeGen/RISCV/rvv/nearbyint-vp.ll
index 8bc2334282653..ebe89817630d0 100644
--- a/llvm/test/CodeGen/RISCV/rvv/nearbyint-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/nearbyint-vp.ll
@@ -23,9 +23,9 @@ define <vscale x 1 x half> @vp_nearbyint_nxv1f16(<vscale x 1 x half> %va, <vscal
; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv1f16:
@@ -42,11 +42,11 @@ define <vscale x 1 x half> @vp_nearbyint_nxv1f16(<vscale x 1 x half> %va, <vscal
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 1 x half> @llvm.vp.nearbyint.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x half> %v
@@ -63,9 +63,9 @@ define <vscale x 1 x half> @vp_nearbyint_nxv1f16_unmasked(<vscale x 1 x half> %v
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv1f16_unmasked:
@@ -80,11 +80,11 @@ define <vscale x 1 x half> @vp_nearbyint_nxv1f16_unmasked(<vscale x 1 x half> %v
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 1 x half> @llvm.vp.nearbyint.nxv1f16(<vscale x 1 x half> %va, <vscale x 1 x i1> splat (i1 true), i32 %evl)
ret <vscale x 1 x half> %v
@@ -105,9 +105,9 @@ define <vscale x 2 x half> @vp_nearbyint_nxv2f16(<vscale x 2 x half> %va, <vscal
; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv2f16:
@@ -124,11 +124,11 @@ define <vscale x 2 x half> @vp_nearbyint_nxv2f16(<vscale x 2 x half> %va, <vscal
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 2 x half> @llvm.vp.nearbyint.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x half> %v
@@ -145,9 +145,9 @@ define <vscale x 2 x half> @vp_nearbyint_nxv2f16_unmasked(<vscale x 2 x half> %v
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv2f16_unmasked:
@@ -162,11 +162,11 @@ define <vscale x 2 x half> @vp_nearbyint_nxv2f16_unmasked(<vscale x 2 x half> %v
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, mf2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 2 x half> @llvm.vp.nearbyint.nxv2f16(<vscale x 2 x half> %va, <vscale x 2 x i1> splat (i1 true), i32 %evl)
ret <vscale x 2 x half> %v
@@ -187,9 +187,9 @@ define <vscale x 4 x half> @vp_nearbyint_nxv4f16(<vscale x 4 x half> %va, <vscal
; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv4f16:
@@ -208,11 +208,11 @@ define <vscale x 4 x half> @vp_nearbyint_nxv4f16(<vscale x 4 x half> %va, <vscal
; ZVFHMIN-NEXT: vmv1r.v v0, v9
; ZVFHMIN-NEXT: vfcvt.x.f.v v12, v10, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v10, v12, v10, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 4 x half> @llvm.vp.nearbyint.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x half> %v
@@ -229,9 +229,9 @@ define <vscale x 4 x half> @vp_nearbyint_nxv4f16_unmasked(<vscale x 4 x half> %v
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv4f16_unmasked:
@@ -246,11 +246,11 @@ define <vscale x 4 x half> @vp_nearbyint_nxv4f16_unmasked(<vscale x 4 x half> %v
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v10, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v10, v8, v10, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m1, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 4 x half> @llvm.vp.nearbyint.nxv4f16(<vscale x 4 x half> %va, <vscale x 4 x i1> splat (i1 true), i32 %evl)
ret <vscale x 4 x half> %v
@@ -273,9 +273,9 @@ define <vscale x 8 x half> @vp_nearbyint_nxv8f16(<vscale x 8 x half> %va, <vscal
; ZVFH-NEXT: vmv1r.v v0, v10
; ZVFH-NEXT: vfcvt.x.f.v v12, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv8f16:
@@ -294,11 +294,11 @@ define <vscale x 8 x half> @vp_nearbyint_nxv8f16(<vscale x 8 x half> %va, <vscal
; ZVFHMIN-NEXT: vmv1r.v v0, v10
; ZVFHMIN-NEXT: vfcvt.x.f.v v16, v12, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v12, v16, v12, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 8 x half> @llvm.vp.nearbyint.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x half> %v
@@ -315,9 +315,9 @@ define <vscale x 8 x half> @vp_nearbyint_nxv8f16_unmasked(<vscale x 8 x half> %v
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v10, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv8f16_unmasked:
@@ -332,11 +332,11 @@ define <vscale x 8 x half> @vp_nearbyint_nxv8f16_unmasked(<vscale x 8 x half> %v
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v12, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v12, v8, v12, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m2, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 8 x half> @llvm.vp.nearbyint.nxv8f16(<vscale x 8 x half> %va, <vscale x 8 x i1> splat (i1 true), i32 %evl)
ret <vscale x 8 x half> %v
@@ -359,9 +359,9 @@ define <vscale x 16 x half> @vp_nearbyint_nxv16f16(<vscale x 16 x half> %va, <vs
; ZVFH-NEXT: vmv1r.v v0, v12
; ZVFH-NEXT: vfcvt.x.f.v v16, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv16f16:
@@ -380,11 +380,11 @@ define <vscale x 16 x half> @vp_nearbyint_nxv16f16(<vscale x 16 x half> %va, <vs
; ZVFHMIN-NEXT: vmv1r.v v0, v12
; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 16 x half> @llvm.vp.nearbyint.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> %m, i32 %evl)
ret <vscale x 16 x half> %v
@@ -401,9 +401,9 @@ define <vscale x 16 x half> @vp_nearbyint_nxv16f16_unmasked(<vscale x 16 x half>
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v12, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv16f16_unmasked:
@@ -418,11 +418,11 @@ define <vscale x 16 x half> @vp_nearbyint_nxv16f16_unmasked(<vscale x 16 x half>
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v16, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v16, v8, v16, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: ret
%v = call <vscale x 16 x half> @llvm.vp.nearbyint.nxv16f16(<vscale x 16 x half> %va, <vscale x 16 x i1> splat (i1 true), i32 %evl)
ret <vscale x 16 x half> %v
@@ -445,9 +445,9 @@ define <vscale x 32 x half> @vp_nearbyint_nxv32f16(<vscale x 32 x half> %va, <vs
; ZVFH-NEXT: vmv1r.v v0, v16
; ZVFH-NEXT: vfcvt.x.f.v v24, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv32f16:
@@ -458,7 +458,7 @@ define <vscale x 32 x half> @vp_nearbyint_nxv32f16(<vscale x 32 x half> %va, <vs
; ZVFHMIN-NEXT: slli a1, a1, 3
; ZVFHMIN-NEXT: sub sp, sp, a1
; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
-; ZVFHMIN-NEXT: vmv1r.v v7, v0
+; ZVFHMIN-NEXT: vmv1r.v v16, v0
; ZVFHMIN-NEXT: csrr a2, vlenb
; ZVFHMIN-NEXT: slli a1, a2, 1
; ZVFHMIN-NEXT: sub a3, a0, a1
@@ -488,29 +488,30 @@ define <vscale x 32 x half> @vp_nearbyint_nxv32f16(<vscale x 32 x half> %va, <vs
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v24, v8, v24, v0.t
; ZVFHMIN-NEXT: vsetvli a2, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v24
+; ZVFHMIN-NEXT: vfncvt.f.f.w v20, v24
; ZVFHMIN-NEXT: bltu a0, a1, .LBB10_2
; ZVFHMIN-NEXT: # %bb.1:
; ZVFHMIN-NEXT: mv a0, a1
; ZVFHMIN-NEXT: .LBB10_2:
; ZVFHMIN-NEXT: addi a1, sp, 16
-; ZVFHMIN-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v16
+; ZVFHMIN-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8
; ZVFHMIN-NEXT: vsetvli zero, a0, e32, m8, ta, ma
-; ZVFHMIN-NEXT: vmv1r.v v0, v7
-; ZVFHMIN-NEXT: vfabs.v v16, v24, v0.t
+; ZVFHMIN-NEXT: vmv1r.v v0, v16
+; ZVFHMIN-NEXT: vfabs.v v8, v24, v0.t
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
-; ZVFHMIN-NEXT: vmflt.vf v7, v16, fa5, v0.t
+; ZVFHMIN-NEXT: vmflt.vf v16, v8, fa5, v0.t
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
-; ZVFHMIN-NEXT: vmv1r.v v0, v7
-; ZVFHMIN-NEXT: vfcvt.x.f.v v16, v24, v0.t
-; ZVFHMIN-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; ZVFHMIN-NEXT: fsflags a0
+; ZVFHMIN-NEXT: vmv1r.v v0, v16
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v24, v0.t
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
-; ZVFHMIN-NEXT: vfsgnj.vv v24, v16, v24, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v24
+; ZVFHMIN-NEXT: vfsgnj.vv v24, v8, v24, v0.t
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v16, v24
+; ZVFHMIN-NEXT: fsflags a0
+; ZVFHMIN-NEXT: vmv8r.v v8, v16
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add sp, sp, a0
@@ -531,9 +532,9 @@ define <vscale x 32 x half> @vp_nearbyint_nxv32f16_unmasked(<vscale x 32 x half>
; ZVFH-NEXT: frflags a0
; ZVFH-NEXT: vfcvt.x.f.v v16, v8, v0.t
; ZVFH-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu
; ZVFH-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; ZVFH-NEXT: fsflags a0
; ZVFH-NEXT: ret
;
; ZVFHMIN-LABEL: vp_nearbyint_nxv32f16_unmasked:
@@ -589,11 +590,11 @@ define <vscale x 32 x half> @vp_nearbyint_nxv32f16_unmasked(<vscale x 32 x half>
; ZVFHMIN-NEXT: frflags a0
; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t
; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vsetvli a1, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT: fsflags a0
; ZVFHMIN-NEXT: csrr a0, vlenb
; ZVFHMIN-NEXT: slli a0, a0, 3
; ZVFHMIN-NEXT: add sp, sp, a0
@@ -618,9 +619,9 @@ define <vscale x 1 x float> @vp_nearbyint_nxv1f32(<vscale x 1 x float> %va, <vsc
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 1 x float> @llvm.vp.nearbyint.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x float> %v
@@ -637,9 +638,9 @@ define <vscale x 1 x float> @vp_nearbyint_nxv1f32_unmasked(<vscale x 1 x float>
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 1 x float> @llvm.vp.nearbyint.nxv1f32(<vscale x 1 x float> %va, <vscale x 1 x i1> splat (i1 true), i32 %evl)
ret <vscale x 1 x float> %v
@@ -660,9 +661,9 @@ define <vscale x 2 x float> @vp_nearbyint_nxv2f32(<vscale x 2 x float> %va, <vsc
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 2 x float> @llvm.vp.nearbyint.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x float> %v
@@ -679,9 +680,9 @@ define <vscale x 2 x float> @vp_nearbyint_nxv2f32_unmasked(<vscale x 2 x float>
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 2 x float> @llvm.vp.nearbyint.nxv2f32(<vscale x 2 x float> %va, <vscale x 2 x i1> splat (i1 true), i32 %evl)
ret <vscale x 2 x float> %v
@@ -704,9 +705,9 @@ define <vscale x 4 x float> @vp_nearbyint_nxv4f32(<vscale x 4 x float> %va, <vsc
; CHECK-NEXT: vmv1r.v v0, v10
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x float> %v
@@ -723,9 +724,9 @@ define <vscale x 4 x float> @vp_nearbyint_nxv4f32_unmasked(<vscale x 4 x float>
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32(<vscale x 4 x float> %va, <vscale x 4 x i1> splat (i1 true), i32 %evl)
ret <vscale x 4 x float> %v
@@ -748,9 +749,9 @@ define <vscale x 8 x float> @vp_nearbyint_nxv8f32(<vscale x 8 x float> %va, <vsc
; CHECK-NEXT: vmv1r.v v0, v12
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 8 x float> @llvm.vp.nearbyint.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x float> %v
@@ -767,9 +768,9 @@ define <vscale x 8 x float> @vp_nearbyint_nxv8f32_unmasked(<vscale x 8 x float>
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 8 x float> @llvm.vp.nearbyint.nxv8f32(<vscale x 8 x float> %va, <vscale x 8 x i1> splat (i1 true), i32 %evl)
ret <vscale x 8 x float> %v
@@ -792,9 +793,9 @@ define <vscale x 16 x float> @vp_nearbyint_nxv16f32(<vscale x 16 x float> %va, <
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 16 x float> @llvm.vp.nearbyint.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> %m, i32 %evl)
ret <vscale x 16 x float> %v
@@ -811,9 +812,9 @@ define <vscale x 16 x float> @vp_nearbyint_nxv16f32_unmasked(<vscale x 16 x floa
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e32, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 16 x float> @llvm.vp.nearbyint.nxv16f32(<vscale x 16 x float> %va, <vscale x 16 x i1> splat (i1 true), i32 %evl)
ret <vscale x 16 x float> %v
@@ -834,9 +835,9 @@ define <vscale x 1 x double> @vp_nearbyint_nxv1f64(<vscale x 1 x double> %va, <v
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, ma
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 1 x double> @llvm.vp.nearbyint.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> %m, i32 %evl)
ret <vscale x 1 x double> %v
@@ -853,9 +854,9 @@ define <vscale x 1 x double> @vp_nearbyint_nxv1f64_unmasked(<vscale x 1 x double
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m1, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 1 x double> @llvm.vp.nearbyint.nxv1f64(<vscale x 1 x double> %va, <vscale x 1 x i1> splat (i1 true), i32 %evl)
ret <vscale x 1 x double> %v
@@ -878,9 +879,9 @@ define <vscale x 2 x double> @vp_nearbyint_nxv2f64(<vscale x 2 x double> %va, <v
; CHECK-NEXT: vmv1r.v v0, v10
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 2 x double> @llvm.vp.nearbyint.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> %m, i32 %evl)
ret <vscale x 2 x double> %v
@@ -897,9 +898,9 @@ define <vscale x 2 x double> @vp_nearbyint_nxv2f64_unmasked(<vscale x 2 x double
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 2 x double> @llvm.vp.nearbyint.nxv2f64(<vscale x 2 x double> %va, <vscale x 2 x i1> splat (i1 true), i32 %evl)
ret <vscale x 2 x double> %v
@@ -922,9 +923,9 @@ define <vscale x 4 x double> @vp_nearbyint_nxv4f64(<vscale x 4 x double> %va, <v
; CHECK-NEXT: vmv1r.v v0, v12
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 4 x double> @llvm.vp.nearbyint.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> %m, i32 %evl)
ret <vscale x 4 x double> %v
@@ -941,9 +942,9 @@ define <vscale x 4 x double> @vp_nearbyint_nxv4f64_unmasked(<vscale x 4 x double
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m4, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 4 x double> @llvm.vp.nearbyint.nxv4f64(<vscale x 4 x double> %va, <vscale x 4 x i1> splat (i1 true), i32 %evl)
ret <vscale x 4 x double> %v
@@ -966,9 +967,9 @@ define <vscale x 7 x double> @vp_nearbyint_nxv7f64(<vscale x 7 x double> %va, <v
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 7 x double> @llvm.vp.nearbyint.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> %m, i32 %evl)
ret <vscale x 7 x double> %v
@@ -985,9 +986,9 @@ define <vscale x 7 x double> @vp_nearbyint_nxv7f64_unmasked(<vscale x 7 x double
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 7 x double> @llvm.vp.nearbyint.nxv7f64(<vscale x 7 x double> %va, <vscale x 7 x i1> splat (i1 true), i32 %evl)
ret <vscale x 7 x double> %v
@@ -1010,9 +1011,9 @@ define <vscale x 8 x double> @vp_nearbyint_nxv8f64(<vscale x 8 x double> %va, <v
; CHECK-NEXT: vmv1r.v v0, v16
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 8 x double> @llvm.vp.nearbyint.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> %m, i32 %evl)
ret <vscale x 8 x double> %v
@@ -1029,9 +1030,9 @@ define <vscale x 8 x double> @vp_nearbyint_nxv8f64_unmasked(<vscale x 8 x double
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 8 x double> @llvm.vp.nearbyint.nxv8f64(<vscale x 8 x double> %va, <vscale x 8 x i1> splat (i1 true), i32 %evl)
ret <vscale x 8 x double> %v
@@ -1046,16 +1047,15 @@ define <vscale x 16 x double> @vp_nearbyint_nxv16f64(<vscale x 16 x double> %va,
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 4
+; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
-; CHECK-NEXT: vmv1r.v v24, v0
-; CHECK-NEXT: addi a1, sp, 16
-; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; CHECK-NEXT: vmv1r.v v7, v0
+; CHECK-NEXT: vmv8r.v v24, v16
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: srli a2, a1, 3
; CHECK-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
-; CHECK-NEXT: vslidedown.vx v25, v0, a2
+; CHECK-NEXT: vslidedown.vx v6, v0, a2
; CHECK-NEXT: sub a2, a0, a1
; CHECK-NEXT: sltu a3, a0, a2
; CHECK-NEXT: addi a3, a3, -1
@@ -1063,60 +1063,41 @@ define <vscale x 16 x double> @vp_nearbyint_nxv16f64(<vscale x 16 x double> %va,
; CHECK-NEXT: lui a3, %hi(.LCPI32_0)
; CHECK-NEXT: fld fa5, %lo(.LCPI32_0)(a3)
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v25
-; CHECK-NEXT: vmv8r.v v8, v16
-; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 3
-; CHECK-NEXT: add a2, sp, a2
-; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT: vmv1r.v v0, v6
; CHECK-NEXT: vfabs.v v16, v16, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT: vmflt.vf v25, v16, fa5, v0.t
+; CHECK-NEXT: vmflt.vf v6, v16, fa5, v0.t
; CHECK-NEXT: frflags a2
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v25
-; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
-; CHECK-NEXT: vfcvt.f.x.v v8, v16, v0.t
+; CHECK-NEXT: vmv1r.v v0, v6
+; CHECK-NEXT: vfcvt.x.f.v v16, v24, v0.t
+; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
; CHECK-NEXT: fsflags a2
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 3
-; CHECK-NEXT: add a2, sp, a2
-; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vl8r.v v16, (a2) # Unknown-size Folded Reload
-; CHECK-NEXT: vfsgnj.vv v16, v8, v16, v0.t
-; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 3
-; CHECK-NEXT: add a2, sp, a2
-; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT: vfsgnj.vv v24, v16, v24, v0.t
+; CHECK-NEXT: addi a2, sp, 16
+; CHECK-NEXT: vs8r.v v24, (a2) # Unknown-size Folded Spill
; CHECK-NEXT: bltu a0, a1, .LBB32_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a0, a1
; CHECK-NEXT: .LBB32_2:
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v24
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: vfabs.v v16, v8, v0.t
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
-; CHECK-NEXT: vmflt.vf v24, v16, fa5, v0.t
+; CHECK-NEXT: vmflt.vf v7, v16, fa5, v0.t
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v24
+; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 3
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
+; CHECK-NEXT: fsflags a0
+; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
@@ -1153,9 +1134,9 @@ define <vscale x 16 x double> @vp_nearbyint_nxv16f64_unmasked(<vscale x 16 x dou
; CHECK-NEXT: frflags a0
; CHECK-NEXT: vfcvt.x.f.v v24, v8, v0.t
; CHECK-NEXT: vfcvt.f.x.v v24, v24, v0.t
-; CHECK-NEXT: fsflags a0
; CHECK-NEXT: vsetvli zero, zero, e64, m8, ta, mu
; CHECK-NEXT: vfsgnj.vv v8, v24, v8, v0.t
+; CHECK-NEXT: fsflags a0
; CHECK-NEXT: ret
%v = call <vscale x 16 x double> @llvm.vp.nearbyint.nxv16f64(<vscale x 16 x double> %va, <vscale x 16 x i1> splat (i1 true), i32 %evl)
ret <vscale x 16 x double> %v
diff --git a/llvm/test/CodeGen/RISCV/rvv/setcc-fp-vp.ll b/llvm/test/CodeGen/RISCV/rvv/setcc-fp-vp.ll
index 897bfdea69f1f..cc967396153bc 100644
--- a/llvm/test/CodeGen/RISCV/rvv/setcc-fp-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/setcc-fp-vp.ll
@@ -2203,17 +2203,17 @@ define <vscale x 64 x i1> @fcmp_oeq_vv_nxv64f16(<vscale x 64 x half> %va, <vscal
; ZVFH-NEXT: add a1, sp, a1
; ZVFH-NEXT: addi a1, a1, 16
; ZVFH-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
-; ZVFH-NEXT: csrr a1, vlenb
-; ZVFH-NEXT: vsetvli a3, zero, e8, m1, ta, ma
-; ZVFH-NEXT: slli a3, a1, 3
-; ZVFH-NEXT: add a3, a0, a3
-; ZVFH-NEXT: vl8re16.v v8, (a3)
-; ZVFH-NEXT: slli a3, a1, 2
+; ZVFH-NEXT: csrr a3, vlenb
+; ZVFH-NEXT: srli a1, a3, 1
+; ZVFH-NEXT: slli a4, a3, 3
+; ZVFH-NEXT: add a4, a0, a4
+; ZVFH-NEXT: vl8re16.v v8, (a4)
+; ZVFH-NEXT: slli a3, a3, 2
; ZVFH-NEXT: sub a4, a2, a3
; ZVFH-NEXT: sltu a5, a2, a4
; ZVFH-NEXT: addi a5, a5, -1
; ZVFH-NEXT: and a4, a5, a4
-; ZVFH-NEXT: srli a1, a1, 1
+; ZVFH-NEXT: vsetvli a5, zero, e8, m1, ta, ma
; ZVFH-NEXT: vl8re16.v v0, (a0)
; ZVFH-NEXT: addi a0, sp, 16
; ZVFH-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
@@ -2249,152 +2249,133 @@ define <vscale x 64 x i1> @fcmp_oeq_vv_nxv64f16(<vscale x 64 x half> %va, <vscal
; ZVFHMIN-NEXT: addi sp, sp, -16
; ZVFHMIN-NEXT: .cfi_def_cfa_offset 16
; ZVFHMIN-NEXT: csrr a1, vlenb
-; ZVFHMIN-NEXT: li a3, 34
-; ZVFHMIN-NEXT: mul a1, a1, a3
+; ZVFHMIN-NEXT: slli a1, a1, 5
; ZVFHMIN-NEXT: sub sp, sp, a1
-; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x22, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 34 * vlenb
-; ZVFHMIN-NEXT: vmv8r.v v24, v16
+; ZVFHMIN-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x20, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 32 * vlenb
+; ZVFHMIN-NEXT: csrr a1, vlenb
+; ZVFHMIN-NEXT: slli a1, a1, 4
+; ZVFHMIN-NEXT: add a1, sp, a1
+; ZVFHMIN-NEXT: addi a1, a1, 16
+; ZVFHMIN-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a1, vlenb
-; ZVFHMIN-NEXT: li a3, 18
-; ZVFHMIN-NEXT: mul a1, a1, a3
+; ZVFHMIN-NEXT: slli a1, a1, 3
; ZVFHMIN-NEXT: add a1, sp, a1
; ZVFHMIN-NEXT: addi a1, a1, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a3, vlenb
-; ZVFHMIN-NEXT: vsetvli a1, zero, e8, m1, ta, ma
-; ZVFHMIN-NEXT: slli a1, a3, 3
-; ZVFHMIN-NEXT: add a1, a0, a1
-; ZVFHMIN-NEXT: vl8re16.v v16, (a1)
+; ZVFHMIN-NEXT: srli a1, a3, 1
+; ZVFHMIN-NEXT: vsetvli a4, zero, e8, m1, ta, ma
+; ZVFHMIN-NEXT: vmv1r.v v17, v0
+; ZVFHMIN-NEXT: vslidedown.vx v18, v0, a1
+; ZVFHMIN-NEXT: slli a4, a3, 3
+; ZVFHMIN-NEXT: add a4, a0, a4
+; ZVFHMIN-NEXT: vl8re16.v v0, (a4)
; ZVFHMIN-NEXT: slli a5, a3, 2
-; ZVFHMIN-NEXT: sub a1, a2, a5
-; ZVFHMIN-NEXT: sltu a4, a2, a1
-; ZVFHMIN-NEXT: addi a4, a4, -1
-; ZVFHMIN-NEXT: and a6, a4, a1
+; ZVFHMIN-NEXT: sub a4, a2, a5
+; ZVFHMIN-NEXT: sltu a6, a2, a4
+; ZVFHMIN-NEXT: addi a6, a6, -1
+; ZVFHMIN-NEXT: and a6, a6, a4
; ZVFHMIN-NEXT: slli a4, a3, 1
-; ZVFHMIN-NEXT: sub a1, a6, a4
-; ZVFHMIN-NEXT: sltu a7, a6, a1
-; ZVFHMIN-NEXT: addi a7, a7, -1
-; ZVFHMIN-NEXT: and a7, a7, a1
-; ZVFHMIN-NEXT: srli a1, a3, 1
-; ZVFHMIN-NEXT: csrr t0, vlenb
-; ZVFHMIN-NEXT: add t0, sp, t0
-; ZVFHMIN-NEXT: addi t0, t0, 16
-; ZVFHMIN-NEXT: vs1r.v v0, (t0) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT: vslidedown.vx v7, v0, a1
+; ZVFHMIN-NEXT: sub a7, a6, a4
+; ZVFHMIN-NEXT: sltu t0, a6, a7
+; ZVFHMIN-NEXT: addi t0, t0, -1
+; ZVFHMIN-NEXT: and a7, t0, a7
; ZVFHMIN-NEXT: srli a3, a3, 2
+; ZVFHMIN-NEXT: vsetvli t0, zero, e8, mf2, ta, ma
+; ZVFHMIN-NEXT: vslidedown.vx v16, v18, a3
+; ZVFHMIN-NEXT: vsetvli t0, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: vl8re16.v v8, (a0)
; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: li t0, 26
+; ZVFHMIN-NEXT: li t0, 24
; ZVFHMIN-NEXT: mul a0, a0, t0
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT: vsetvli a0, zero, e8, mf2, ta, ma
; ZVFHMIN-NEXT: addi a0, sp, 16
-; ZVFHMIN-NEXT: vs1r.v v7, (a0) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT: vslidedown.vx v0, v7, a3
-; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: slli a0, a0, 1
-; ZVFHMIN-NEXT: add a0, sp, a0
-; ZVFHMIN-NEXT: addi a0, a0, 16
-; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v20
-; ZVFHMIN-NEXT: vmv4r.v v16, v24
+; ZVFHMIN-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v4
; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: li t0, 10
-; ZVFHMIN-NEXT: mul a0, a0, t0
+; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
-; ZVFHMIN-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v28
+; ZVFHMIN-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v4
; ZVFHMIN-NEXT: vsetvli zero, a7, e32, m8, ta, ma
-; ZVFHMIN-NEXT: vmfeq.vv v26, v16, v8, v0.t
+; ZVFHMIN-NEXT: vmv1r.v v0, v16
+; ZVFHMIN-NEXT: vmfeq.vv v20, v8, v24, v0.t
; ZVFHMIN-NEXT: bltu a6, a4, .LBB85_2
; ZVFHMIN-NEXT: # %bb.1:
; ZVFHMIN-NEXT: mv a6, a4
; ZVFHMIN-NEXT: .LBB85_2:
; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: addi a0, sp, 16
+; ZVFHMIN-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v24
; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: slli a0, a0, 1
-; ZVFHMIN-NEXT: add a0, sp, a0
-; ZVFHMIN-NEXT: addi a0, a0, 16
-; ZVFHMIN-NEXT: vl8r.v v16, (a0) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v16
-; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: li a7, 10
-; ZVFHMIN-NEXT: mul a0, a0, a7
+; ZVFHMIN-NEXT: slli a0, a0, 4
; ZVFHMIN-NEXT: add a0, sp, a0
; ZVFHMIN-NEXT: addi a0, a0, 16
; ZVFHMIN-NEXT: vl8r.v v0, (a0) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v0
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v0
; ZVFHMIN-NEXT: vsetvli zero, a6, e32, m8, ta, ma
-; ZVFHMIN-NEXT: addi a0, sp, 16
-; ZVFHMIN-NEXT: vl1r.v v0, (a0) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vmfeq.vv v6, v16, v8, v0.t
+; ZVFHMIN-NEXT: vmv1r.v v0, v18
+; ZVFHMIN-NEXT: vmfeq.vv v6, v24, v8, v0.t
; ZVFHMIN-NEXT: add a0, a3, a3
; ZVFHMIN-NEXT: bltu a2, a5, .LBB85_4
; ZVFHMIN-NEXT: # %bb.3:
; ZVFHMIN-NEXT: mv a2, a5
; ZVFHMIN-NEXT: .LBB85_4:
; ZVFHMIN-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
-; ZVFHMIN-NEXT: vslideup.vx v6, v26, a3
+; ZVFHMIN-NEXT: vslideup.vx v6, v20, a3
; ZVFHMIN-NEXT: sub a5, a2, a4
; ZVFHMIN-NEXT: sltu a6, a2, a5
; ZVFHMIN-NEXT: addi a6, a6, -1
; ZVFHMIN-NEXT: and a5, a6, a5
; ZVFHMIN-NEXT: vsetvli a6, zero, e8, mf2, ta, ma
-; ZVFHMIN-NEXT: csrr a6, vlenb
-; ZVFHMIN-NEXT: add a6, sp, a6
-; ZVFHMIN-NEXT: addi a6, a6, 16
-; ZVFHMIN-NEXT: vl1r.v v8, (a6) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vmv1r.v v7, v8
-; ZVFHMIN-NEXT: vslidedown.vx v0, v8, a3
+; ZVFHMIN-NEXT: vmv1r.v v7, v17
+; ZVFHMIN-NEXT: vslidedown.vx v0, v17, a3
; ZVFHMIN-NEXT: vsetvli a6, zero, e16, m4, ta, ma
; ZVFHMIN-NEXT: csrr a6, vlenb
-; ZVFHMIN-NEXT: li a7, 18
-; ZVFHMIN-NEXT: mul a6, a6, a7
+; ZVFHMIN-NEXT: slli a6, a6, 3
; ZVFHMIN-NEXT: add a6, sp, a6
; ZVFHMIN-NEXT: addi a6, a6, 16
-; ZVFHMIN-NEXT: vl8r.v v24, (a6) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v28
+; ZVFHMIN-NEXT: vl8r.v v16, (a6) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v20
; ZVFHMIN-NEXT: csrr a6, vlenb
-; ZVFHMIN-NEXT: li a7, 10
-; ZVFHMIN-NEXT: mul a6, a6, a7
+; ZVFHMIN-NEXT: slli a6, a6, 4
; ZVFHMIN-NEXT: add a6, sp, a6
; ZVFHMIN-NEXT: addi a6, a6, 16
; ZVFHMIN-NEXT: vs8r.v v8, (a6) # Unknown-size Folded Spill
; ZVFHMIN-NEXT: csrr a6, vlenb
-; ZVFHMIN-NEXT: li a7, 26
+; ZVFHMIN-NEXT: li a7, 24
; ZVFHMIN-NEXT: mul a6, a6, a7
; ZVFHMIN-NEXT: add a6, sp, a6
; ZVFHMIN-NEXT: addi a6, a6, 16
-; ZVFHMIN-NEXT: vl8r.v v16, (a6) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v20
+; ZVFHMIN-NEXT: vl8r.v v24, (a6) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v8, v28
; ZVFHMIN-NEXT: vsetvli zero, a5, e32, m8, ta, ma
; ZVFHMIN-NEXT: csrr a5, vlenb
-; ZVFHMIN-NEXT: li a6, 10
-; ZVFHMIN-NEXT: mul a5, a5, a6
+; ZVFHMIN-NEXT: slli a5, a5, 4
; ZVFHMIN-NEXT: add a5, sp, a5
; ZVFHMIN-NEXT: addi a5, a5, 16
-; ZVFHMIN-NEXT: vl8r.v v16, (a5) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vmfeq.vv v5, v16, v8, v0.t
+; ZVFHMIN-NEXT: vl8r.v v24, (a5) # Unknown-size Folded Reload
+; ZVFHMIN-NEXT: vmfeq.vv v5, v24, v8, v0.t
; ZVFHMIN-NEXT: bltu a2, a4, .LBB85_6
; ZVFHMIN-NEXT: # %bb.5:
; ZVFHMIN-NEXT: mv a2, a4
; ZVFHMIN-NEXT: .LBB85_6:
; ZVFHMIN-NEXT: vsetvli a4, zero, e16, m4, ta, ma
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v24
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v16
; ZVFHMIN-NEXT: csrr a4, vlenb
-; ZVFHMIN-NEXT: li a5, 26
+; ZVFHMIN-NEXT: li a5, 24
; ZVFHMIN-NEXT: mul a4, a4, a5
; ZVFHMIN-NEXT: add a4, sp, a4
; ZVFHMIN-NEXT: addi a4, a4, 16
; ZVFHMIN-NEXT: vl8r.v v8, (a4) # Unknown-size Folded Reload
-; ZVFHMIN-NEXT: vfwcvt.f.f.v v24, v8
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
; ZVFHMIN-NEXT: vsetvli zero, a2, e32, m8, ta, ma
; ZVFHMIN-NEXT: vmv1r.v v0, v7
-; ZVFHMIN-NEXT: vmfeq.vv v8, v16, v24, v0.t
+; ZVFHMIN-NEXT: vmfeq.vv v8, v24, v16, v0.t
; ZVFHMIN-NEXT: vsetvli zero, a0, e8, mf2, ta, ma
; ZVFHMIN-NEXT: vslideup.vx v8, v5, a3
; ZVFHMIN-NEXT: add a0, a1, a1
@@ -2402,8 +2383,7 @@ define <vscale x 64 x i1> @fcmp_oeq_vv_nxv64f16(<vscale x 64 x half> %va, <vscal
; ZVFHMIN-NEXT: vslideup.vx v8, v6, a1
; ZVFHMIN-NEXT: vmv.v.v v0, v8
; ZVFHMIN-NEXT: csrr a0, vlenb
-; ZVFHMIN-NEXT: li a1, 34
-; ZVFHMIN-NEXT: mul a0, a0, a1
+; ZVFHMIN-NEXT: slli a0, a0, 5
; ZVFHMIN-NEXT: add sp, sp, a0
; ZVFHMIN-NEXT: addi sp, sp, 16
; ZVFHMIN-NEXT: ret
@@ -3494,109 +3474,93 @@ define <vscale x 32 x i1> @fcmp_oeq_vv_nxv32f64(<vscale x 32 x double> %va, <vsc
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 48
+; CHECK-NEXT: li a3, 24
; CHECK-NEXT: mul a1, a1, a3
; CHECK-NEXT: sub sp, sp, a1
-; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x30, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 48 * vlenb
+; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 24 * vlenb
; CHECK-NEXT: vmv1r.v v24, v0
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: slli a1, a1, 5
+; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: li a3, 40
-; CHECK-NEXT: mul a1, a1, a3
+; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a3, vlenb
; CHECK-NEXT: li a1, 24
; CHECK-NEXT: mul t2, a3, a1
-; CHECK-NEXT: slli t1, a3, 3
+; CHECK-NEXT: slli a7, a3, 3
; CHECK-NEXT: srli a4, a3, 2
; CHECK-NEXT: vsetvli a1, zero, e8, mf2, ta, ma
; CHECK-NEXT: vslidedown.vx v7, v0, a4
; CHECK-NEXT: srli a1, a3, 3
-; CHECK-NEXT: vsetvli a5, zero, e8, mf4, ta, ma
-; CHECK-NEXT: add a5, a2, t1
-; CHECK-NEXT: vl8re64.v v8, (a5)
; CHECK-NEXT: slli t0, a3, 4
+; CHECK-NEXT: add a5, a2, a7
+; CHECK-NEXT: vl8re64.v v16, (a5)
+; CHECK-NEXT: vsetvli a5, zero, e8, mf4, ta, ma
; CHECK-NEXT: slli a5, a3, 1
; CHECK-NEXT: vslidedown.vx v0, v0, a1
-; CHECK-NEXT: mv a7, a6
+; CHECK-NEXT: mv t1, a6
; CHECK-NEXT: bltu a6, a5, .LBB171_2
; CHECK-NEXT: # %bb.1:
-; CHECK-NEXT: mv a7, a5
+; CHECK-NEXT: mv t1, a5
; CHECK-NEXT: .LBB171_2:
; CHECK-NEXT: add t2, a2, t2
-; CHECK-NEXT: add t1, a0, t1
+; CHECK-NEXT: add a7, a0, a7
; CHECK-NEXT: add t0, a2, t0
-; CHECK-NEXT: vl8re64.v v16, (a2)
-; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 4
-; CHECK-NEXT: add a2, sp, a2
-; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
-; CHECK-NEXT: sub a2, a7, a3
-; CHECK-NEXT: sltu t3, a7, a2
+; CHECK-NEXT: vl8re64.v v8, (a2)
+; CHECK-NEXT: addi a2, sp, 16
+; CHECK-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT: sub a2, t1, a3
+; CHECK-NEXT: sltu t3, t1, a2
; CHECK-NEXT: addi t3, t3, -1
; CHECK-NEXT: and a2, t3, a2
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 5
+; CHECK-NEXT: slli a2, a2, 3
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vl8r.v v16, (a2) # Unknown-size Folded Reload
-; CHECK-NEXT: vmfeq.vv v6, v16, v8, v0.t
-; CHECK-NEXT: bltu a7, a3, .LBB171_4
+; CHECK-NEXT: vl8r.v v8, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT: vmfeq.vv v6, v8, v16, v0.t
+; CHECK-NEXT: bltu t1, a3, .LBB171_4
; CHECK-NEXT: # %bb.3:
-; CHECK-NEXT: mv a7, a3
+; CHECK-NEXT: mv t1, a3
; CHECK-NEXT: .LBB171_4:
-; CHECK-NEXT: vl8re64.v v8, (t2)
+; CHECK-NEXT: vl8re64.v v16, (t2)
; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 5
+; CHECK-NEXT: slli a2, a2, 3
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v8, (t1)
+; CHECK-NEXT: vs8r.v v16, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT: vsetvli a2, zero, e8, mf4, ta, ma
+; CHECK-NEXT: vslidedown.vx v18, v7, a1
+; CHECK-NEXT: vsetvli zero, t1, e64, m8, ta, ma
+; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: li t1, 24
-; CHECK-NEXT: mul a2, a2, t1
+; CHECK-NEXT: slli a2, a2, 4
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli a2, zero, e8, mf4, ta, ma
-; CHECK-NEXT: vslidedown.vx v18, v7, a1
-; CHECK-NEXT: vl8re64.v v8, (t0)
+; CHECK-NEXT: vl8r.v v24, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT: addi a2, sp, 16
+; CHECK-NEXT: vl8r.v v8, (a2) # Unknown-size Folded Reload
+; CHECK-NEXT: vmfeq.vv v17, v24, v8, v0.t
+; CHECK-NEXT: vl8re64.v v8, (a7)
; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 3
+; CHECK-NEXT: slli a2, a2, 4
; CHECK-NEXT: add a2, sp, a2
; CHECK-NEXT: addi a2, a2, 16
; CHECK-NEXT: vs8r.v v8, (a2) # Unknown-size Folded Spill
-; CHECK-NEXT: vl8re64.v v8, (a0)
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vs8r.v v8, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli zero, a7, e64, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v24
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 40
-; CHECK-NEXT: mul a0, a0, a2
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 4
-; CHECK-NEXT: add a0, sp, a0
-; CHECK-NEXT: addi a0, a0, 16
-; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
-; CHECK-NEXT: vmfeq.vv v17, v24, v8, v0.t
-; CHECK-NEXT: add a0, a1, a1
-; CHECK-NEXT: vsetvli zero, a0, e8, mf2, tu, ma
-; CHECK-NEXT: sub a0, a6, a5
-; CHECK-NEXT: sltu a2, a6, a0
-; CHECK-NEXT: addi a2, a2, -1
-; CHECK-NEXT: and a0, a2, a0
+; CHECK-NEXT: vl8re64.v v8, (t0)
+; CHECK-NEXT: add a2, a1, a1
+; CHECK-NEXT: vsetvli zero, a2, e8, mf2, tu, ma
+; CHECK-NEXT: sub a2, a6, a5
+; CHECK-NEXT: sltu a5, a6, a2
+; CHECK-NEXT: vl8re64.v v24, (a0)
+; CHECK-NEXT: addi a0, a5, -1
+; CHECK-NEXT: and a0, a0, a2
; CHECK-NEXT: vslideup.vx v17, v6, a1
; CHECK-NEXT: mv a2, a0
; CHECK-NEXT: bltu a0, a3, .LBB171_6
@@ -3605,13 +3569,6 @@ define <vscale x 32 x i1> @fcmp_oeq_vv_nxv32f64(<vscale x 32 x double> %va, <vsc
; CHECK-NEXT: .LBB171_6:
; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
; CHECK-NEXT: vmv1r.v v0, v7
-; CHECK-NEXT: csrr a2, vlenb
-; CHECK-NEXT: slli a2, a2, 3
-; CHECK-NEXT: add a2, sp, a2
-; CHECK-NEXT: addi a2, a2, 16
-; CHECK-NEXT: vl8r.v v8, (a2) # Unknown-size Folded Reload
-; CHECK-NEXT: addi a2, sp, 16
-; CHECK-NEXT: vl8r.v v24, (a2) # Unknown-size Folded Reload
; CHECK-NEXT: vmfeq.vv v16, v24, v8, v0.t
; CHECK-NEXT: add a2, a4, a1
; CHECK-NEXT: vsetvli zero, a2, e8, mf2, tu, ma
@@ -3623,13 +3580,12 @@ define <vscale x 32 x i1> @fcmp_oeq_vv_nxv32f64(<vscale x 32 x double> %va, <vsc
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, ma
; CHECK-NEXT: vmv1r.v v0, v18
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: slli a0, a0, 5
+; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a2, 24
-; CHECK-NEXT: mul a0, a0, a2
+; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add a0, sp, a0
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: vl8r.v v8, (a0) # Unknown-size Folded Reload
@@ -3641,7 +3597,7 @@ define <vscale x 32 x i1> @fcmp_oeq_vv_nxv32f64(<vscale x 32 x double> %va, <vsc
; CHECK-NEXT: vslideup.vx v17, v16, a0
; CHECK-NEXT: vmv1r.v v0, v17
; CHECK-NEXT: csrr a0, vlenb
-; CHECK-NEXT: li a1, 48
+; CHECK-NEXT: li a1, 24
; CHECK-NEXT: mul a0, a0, a1
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
diff --git a/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll b/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
index 7fd77c050b295..85f5ffd784e98 100644
--- a/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
@@ -1092,7 +1092,7 @@ define <vscale x 128 x i1> @icmp_eq_vv_nxv128i8(<vscale x 128 x i8> %va, <vscale
; CHECK-NEXT: slli a1, a1, 4
; CHECK-NEXT: sub sp, sp, a1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
-; CHECK-NEXT: vmv1r.v v24, v0
+; CHECK-NEXT: vmv1r.v v7, v0
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, sp, a1
@@ -1102,23 +1102,23 @@ define <vscale x 128 x i1> @icmp_eq_vv_nxv128i8(<vscale x 128 x i8> %va, <vscale
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a4, a0, a1
; CHECK-NEXT: vl8r.v v8, (a4)
-; CHECK-NEXT: vl8r.v v0, (a0)
-; CHECK-NEXT: addi a0, sp, 16
-; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, ma
-; CHECK-NEXT: sub a0, a3, a1
+; CHECK-NEXT: vsetvli a4, zero, e8, m8, ta, ma
; CHECK-NEXT: vlm.v v0, (a2)
-; CHECK-NEXT: sltu a2, a3, a0
-; CHECK-NEXT: addi a2, a2, -1
-; CHECK-NEXT: and a0, a2, a0
-; CHECK-NEXT: vsetvli zero, a0, e8, m8, ta, ma
-; CHECK-NEXT: vmseq.vv v7, v16, v8, v0.t
+; CHECK-NEXT: sub a2, a3, a1
+; CHECK-NEXT: sltu a4, a3, a2
+; CHECK-NEXT: addi a4, a4, -1
+; CHECK-NEXT: vl8r.v v24, (a0)
+; CHECK-NEXT: addi a0, sp, 16
+; CHECK-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT: and a2, a4, a2
+; CHECK-NEXT: vsetvli zero, a2, e8, m8, ta, ma
+; CHECK-NEXT: vmseq.vv v6, v16, v8, v0.t
; CHECK-NEXT: bltu a3, a1, .LBB96_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: mv a3, a1
; CHECK-NEXT: .LBB96_2:
; CHECK-NEXT: vsetvli zero, a3, e8, m8, ta, ma
-; CHECK-NEXT: vmv1r.v v0, v24
+; CHECK-NEXT: vmv1r.v v0, v7
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add a0, sp, a0
@@ -1128,7 +1128,7 @@ define <vscale x 128 x i1> @icmp_eq_vv_nxv128i8(<vscale x 128 x i8> %va, <vscale
; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vmseq.vv v16, v8, v24, v0.t
; CHECK-NEXT: vmv1r.v v0, v16
-; CHECK-NEXT: vmv1r.v v8, v7
+; CHECK-NEXT: vmv1r.v v8, v6
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add sp, sp, a0
@@ -2248,17 +2248,17 @@ define <vscale x 32 x i1> @icmp_eq_vv_nxv32i32(<vscale x 32 x i32> %va, <vscale
; CHECK-NEXT: add a1, sp, a1
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
-; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: vsetvli a3, zero, e8, mf2, ta, ma
-; CHECK-NEXT: slli a3, a1, 3
-; CHECK-NEXT: add a3, a0, a3
-; CHECK-NEXT: vl8re32.v v8, (a3)
-; CHECK-NEXT: slli a3, a1, 1
+; CHECK-NEXT: csrr a3, vlenb
+; CHECK-NEXT: srli a1, a3, 2
+; CHECK-NEXT: slli a4, a3, 3
+; CHECK-NEXT: add a4, a0, a4
+; CHECK-NEXT: vl8re32.v v8, (a4)
+; CHECK-NEXT: slli a3, a3, 1
; CHECK-NEXT: sub a4, a2, a3
; CHECK-NEXT: sltu a5, a2, a4
; CHECK-NEXT: addi a5, a5, -1
; CHECK-NEXT: and a4, a5, a4
-; CHECK-NEXT: srli a1, a1, 2
+; CHECK-NEXT: vsetvli a5, zero, e8, mf2, ta, ma
; CHECK-NEXT: vl8re32.v v0, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
diff --git a/llvm/test/CodeGen/RISCV/rvv/vfma-vp.ll b/llvm/test/CodeGen/RISCV/rvv/vfma-vp.ll
index a41c262116136..0f47236d66007 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vfma-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vfma-vp.ll
@@ -1125,22 +1125,22 @@ define <vscale x 16 x double> @vfma_vv_nxv16f64(<vscale x 16 x double> %va, <vsc
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
-; CHECK-NEXT: slli a3, a1, 3
-; CHECK-NEXT: add a5, a2, a3
+; CHECK-NEXT: srli a3, a1, 3
+; CHECK-NEXT: slli a5, a1, 3
+; CHECK-NEXT: add a6, a2, a5
+; CHECK-NEXT: vl8re64.v v8, (a6)
+; CHECK-NEXT: csrr a6, vlenb
+; CHECK-NEXT: slli a6, a6, 4
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: addi a6, a6, 16
+; CHECK-NEXT: vs8r.v v8, (a6) # Unknown-size Folded Spill
+; CHECK-NEXT: sub a6, a4, a1
+; CHECK-NEXT: sltu a7, a4, a6
+; CHECK-NEXT: addi a7, a7, -1
+; CHECK-NEXT: and a6, a7, a6
+; CHECK-NEXT: vsetvli a7, zero, e8, mf4, ta, ma
+; CHECK-NEXT: add a5, a0, a5
; CHECK-NEXT: vl8re64.v v8, (a5)
-; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: slli a5, a5, 4
-; CHECK-NEXT: add a5, sp, a5
-; CHECK-NEXT: addi a5, a5, 16
-; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: sub a5, a4, a1
-; CHECK-NEXT: sltu a6, a4, a5
-; CHECK-NEXT: addi a6, a6, -1
-; CHECK-NEXT: and a5, a6, a5
-; CHECK-NEXT: srli a6, a1, 3
-; CHECK-NEXT: add a3, a0, a3
-; CHECK-NEXT: vl8re64.v v8, (a3)
; CHECK-NEXT: vl8re64.v v16, (a2)
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: slli a2, a2, 3
@@ -1150,8 +1150,8 @@ define <vscale x 16 x double> @vfma_vv_nxv16f64(<vscale x 16 x double> %va, <vsc
; CHECK-NEXT: vl8re64.v v16, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vslidedown.vx v0, v0, a6
-; CHECK-NEXT: vsetvli zero, a5, e64, m8, ta, ma
+; CHECK-NEXT: vslidedown.vx v0, v0, a3
+; CHECK-NEXT: vsetvli zero, a6, e64, m8, ta, ma
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: li a2, 24
; CHECK-NEXT: mul a0, a0, a2
diff --git a/llvm/test/CodeGen/RISCV/rvv/vfmuladd-vp.ll b/llvm/test/CodeGen/RISCV/rvv/vfmuladd-vp.ll
index 292f27794f378..bacf9bae83ed7 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vfmuladd-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vfmuladd-vp.ll
@@ -1125,22 +1125,22 @@ define <vscale x 16 x double> @vfma_vv_nxv16f64(<vscale x 16 x double> %va, <vsc
; CHECK-NEXT: addi a1, a1, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: csrr a1, vlenb
-; CHECK-NEXT: vsetvli a3, zero, e8, mf4, ta, ma
-; CHECK-NEXT: slli a3, a1, 3
-; CHECK-NEXT: add a5, a2, a3
+; CHECK-NEXT: srli a3, a1, 3
+; CHECK-NEXT: slli a5, a1, 3
+; CHECK-NEXT: add a6, a2, a5
+; CHECK-NEXT: vl8re64.v v8, (a6)
+; CHECK-NEXT: csrr a6, vlenb
+; CHECK-NEXT: slli a6, a6, 4
+; CHECK-NEXT: add a6, sp, a6
+; CHECK-NEXT: addi a6, a6, 16
+; CHECK-NEXT: vs8r.v v8, (a6) # Unknown-size Folded Spill
+; CHECK-NEXT: sub a6, a4, a1
+; CHECK-NEXT: sltu a7, a4, a6
+; CHECK-NEXT: addi a7, a7, -1
+; CHECK-NEXT: and a6, a7, a6
+; CHECK-NEXT: vsetvli a7, zero, e8, mf4, ta, ma
+; CHECK-NEXT: add a5, a0, a5
; CHECK-NEXT: vl8re64.v v8, (a5)
-; CHECK-NEXT: csrr a5, vlenb
-; CHECK-NEXT: slli a5, a5, 4
-; CHECK-NEXT: add a5, sp, a5
-; CHECK-NEXT: addi a5, a5, 16
-; CHECK-NEXT: vs8r.v v8, (a5) # Unknown-size Folded Spill
-; CHECK-NEXT: sub a5, a4, a1
-; CHECK-NEXT: sltu a6, a4, a5
-; CHECK-NEXT: addi a6, a6, -1
-; CHECK-NEXT: and a5, a6, a5
-; CHECK-NEXT: srli a6, a1, 3
-; CHECK-NEXT: add a3, a0, a3
-; CHECK-NEXT: vl8re64.v v8, (a3)
; CHECK-NEXT: vl8re64.v v16, (a2)
; CHECK-NEXT: csrr a2, vlenb
; CHECK-NEXT: slli a2, a2, 3
@@ -1150,8 +1150,8 @@ define <vscale x 16 x double> @vfma_vv_nxv16f64(<vscale x 16 x double> %va, <vsc
; CHECK-NEXT: vl8re64.v v16, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vslidedown.vx v0, v0, a6
-; CHECK-NEXT: vsetvli zero, a5, e64, m8, ta, ma
+; CHECK-NEXT: vslidedown.vx v0, v0, a3
+; CHECK-NEXT: vsetvli zero, a6, e64, m8, ta, ma
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: li a2, 24
; CHECK-NEXT: mul a0, a0, a2
diff --git a/llvm/test/CodeGen/RISCV/rvv/vpmerge-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/vpmerge-sdnode.ll
index 76efdda15bf77..26f7c56f05cec 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vpmerge-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vpmerge-sdnode.ll
@@ -369,14 +369,14 @@ define <vscale x 128 x i8> @vpmerge_vv_nxv128i8(<vscale x 128 x i8> %va, <vscale
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a4, a0, a1
; CHECK-NEXT: vl8r.v v16, (a4)
-; CHECK-NEXT: vl8r.v v8, (a0)
-; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, ma
-; CHECK-NEXT: sub a0, a3, a1
+; CHECK-NEXT: vsetvli a4, zero, e8, m8, ta, ma
; CHECK-NEXT: vlm.v v0, (a2)
-; CHECK-NEXT: sltu a2, a3, a0
-; CHECK-NEXT: addi a2, a2, -1
-; CHECK-NEXT: and a0, a2, a0
-; CHECK-NEXT: vsetvli zero, a0, e8, m8, tu, ma
+; CHECK-NEXT: sub a2, a3, a1
+; CHECK-NEXT: sltu a4, a3, a2
+; CHECK-NEXT: addi a4, a4, -1
+; CHECK-NEXT: vl8r.v v8, (a0)
+; CHECK-NEXT: and a2, a4, a2
+; CHECK-NEXT: vsetvli zero, a2, e8, m8, tu, ma
; CHECK-NEXT: vmerge.vvm v16, v16, v24, v0
; CHECK-NEXT: bltu a3, a1, .LBB28_2
; CHECK-NEXT: # %bb.1:
diff --git a/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll b/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
index 0a5e50160fbc9..312378d393737 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vselect-vp.ll
@@ -373,10 +373,10 @@ define <vscale x 32 x i32> @select_nxv32i32(<vscale x 32 x i1> %a, <vscale x 32
; CHECK-NEXT: addi a5, a5, -1
; CHECK-NEXT: and a4, a5, a4
; CHECK-NEXT: srli a3, a3, 2
+; CHECK-NEXT: vsetvli a5, zero, e8, mf2, ta, ma
; CHECK-NEXT: vl8re32.v v0, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, ma
; CHECK-NEXT: vslidedown.vx v0, v24, a3
; CHECK-NEXT: vsetvli zero, a4, e32, m8, ta, ma
; CHECK-NEXT: vmerge.vvm v16, v8, v16, v0
@@ -430,10 +430,10 @@ define <vscale x 32 x i32> @select_evl_nxv32i32(<vscale x 32 x i1> %a, <vscale x
; CHECK-NEXT: addi a4, a4, -1
; CHECK-NEXT: and a3, a4, a3
; CHECK-NEXT: srli a4, a1, 2
+; CHECK-NEXT: vsetvli a5, zero, e8, mf2, ta, ma
; CHECK-NEXT: vl8re32.v v0, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, ma
; CHECK-NEXT: vslidedown.vx v0, v24, a4
; CHECK-NEXT: vsetvli zero, a3, e32, m8, ta, ma
; CHECK-NEXT: vmerge.vvm v16, v8, v16, v0
@@ -716,10 +716,10 @@ define <vscale x 16 x double> @select_nxv16f64(<vscale x 16 x i1> %a, <vscale x
; CHECK-NEXT: addi a4, a4, -1
; CHECK-NEXT: and a3, a4, a3
; CHECK-NEXT: srli a4, a1, 3
+; CHECK-NEXT: vsetvli a5, zero, e8, mf4, ta, ma
; CHECK-NEXT: vl8re64.v v0, (a0)
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vs8r.v v0, (a0) # Unknown-size Folded Spill
-; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, ma
; CHECK-NEXT: vslidedown.vx v0, v24, a4
; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
; CHECK-NEXT: vmerge.vvm v16, v8, v16, v0
diff --git a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.ll b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.ll
index 25aa3a7081a16..9d5ff00fd597d 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vsetvli-insert-crossbb.ll
@@ -242,7 +242,6 @@ define <vscale x 1 x double> @test6(i64 %avl, i8 zeroext %cond, <vscale x 1 x do
; CHECK-NEXT: andi a1, a1, 2
; CHECK-NEXT: beqz a1, .LBB5_4
; CHECK-NEXT: .LBB5_2: # %if.then4
-; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; CHECK-NEXT: lui a0, %hi(.LCPI5_0)
; CHECK-NEXT: addi a0, a0, %lo(.LCPI5_0)
; CHECK-NEXT: vlse64.v v9, (a0), zero
@@ -631,22 +630,22 @@ declare <vscale x 2 x i32> @llvm.riscv.vwadd.w.nxv2i32.nxv2i16(<vscale x 2 x i32
define void @vlmax(i64 %N, ptr %c, ptr %a, ptr %b) {
; CHECK-LABEL: vlmax:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: vsetvli a6, zero, e64, m1, ta, ma
; CHECK-NEXT: blez a0, .LBB12_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
-; CHECK-NEXT: li a5, 0
-; CHECK-NEXT: slli a4, a6, 3
+; CHECK-NEXT: li a4, 0
+; CHECK-NEXT: vsetvli a6, zero, e64, m1, ta, ma
+; CHECK-NEXT: slli a5, a6, 3
; CHECK-NEXT: .LBB12_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vle64.v v8, (a2)
; CHECK-NEXT: vle64.v v9, (a3)
; CHECK-NEXT: vfadd.vv v8, v8, v9
; CHECK-NEXT: vse64.v v8, (a1)
-; CHECK-NEXT: add a5, a5, a6
-; CHECK-NEXT: add a1, a1, a4
-; CHECK-NEXT: add a3, a3, a4
-; CHECK-NEXT: add a2, a2, a4
-; CHECK-NEXT: blt a5, a0, .LBB12_2
+; CHECK-NEXT: add a4, a4, a6
+; CHECK-NEXT: add a1, a1, a5
+; CHECK-NEXT: add a3, a3, a5
+; CHECK-NEXT: add a2, a2, a5
+; CHECK-NEXT: blt a4, a0, .LBB12_2
; CHECK-NEXT: .LBB12_3: # %for.end
; CHECK-NEXT: ret
entry:
@@ -678,18 +677,18 @@ for.end: ; preds = %for.body, %entry
define void @vector_init_vlmax(i64 %N, ptr %c) {
; CHECK-LABEL: vector_init_vlmax:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: vsetvli a2, zero, e64, m1, ta, ma
; CHECK-NEXT: blez a0, .LBB13_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
-; CHECK-NEXT: li a3, 0
-; CHECK-NEXT: slli a4, a2, 3
+; CHECK-NEXT: li a2, 0
+; CHECK-NEXT: vsetvli a3, zero, e64, m1, ta, ma
+; CHECK-NEXT: slli a4, a3, 3
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: .LBB13_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vse64.v v8, (a1)
-; CHECK-NEXT: add a3, a3, a2
+; CHECK-NEXT: add a2, a2, a3
; CHECK-NEXT: add a1, a1, a4
-; CHECK-NEXT: blt a3, a0, .LBB13_2
+; CHECK-NEXT: blt a2, a0, .LBB13_2
; CHECK-NEXT: .LBB13_3: # %for.end
; CHECK-NEXT: ret
entry:
@@ -714,20 +713,20 @@ for.end: ; preds = %for.body, %entry
define void @vector_init_vsetvli_N(i64 %N, ptr %c) {
; CHECK-LABEL: vector_init_vsetvli_N:
; CHECK: # %bb.0: # %entry
-; CHECK-NEXT: vsetvli a2, a0, e64, m1, ta, ma
; CHECK-NEXT: blez a0, .LBB14_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
-; CHECK-NEXT: li a3, 0
-; CHECK-NEXT: slli a4, a2, 3
+; CHECK-NEXT: li a2, 0
+; CHECK-NEXT: vsetvli a3, a0, e64, m1, ta, ma
+; CHECK-NEXT: slli a4, a3, 3
; CHECK-NEXT: vsetvli a5, zero, e64, m1, ta, ma
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: .LBB14_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
+; CHECK-NEXT: vsetvli zero, a3, e64, m1, ta, ma
; CHECK-NEXT: vse64.v v8, (a1)
-; CHECK-NEXT: add a3, a3, a2
+; CHECK-NEXT: add a2, a2, a3
; CHECK-NEXT: add a1, a1, a4
-; CHECK-NEXT: blt a3, a0, .LBB14_2
+; CHECK-NEXT: blt a2, a0, .LBB14_2
; CHECK-NEXT: .LBB14_3: # %for.end
; CHECK-NEXT: ret
entry:
diff --git a/llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll b/llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll
index f658a2c6b24a6..c3b19b59ec3d6 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vsetvli-regression.ll
@@ -11,9 +11,10 @@ define i32 @illegal_preserve_vl(<vscale x 2 x i32> %a, <vscale x 4 x i64> %x, pt
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a1, zero, e64, m4, ta, ma
; CHECK-NEXT: vadd.vv v12, v12, v12
-; CHECK-NEXT: vs4r.v v12, (a0)
; CHECK-NEXT: vsetvli zero, zero, e32, m2, ta, ma
-; CHECK-NEXT: vmv.x.s a0, v8
+; CHECK-NEXT: vmv.x.s a1, v8
+; CHECK-NEXT: vs4r.v v12, (a0)
+; CHECK-NEXT: mv a0, a1
; CHECK-NEXT: ret
%index = add <vscale x 4 x i64> %x, %x
store <vscale x 4 x i64> %index, ptr %y
More information about the llvm-commits
mailing list