Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[RISCV] Don't emit vxrm writes for vnclip(u).wi with shift of 0. #76578

Merged
merged 1 commit into from
Jan 2, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions llvm/lib/Target/RISCV/RISCVInsertWriteVXRM.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -198,13 +198,23 @@ char RISCVInsertWriteVXRM::ID = 0;
INITIALIZE_PASS(RISCVInsertWriteVXRM, DEBUG_TYPE, RISCV_INSERT_WRITE_VXRM_NAME,
false, false)

static bool ignoresVXRM(const MachineInstr &MI) {
switch (RISCV::getRVVMCOpcode(MI.getOpcode())) {
default:
return false;
case RISCV::VNCLIP_WI:
case RISCV::VNCLIPU_WI:
return MI.getOperand(3).getImm() == 0;
}
}

bool RISCVInsertWriteVXRM::computeVXRMChanges(const MachineBasicBlock &MBB) {
BlockData &BBInfo = BlockInfo[MBB.getNumber()];

bool NeedVXRMWrite = false;
for (const MachineInstr &MI : MBB) {
int VXRMIdx = RISCVII::getVXRMOpNum(MI.getDesc());
if (VXRMIdx >= 0) {
if (VXRMIdx >= 0 && !ignoresVXRM(MI)) {
unsigned NewVXRMImm = MI.getOperand(VXRMIdx).getImm();

if (!BBInfo.VXRMUse.isValid())
Expand Down Expand Up @@ -356,7 +366,7 @@ void RISCVInsertWriteVXRM::emitWriteVXRM(MachineBasicBlock &MBB) {

for (MachineInstr &MI : MBB) {
int VXRMIdx = RISCVII::getVXRMOpNum(MI.getDesc());
if (VXRMIdx >= 0) {
if (VXRMIdx >= 0 && !ignoresVXRM(MI)) {
unsigned NewVXRMImm = MI.getOperand(VXRMIdx).getImm();

if (PendingInsert || !Info.isStatic() ||
Expand Down
24 changes: 0 additions & 24 deletions llvm/test/CodeGen/RISCV/rvv/fpclamptosat_vec.ll
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,6 @@ define <2 x i32> @stest_f64i32(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.x.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -77,7 +76,6 @@ define <2 x i32> @utest_f64i32(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.xu.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -193,7 +191,6 @@ define <4 x i32> @stest_f32i32(<4 x float> %x) {
; CHECK-V: # %bb.0: # %entry
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfwcvt.rtz.x.f.v v10, v8
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -247,7 +244,6 @@ define <4 x i32> @utest_f32i32(<4 x float> %x) {
; CHECK-V: # %bb.0: # %entry
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfwcvt.rtz.xu.f.v v10, v8
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -497,7 +493,6 @@ define <4 x i32> @stest_f16i32(<4 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 3
; CHECK-V-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 2
Expand Down Expand Up @@ -666,7 +661,6 @@ define <4 x i32> @utesth_f16i32(<4 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 3
; CHECK-V-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 2
Expand Down Expand Up @@ -907,7 +901,6 @@ define <2 x i16> @stest_f64i16(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-V-NEXT: vfncvt.rtz.x.f.w v9, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v9, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -944,7 +937,6 @@ define <2 x i16> @utest_f64i16(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-V-NEXT: vfncvt.rtz.xu.f.w v9, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v9, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -1063,7 +1055,6 @@ define <4 x i16> @stest_f32i16(<4 x float> %x) {
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.x.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -1118,7 +1109,6 @@ define <4 x i16> @utest_f32i16(<4 x float> %x) {
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.xu.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -1495,7 +1485,6 @@ define <8 x i16> @stest_f16i16(<8 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 7
; CHECK-V-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 1
Expand Down Expand Up @@ -1774,7 +1763,6 @@ define <8 x i16> @utesth_f16i16(<8 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 7
; CHECK-V-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 1
Expand Down Expand Up @@ -3349,7 +3337,6 @@ define <2 x i32> @stest_f64i32_mm(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.x.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -3384,7 +3371,6 @@ define <2 x i32> @utest_f64i32_mm(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.xu.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -3497,7 +3483,6 @@ define <4 x i32> @stest_f32i32_mm(<4 x float> %x) {
; CHECK-V: # %bb.0: # %entry
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfwcvt.rtz.x.f.v v10, v8
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -3549,7 +3534,6 @@ define <4 x i32> @utest_f32i32_mm(<4 x float> %x) {
; CHECK-V: # %bb.0: # %entry
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfwcvt.rtz.xu.f.v v10, v8
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -3796,7 +3780,6 @@ define <4 x i32> @stest_f16i32_mm(<4 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 3
; CHECK-V-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 2
Expand Down Expand Up @@ -3963,7 +3946,6 @@ define <4 x i32> @utesth_f16i32_mm(<4 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 3
; CHECK-V-NEXT: vsetvli zero, zero, e32, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 2
Expand Down Expand Up @@ -4201,7 +4183,6 @@ define <2 x i16> @stest_f64i16_mm(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-V-NEXT: vfncvt.rtz.x.f.w v9, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v9, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -4236,7 +4217,6 @@ define <2 x i16> @utest_f64i16_mm(<2 x double> %x) {
; CHECK-V-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-V-NEXT: vfncvt.rtz.xu.f.w v9, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v9, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -4352,7 +4332,6 @@ define <4 x i16> @stest_f32i16_mm(<4 x float> %x) {
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.x.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -4405,7 +4384,6 @@ define <4 x i16> @utest_f32i16_mm(<4 x float> %x) {
; CHECK-V-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-V-NEXT: vfcvt.rtz.xu.f.v v8, v8
; CHECK-V-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v8, 0
; CHECK-V-NEXT: ret
entry:
Expand Down Expand Up @@ -4779,7 +4757,6 @@ define <8 x i16> @stest_f16i16_mm(<8 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 7
; CHECK-V-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclip.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 1
Expand Down Expand Up @@ -5054,7 +5031,6 @@ define <8 x i16> @utesth_f16i16_mm(<8 x half> %x) {
; CHECK-V-NEXT: vl2r.v v10, (a0) # Unknown-size Folded Reload
; CHECK-V-NEXT: vslideup.vi v10, v8, 7
; CHECK-V-NEXT: vsetvli zero, zero, e16, m1, ta, ma
; CHECK-V-NEXT: csrwi vxrm, 0
; CHECK-V-NEXT: vnclipu.wi v8, v10, 0
; CHECK-V-NEXT: csrr a0, vlenb
; CHECK-V-NEXT: slli a0, a0, 1
Expand Down
15 changes: 0 additions & 15 deletions llvm/test/CodeGen/RISCV/rvv/trunc-sat-clip.ll
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,6 @@ define void @trunc_sat_i8i16_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v8, v8, 0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
Expand All @@ -37,7 +36,6 @@ define void @trunc_sat_i8i16_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v8, v8, 0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -75,7 +73,6 @@ define void @trunc_sat_u8u16_min(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -109,7 +106,6 @@ define void @trunc_sat_u8u16_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
Expand All @@ -126,7 +122,6 @@ define void @trunc_sat_u8u16_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-NEXT: vle16.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse8.v v8, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -166,7 +161,6 @@ define void @trunc_sat_i16i32_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v8, v8, 0
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
Expand All @@ -183,7 +177,6 @@ define void @trunc_sat_i16i32_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v8, v8, 0
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -219,7 +212,6 @@ define void @trunc_sat_u16u32_min(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
Expand All @@ -235,7 +227,6 @@ define void @trunc_sat_u16u32_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
Expand All @@ -252,7 +243,6 @@ define void @trunc_sat_u16u32_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v8, v8, 0
; CHECK-NEXT: vse16.v v8, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -293,7 +283,6 @@ define void @trunc_sat_i32i64_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v10, v8, 0
; CHECK-NEXT: vse32.v v10, (a1)
; CHECK-NEXT: ret
Expand All @@ -310,7 +299,6 @@ define void @trunc_sat_i32i64_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclip.wi v10, v8, 0
; CHECK-NEXT: vse32.v v10, (a1)
; CHECK-NEXT: ret
Expand Down Expand Up @@ -347,7 +335,6 @@ define void @trunc_sat_u32u64_min(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v10, v8, 0
; CHECK-NEXT: vse32.v v10, (a1)
; CHECK-NEXT: ret
Expand All @@ -364,7 +351,6 @@ define void @trunc_sat_u32u64_maxmin(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v10, v8, 0
; CHECK-NEXT: vse32.v v10, (a1)
; CHECK-NEXT: ret
Expand All @@ -381,7 +367,6 @@ define void @trunc_sat_u32u64_minmax(ptr %x, ptr %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vle64.v v8, (a0)
; CHECK-NEXT: csrwi vxrm, 0
; CHECK-NEXT: vnclipu.wi v10, v8, 0
; CHECK-NEXT: vse32.v v10, (a1)
; CHECK-NEXT: ret
Expand Down