From 92ad6d57c21824ddb4bca2d01734c5d2c391b5b5 Mon Sep 17 00:00:00 2001
From: Lucas Prates <lucas.prates@arm.com>
Date: Fri, 5 Jun 2020 13:23:30 +0100
Subject: [PATCH] [ARM] Moving CMSE handling of half arguments and return to
 the backend

Summary:
As half-precision floating point arguments and returns were previously
coerced to either float or int32 by clang's codegen, the CMSE handling
of those was also performed in clang's side by zeroing the unused MSBs
of the coercer values.

This patch moves this handling to the backend's calling convention
lowering, making sure the high bits of the registers used by
half-precision arguments and returns are zeroed.

Reviewers: chill, rjmccall, ostannard

Reviewed By: ostannard

Subscribers: kristof.beyls, hiraditya, danielkiss, cfe-commits, llvm-commits

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D81428
---
 llvm/lib/Target/ARM/ARMISelLowering.cpp        |  34 ++
 llvm/test/CodeGen/ARM/cmse-clear-float-hard.ll | 448 ++++++++++++++++++++++++-
 2 files changed, 478 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 5e6c9b3..95132ec 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -2262,6 +2262,19 @@ ARMTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       Arg = DAG.getNode(ARMISD::VMOVrh, dl,
                         MVT::getIntegerVT(VA.getLocVT().getSizeInBits()), Arg);
       Arg = DAG.getNode(ISD::BITCAST, dl, VA.getLocVT(), Arg);
+    } else {
+      // f16 arguments could have been extended prior to argument lowering.
+      // Mask them arguments if this is a CMSE nonsecure call.
+      auto ArgVT = Outs[realArgIdx].ArgVT;
+      if (isCmseNSCall && (ArgVT == MVT::f16)) {
+        auto LocBits = VA.getLocVT().getSizeInBits();
+        auto MaskValue = APInt::getLowBitsSet(LocBits, ArgVT.getSizeInBits());
+        SDValue Mask =
+            DAG.getConstant(MaskValue, dl, MVT::getIntegerVT(LocBits));
+        Arg = DAG.getNode(ISD::BITCAST, dl, MVT::getIntegerVT(LocBits), Arg);
+        Arg = DAG.getNode(ISD::AND, dl, MVT::getIntegerVT(LocBits), Arg, Mask);
+        Arg = DAG.getNode(ISD::BITCAST, dl, VA.getLocVT(), Arg);
+      }
     }
 
     // f64 and v2f64 might be passed in i32 pairs and must be split into pieces
@@ -2928,6 +2941,27 @@ ARMTargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
       break;
     }
 
+    // Mask f16 arguments if this is a CMSE nonsecure entry.
+    auto RetVT = Outs[realRVLocIdx].ArgVT;
+    if (AFI->isCmseNSEntryFunction() && (RetVT == MVT::f16)) {
+      if (VA.needsCustom() && VA.getValVT() == MVT::f16) {
+        assert(Subtarget->hasFullFP16() &&
+               "Lowering f16 type argument without full fp16 support");
+        Arg =
+            DAG.getNode(ARMISD::VMOVrh, dl,
+                        MVT::getIntegerVT(VA.getLocVT().getSizeInBits()), Arg);
+        Arg = DAG.getNode(ISD::BITCAST, dl, VA.getLocVT(), Arg);
+      } else {
+        auto LocBits = VA.getLocVT().getSizeInBits();
+        auto MaskValue = APInt::getLowBitsSet(LocBits, RetVT.getSizeInBits());
+        SDValue Mask =
+            DAG.getConstant(MaskValue, dl, MVT::getIntegerVT(LocBits));
+        Arg = DAG.getNode(ISD::BITCAST, dl, MVT::getIntegerVT(LocBits), Arg);
+        Arg = DAG.getNode(ISD::AND, dl, MVT::getIntegerVT(LocBits), Arg, Mask);
+        Arg = DAG.getNode(ISD::BITCAST, dl, VA.getLocVT(), Arg);
+      }
+    }
+
     if (VA.needsCustom() &&
         (VA.getLocVT() == MVT::v2f64 || VA.getLocVT() == MVT::f64)) {
       if (VA.getLocVT() == MVT::v2f64) {
diff --git a/llvm/test/CodeGen/ARM/cmse-clear-float-hard.ll b/llvm/test/CodeGen/ARM/cmse-clear-float-hard.ll
index 1975b8f..444c689 100644
--- a/llvm/test/CodeGen/ARM/cmse-clear-float-hard.ll
+++ b/llvm/test/CodeGen/ARM/cmse-clear-float-hard.ll
@@ -4,13 +4,13 @@
 ; RUN: llc %s -o - -mtriple=thumbebv8m.main -mattr=+fp-armv8d16sp,+dsp -float-abi=hard | \
 ; RUN:   FileCheck %s --check-prefix=CHECK-8M --check-prefix=CHECK-8M-BE
 ; RUN: llc %s -o - -mtriple=thumbv8.1m.main -mattr=+fp-armv8d16sp,+dsp -float-abi=hard | \
-; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-81M-LE
+; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-NO-MVE --check-prefix=CHECK-81M-LE
 ; RUN: llc %s -o - -mtriple=thumbebv8.1m.main -mattr=+fp-armv8d16sp,+dsp -float-abi=hard | \
-; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-81M-BE
+; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-NO-MVE --check-prefix=CHECK-81M-BE
 ; RUN: llc %s -o - -mtriple=thumbv8.1m.main -mattr=+mve.fp -float-abi=hard | \
-; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-81M-LE
+; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-MVE --check-prefix=CHECK-81M-LE
 ; RUN: llc %s -o - -mtriple=thumbebv8.1m.main -mattr=+mve.fp -float-abi=hard | \
-; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-81M-BE
+; RUN:   FileCheck %s --check-prefix=CHECK-81M --check-prefix=CHECK-MVE --check-prefix=CHECK-81M-BE
 
 define float @f1(float (float)* nocapture %fptr) #0 {
 ; CHECK-8M-LABEL: f1:
@@ -809,3 +809,443 @@ entry:
   ret void
 }
 
+define half @h1(half (half)* nocapture %hptr) "cmse_nonsecure_entry" nounwind {
+; CHECK-8M-LABEL: h1:
+; CHECK-8M:       @ %bb.0:
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    vldr s0, .LCPI11_0
+; CHECK-8M-NEXT:    blx r0
+; CHECK-8M-NEXT:    vmov r0, s0
+; CHECK-8M-NEXT:    uxth r0, r0
+; CHECK-8M-NEXT:    vmov s0, r0
+; CHECK-8M-NEXT:    pop.w {r7, lr}
+; CHECK-8M-NEXT:    mrs r12, control
+; CHECK-8M-NEXT:    tst.w r12, #8
+; CHECK-8M-NEXT:    beq .LBB11_2
+; CHECK-8M-NEXT:  @ %bb.1:
+; CHECK-8M-NEXT:    vmrs r12, fpscr
+; CHECK-8M-NEXT:    vmov s1, lr
+; CHECK-8M-NEXT:    vmov d1, lr, lr
+; CHECK-8M-NEXT:    vmov d2, lr, lr
+; CHECK-8M-NEXT:    vmov d3, lr, lr
+; CHECK-8M-NEXT:    vmov d4, lr, lr
+; CHECK-8M-NEXT:    vmov d5, lr, lr
+; CHECK-8M-NEXT:    vmov d6, lr, lr
+; CHECK-8M-NEXT:    vmov d7, lr, lr
+; CHECK-8M-NEXT:    bic r12, r12, #159
+; CHECK-8M-NEXT:    bic r12, r12, #4026531840
+; CHECK-8M-NEXT:    vmsr fpscr, r12
+; CHECK-8M-NEXT:  .LBB11_2:
+; CHECK-8M-NEXT:    mov r0, lr
+; CHECK-8M-NEXT:    mov r1, lr
+; CHECK-8M-NEXT:    mov r2, lr
+; CHECK-8M-NEXT:    mov r3, lr
+; CHECK-8M-NEXT:    mov r12, lr
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, lr
+; CHECK-8M-NEXT:    bxns lr
+; CHECK-8M-NEXT:    .p2align 2
+; CHECK-8M-NEXT:  @ %bb.3:
+; CHECK-8M-NEXT:  .LCPI11_0:
+; CHECK-8M-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-NO-MVE-LABEL: h1:
+; CHECK-NO-MVE:       @ %bb.0:
+; CHECK-NO-MVE-NEXT:    vstr fpcxtns, [sp, #-4]!
+; CHECK-NO-MVE-NEXT:    push {r7, lr}
+; CHECK-NO-MVE-NEXT:    sub sp, #4
+; CHECK-NO-MVE-NEXT:    vldr s0, .LCPI11_0
+; CHECK-NO-MVE-NEXT:    blx r0
+; CHECK-NO-MVE-NEXT:    vmov r0, s0
+; CHECK-NO-MVE-NEXT:    uxth r0, r0
+; CHECK-NO-MVE-NEXT:    vmov s0, r0
+; CHECK-NO-MVE-NEXT:    add sp, #4
+; CHECK-NO-MVE-NEXT:    pop.w {r7, lr}
+; CHECK-NO-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, vpr}
+; CHECK-NO-MVE-NEXT:    vldr fpcxtns, [sp], #4
+; CHECK-NO-MVE-NEXT:    clrm {r0, r1, r2, r3, r12, apsr}
+; CHECK-NO-MVE-NEXT:    bxns lr
+; CHECK-NO-MVE-NEXT:    .p2align 2
+; CHECK-NO-MVE-NEXT:  @ %bb.1:
+; CHECK-NO-MVE-NEXT:  .LCPI11_0:
+; CHECK-NO-MVE-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-MVE-LABEL: h1:
+; CHECK-MVE:       @ %bb.0:
+; CHECK-MVE-NEXT:    vstr fpcxtns, [sp, #-4]!
+; CHECK-MVE-NEXT:    push {r7, lr}
+; CHECK-MVE-NEXT:    sub sp, #4
+; CHECK-MVE-NEXT:    vmov.f16 s0, #1.000000e+01
+; CHECK-MVE-NEXT:    vmov.f16 r1, s0
+; CHECK-MVE-NEXT:    vmov s0, r1
+; CHECK-MVE-NEXT:    blx r0
+; CHECK-MVE-NEXT:    vmov.f16 r0, s0
+; CHECK-MVE-NEXT:    vmov s0, r0
+; CHECK-MVE-NEXT:    add sp, #4
+; CHECK-MVE-NEXT:    pop.w {r7, lr}
+; CHECK-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, vpr}
+; CHECK-MVE-NEXT:    vldr fpcxtns, [sp], #4
+; CHECK-MVE-NEXT:    clrm {r0, r1, r2, r3, r12, apsr}
+; CHECK-MVE-NEXT:    bxns lr
+  %call = call half %hptr(half 10.0) nounwind
+  ret half %call
+}
+
+define half @h2(half (half)* nocapture %hptr) nounwind {
+; CHECK-8M-LABEL: h2:
+; CHECK-8M:       @ %bb.0: @ %entry
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    vldr s0, .LCPI12_0
+; CHECK-8M-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    bic r0, r0, #1
+; CHECK-8M-NEXT:    sub sp, #136
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlstm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    ldr r1, [sp, #64]
+; CHECK-8M-NEXT:    bic r1, r1, #159
+; CHECK-8M-NEXT:    bic r1, r1, #4026531840
+; CHECK-8M-NEXT:    vmsr fpscr, r1
+; CHECK-8M-NEXT:    mov r1, r0
+; CHECK-8M-NEXT:    mov r2, r0
+; CHECK-8M-NEXT:    mov r3, r0
+; CHECK-8M-NEXT:    mov r4, r0
+; CHECK-8M-NEXT:    mov r5, r0
+; CHECK-8M-NEXT:    mov r6, r0
+; CHECK-8M-NEXT:    mov r7, r0
+; CHECK-8M-NEXT:    mov r8, r0
+; CHECK-8M-NEXT:    mov r9, r0
+; CHECK-8M-NEXT:    mov r10, r0
+; CHECK-8M-NEXT:    mov r11, r0
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, r0
+; CHECK-8M-NEXT:    blxns r0
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlldm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    add sp, #136
+; CHECK-8M-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    pop {r7, pc}
+; CHECK-8M-NEXT:    .p2align 2
+; CHECK-8M-NEXT:  @ %bb.1:
+; CHECK-8M-NEXT:  .LCPI12_0:
+; CHECK-8M-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-NO-MVE-LABEL: h2:
+; CHECK-NO-MVE:       @ %bb.0: @ %entry
+; CHECK-NO-MVE-NEXT:    push {r7, lr}
+; CHECK-NO-MVE-NEXT:    vldr s0, .LCPI12_0
+; CHECK-NO-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    bic r0, r0, #1
+; CHECK-NO-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-NO-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-NO-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-NO-MVE-NEXT:    blxns r0
+; CHECK-NO-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-NO-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    pop {r7, pc}
+; CHECK-NO-MVE-NEXT:    .p2align 2
+; CHECK-NO-MVE-NEXT:  @ %bb.1:
+; CHECK-NO-MVE-NEXT:  .LCPI12_0:
+; CHECK-NO-MVE-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-MVE-LABEL: h2:
+; CHECK-MVE:       @ %bb.0: @ %entry
+; CHECK-MVE-NEXT:    push {r7, lr}
+; CHECK-MVE-NEXT:    vmov.f16 s0, #1.000000e+01
+; CHECK-MVE-NEXT:    vmov.f16 r1, s0
+; CHECK-MVE-NEXT:    vmov s0, r1
+; CHECK-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    bic r0, r0, #1
+; CHECK-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-MVE-NEXT:    blxns r0
+; CHECK-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    pop {r7, pc}
+entry:
+  %call = call half %hptr(half 10.0) "cmse_nonsecure_call" nounwind
+  ret half %call
+}
+
+define half @h3(half (half)* nocapture %hptr) nounwind {
+; CHECK-8M-LABEL: h3:
+; CHECK-8M:       @ %bb.0: @ %entry
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    vldr s0, .LCPI13_0
+; CHECK-8M-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    bic r0, r0, #1
+; CHECK-8M-NEXT:    sub sp, #136
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlstm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    ldr r1, [sp, #64]
+; CHECK-8M-NEXT:    bic r1, r1, #159
+; CHECK-8M-NEXT:    bic r1, r1, #4026531840
+; CHECK-8M-NEXT:    vmsr fpscr, r1
+; CHECK-8M-NEXT:    mov r1, r0
+; CHECK-8M-NEXT:    mov r2, r0
+; CHECK-8M-NEXT:    mov r3, r0
+; CHECK-8M-NEXT:    mov r4, r0
+; CHECK-8M-NEXT:    mov r5, r0
+; CHECK-8M-NEXT:    mov r6, r0
+; CHECK-8M-NEXT:    mov r7, r0
+; CHECK-8M-NEXT:    mov r8, r0
+; CHECK-8M-NEXT:    mov r9, r0
+; CHECK-8M-NEXT:    mov r10, r0
+; CHECK-8M-NEXT:    mov r11, r0
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, r0
+; CHECK-8M-NEXT:    blxns r0
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlldm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    add sp, #136
+; CHECK-8M-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    pop {r7, pc}
+; CHECK-8M-NEXT:    .p2align 2
+; CHECK-8M-NEXT:  @ %bb.1:
+; CHECK-8M-NEXT:  .LCPI13_0:
+; CHECK-8M-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-NO-MVE-LABEL: h3:
+; CHECK-NO-MVE:       @ %bb.0: @ %entry
+; CHECK-NO-MVE-NEXT:    push {r7, lr}
+; CHECK-NO-MVE-NEXT:    vldr s0, .LCPI13_0
+; CHECK-NO-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    bic r0, r0, #1
+; CHECK-NO-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-NO-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-NO-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-NO-MVE-NEXT:    blxns r0
+; CHECK-NO-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-NO-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    pop {r7, pc}
+; CHECK-NO-MVE-NEXT:    .p2align 2
+; CHECK-NO-MVE-NEXT:  @ %bb.1:
+; CHECK-NO-MVE-NEXT:  .LCPI13_0:
+; CHECK-NO-MVE-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-MVE-LABEL: h3:
+; CHECK-MVE:       @ %bb.0: @ %entry
+; CHECK-MVE-NEXT:    push {r7, lr}
+; CHECK-MVE-NEXT:    vmov.f16 s0, #1.000000e+01
+; CHECK-MVE-NEXT:    vmov.f16 r1, s0
+; CHECK-MVE-NEXT:    vmov s0, r1
+; CHECK-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    bic r0, r0, #1
+; CHECK-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-MVE-NEXT:    blxns r0
+; CHECK-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    pop {r7, pc}
+entry:
+  %call = tail call half %hptr(half 10.0) "cmse_nonsecure_call" nounwind
+  ret half %call
+}
+
+define half @h4(half ()* nocapture %hptr) nounwind {
+; CHECK-8M-LABEL: h4:
+; CHECK-8M:       @ %bb.0: @ %entry
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    bic r0, r0, #1
+; CHECK-8M-NEXT:    sub sp, #136
+; CHECK-8M-NEXT:    vlstm sp
+; CHECK-8M-NEXT:    mov r1, r0
+; CHECK-8M-NEXT:    mov r2, r0
+; CHECK-8M-NEXT:    mov r3, r0
+; CHECK-8M-NEXT:    mov r4, r0
+; CHECK-8M-NEXT:    mov r5, r0
+; CHECK-8M-NEXT:    mov r6, r0
+; CHECK-8M-NEXT:    mov r7, r0
+; CHECK-8M-NEXT:    mov r8, r0
+; CHECK-8M-NEXT:    mov r9, r0
+; CHECK-8M-NEXT:    mov r10, r0
+; CHECK-8M-NEXT:    mov r11, r0
+; CHECK-8M-NEXT:    mov r12, r0
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, r0
+; CHECK-8M-NEXT:    blxns r0
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlldm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    add sp, #136
+; CHECK-8M-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    pop {r7, pc}
+;
+; CHECK-81M-LABEL: h4:
+; CHECK-81M:       @ %bb.0: @ %entry
+; CHECK-81M-NEXT:    push {r7, lr}
+; CHECK-81M-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-81M-NEXT:    bic r0, r0, #1
+; CHECK-81M-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-81M-NEXT:    vscclrm {s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-81M-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-81M-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-81M-NEXT:    blxns r0
+; CHECK-81M-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-81M-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-81M-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-81M-NEXT:    pop {r7, pc}
+entry:
+  %call = call half %hptr() "cmse_nonsecure_call" nounwind
+  ret half %call
+}
+
+define half @h1_minsize(half (half)* nocapture %hptr) "cmse_nonsecure_entry" minsize nounwind {
+; CHECK-8M-LABEL: h1_minsize:
+; CHECK-8M:       @ %bb.0: @ %entry
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    vldr s0, .LCPI15_0
+; CHECK-8M-NEXT:    blx r0
+; CHECK-8M-NEXT:    vmov r0, s0
+; CHECK-8M-NEXT:    uxth r0, r0
+; CHECK-8M-NEXT:    vmov s0, r0
+; CHECK-8M-NEXT:    pop.w {r7, lr}
+; CHECK-8M-NEXT:    vmrs r12, fpscr
+; CHECK-8M-NEXT:    vmov s1, lr
+; CHECK-8M-NEXT:    vmov d1, lr, lr
+; CHECK-8M-NEXT:    mov r0, lr
+; CHECK-8M-NEXT:    vmov d2, lr, lr
+; CHECK-8M-NEXT:    mov r1, lr
+; CHECK-8M-NEXT:    vmov d3, lr, lr
+; CHECK-8M-NEXT:    mov r2, lr
+; CHECK-8M-NEXT:    vmov d4, lr, lr
+; CHECK-8M-NEXT:    mov r3, lr
+; CHECK-8M-NEXT:    vmov d5, lr, lr
+; CHECK-8M-NEXT:    vmov d6, lr, lr
+; CHECK-8M-NEXT:    vmov d7, lr, lr
+; CHECK-8M-NEXT:    bic r12, r12, #159
+; CHECK-8M-NEXT:    bic r12, r12, #4026531840
+; CHECK-8M-NEXT:    vmsr fpscr, r12
+; CHECK-8M-NEXT:    mov r12, lr
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, lr
+; CHECK-8M-NEXT:    bxns lr
+; CHECK-8M-NEXT:    .p2align 2
+; CHECK-8M-NEXT:  @ %bb.1:
+; CHECK-8M-NEXT:  .LCPI15_0:
+; CHECK-8M-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-NO-MVE-LABEL: h1_minsize:
+; CHECK-NO-MVE:       @ %bb.0: @ %entry
+; CHECK-NO-MVE-NEXT:    vstr fpcxtns, [sp, #-4]!
+; CHECK-NO-MVE-NEXT:    push {r6, r7, lr}
+; CHECK-NO-MVE-NEXT:    vldr s0, .LCPI15_0
+; CHECK-NO-MVE-NEXT:    blx r0
+; CHECK-NO-MVE-NEXT:    vmov r0, s0
+; CHECK-NO-MVE-NEXT:    uxth r0, r0
+; CHECK-NO-MVE-NEXT:    vmov s0, r0
+; CHECK-NO-MVE-NEXT:    pop.w {r3, r7, lr}
+; CHECK-NO-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, vpr}
+; CHECK-NO-MVE-NEXT:    vldr fpcxtns, [sp], #4
+; CHECK-NO-MVE-NEXT:    clrm {r0, r1, r2, r3, r12, apsr}
+; CHECK-NO-MVE-NEXT:    bxns lr
+; CHECK-NO-MVE-NEXT:    .p2align 2
+; CHECK-NO-MVE-NEXT:  @ %bb.1:
+; CHECK-NO-MVE-NEXT:  .LCPI15_0:
+; CHECK-NO-MVE-NEXT:    .long 0x00004900 @ float 2.61874657E-41
+;
+; CHECK-MVE-LABEL: h1_minsize:
+; CHECK-MVE:       @ %bb.0: @ %entry
+; CHECK-MVE-NEXT:    vstr fpcxtns, [sp, #-4]!
+; CHECK-MVE-NEXT:    push {r6, r7, lr}
+; CHECK-MVE-NEXT:    vmov.f16 s0, #1.000000e+01
+; CHECK-MVE-NEXT:    vmov.f16 r1, s0
+; CHECK-MVE-NEXT:    vmov s0, r1
+; CHECK-MVE-NEXT:    blx r0
+; CHECK-MVE-NEXT:    vmov.f16 r0, s0
+; CHECK-MVE-NEXT:    vmov s0, r0
+; CHECK-MVE-NEXT:    pop.w {r3, r7, lr}
+; CHECK-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, vpr}
+; CHECK-MVE-NEXT:    vldr fpcxtns, [sp], #4
+; CHECK-MVE-NEXT:    clrm {r0, r1, r2, r3, r12, apsr}
+; CHECK-MVE-NEXT:    bxns lr
+entry:
+  %call = call half %hptr(half 10.0) nounwind
+  ret half %call
+}
+
+define half @h1_arg(half (half)* nocapture %hptr, half %harg) nounwind {
+; CHECK-8M-LABEL: h1_arg:
+; CHECK-8M:       @ %bb.0: @ %entry
+; CHECK-8M-NEXT:    push {r7, lr}
+; CHECK-8M-NEXT:    vmov r1, s0
+; CHECK-8M-NEXT:    uxth r1, r1
+; CHECK-8M-NEXT:    vmov s0, r1
+; CHECK-8M-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    bic r0, r0, #1
+; CHECK-8M-NEXT:    sub sp, #136
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlstm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    ldr r1, [sp, #64]
+; CHECK-8M-NEXT:    bic r1, r1, #159
+; CHECK-8M-NEXT:    bic r1, r1, #4026531840
+; CHECK-8M-NEXT:    vmsr fpscr, r1
+; CHECK-8M-NEXT:    mov r1, r0
+; CHECK-8M-NEXT:    mov r2, r0
+; CHECK-8M-NEXT:    mov r3, r0
+; CHECK-8M-NEXT:    mov r4, r0
+; CHECK-8M-NEXT:    mov r5, r0
+; CHECK-8M-NEXT:    mov r6, r0
+; CHECK-8M-NEXT:    mov r7, r0
+; CHECK-8M-NEXT:    mov r8, r0
+; CHECK-8M-NEXT:    mov r9, r0
+; CHECK-8M-NEXT:    mov r10, r0
+; CHECK-8M-NEXT:    mov r11, r0
+; CHECK-8M-NEXT:    msr apsr_nzcvqg, r0
+; CHECK-8M-NEXT:    blxns r0
+; CHECK-8M-NEXT:    vmov r12, s0
+; CHECK-8M-NEXT:    vlldm sp
+; CHECK-8M-NEXT:    vmov s0, r12
+; CHECK-8M-NEXT:    add sp, #136
+; CHECK-8M-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-8M-NEXT:    pop {r7, pc}
+;
+; CHECK-NO-MVE-LABEL: h1_arg:
+; CHECK-NO-MVE:       @ %bb.0: @ %entry
+; CHECK-NO-MVE-NEXT:    push {r7, lr}
+; CHECK-NO-MVE-NEXT:    vmov r1, s0
+; CHECK-NO-MVE-NEXT:    uxth r1, r1
+; CHECK-NO-MVE-NEXT:    vmov s0, r1
+; CHECK-NO-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    bic r0, r0, #1
+; CHECK-NO-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-NO-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-NO-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-NO-MVE-NEXT:    blxns r0
+; CHECK-NO-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-NO-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-NO-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-NO-MVE-NEXT:    pop {r7, pc}
+;
+; CHECK-MVE-LABEL: h1_arg:
+; CHECK-MVE:       @ %bb.0: @ %entry
+; CHECK-MVE-NEXT:    push {r7, lr}
+; CHECK-MVE-NEXT:    vmov.f16 r1, s0
+; CHECK-MVE-NEXT:    vmov s0, r1
+; CHECK-MVE-NEXT:    push.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    bic r0, r0, #1
+; CHECK-MVE-NEXT:    vpush {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    vscclrm {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15, s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31, vpr}
+; CHECK-MVE-NEXT:    vstr fpcxts, [sp, #-8]!
+; CHECK-MVE-NEXT:    clrm {r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11, r12, apsr}
+; CHECK-MVE-NEXT:    blxns r0
+; CHECK-MVE-NEXT:    vldr fpcxts, [sp], #8
+; CHECK-MVE-NEXT:    vpop {s16, s17, s18, s19, s20, s21, s22, s23, s24, s25, s26, s27, s28, s29, s30, s31}
+; CHECK-MVE-NEXT:    pop.w {r4, r5, r6, r7, r8, r9, r10, r11}
+; CHECK-MVE-NEXT:    pop {r7, pc}
+entry:
+  %call = call half %hptr(half %harg) "cmse_nonsecure_call" nounwind
+  ret half %call
+}
+
-- 
2.7.4