[RISCV] Ensure the entire stack is aligned to the RVV stack alignment

[frasercrmck]

Summary

This patch fixes another bug in the RVV frame lowering. While some frame
objects with non-default stack IDs (such scalable-vector alloca
instructions) are considered in the target-independent max alignment
calculations, others (for example, during calling-convention lowering)
are not. This means we'd occasionally align the base of the stack to
only 16 bytes, with no way to ensure that the RVV section contained
within that is aligned to anything higher.

[frasercrmck]

fix typo

[frasercrmck]

While this bug is reproducible on main, there's no way to properly fix the codegen without D125787 as we lack the ability to ensure RVV alignment beyond 8, and we don't need to ensure an alignment of 8 as we get that for free. So I thought it better to base this patch on D125787.

[StephenFan]

LGTM.

llvm/lib/Target/RISCV/RISCVFrameLowering.cpp

void RISCVFrameLowering::processFunctionBeforeFrameFinalized(
 
   int64_t RVVStackSize;
   Align RVVStackAlign;
   std::tie(RVVStackSize, RVVStackAlign) = assignRVVStackObjectOffsets(MFI);
 
   RVFI->setRVVStackSize(RVVStackSize);
   RVFI->setRVVStackAlign(RVVStackAlign);
 
+  // Ensure the entire stack is aligned to at least the RVV requirement: some
+  // scalable-vector object alignments are not considered by the
+  // target-independent code.
+  MFI.ensureMaxAlignment(RVVStackAlign);
+
   const RISCVInstrInfo &TII = *MF.getSubtarget<RISCVSubtarget>().getInstrInfo();
 
   // estimateStackSize has been observed to under-estimate the final stack
   // size, so give ourselves wiggle-room by checking for stack size
   // representable an 11-bit signed field rather than 12-bits.
   // FIXME: It may be possible to craft a function with a small stack that
   // still needs an emergency spill slot for branch relaxation. This case
   // would currently be missed.

llvm/test/CodeGen/RISCV/rvv/calling-conv-fastcc.ll

 
 define fastcc <vscale x 32 x i32> @ret_nxv32i32_call_nxv32i32_nxv32i32_i32(<vscale x 32 x i32> %x, <vscale x 32 x i32> %y, i32 %w) {
 ; RV32-LABEL: ret_nxv32i32_call_nxv32i32_nxv32i32_i32:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    addi sp, sp, -144
 ; RV32-NEXT:    .cfi_def_cfa_offset 144
 ; RV32-NEXT:    sw ra, 140(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    .cfi_offset ra, -4
+; RV32-NEXT:    addi s0, sp, 144
+; RV32-NEXT:    .cfi_def_cfa s0, 0
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 4
 ; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    andi sp, sp, -128
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 3
 ; RV32-NEXT:    add a3, a0, a1
 ; RV32-NEXT:    vl8re32.v v24, (a3)
 ; RV32-NEXT:    vl8re32.v v0, (a0)
 ; RV32-NEXT:    addi a0, sp, 128
 ; RV32-NEXT:    add a0, a0, a1
 ; RV32-NEXT:    vs8r.v v16, (a0)
 ; RV32-NEXT:    addi a0, sp, 128
 ; RV32-NEXT:    li a3, 2
 ; RV32-NEXT:    addi a1, sp, 128
 ; RV32-NEXT:    vs8r.v v8, (a1)
 ; RV32-NEXT:    vmv8r.v v8, v0
 ; RV32-NEXT:    vmv8r.v v16, v24
 ; RV32-NEXT:    call ext2@plt
-; RV32-NEXT:    csrr a0, vlenb
-; RV32-NEXT:    slli a0, a0, 4
-; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, s0, -144
 ; RV32-NEXT:    lw ra, 140(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    addi sp, sp, 144
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: ret_nxv32i32_call_nxv32i32_nxv32i32_i32:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    addi sp, sp, -144
 ; RV64-NEXT:    .cfi_def_cfa_offset 144
 ; RV64-NEXT:    sd ra, 136(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    .cfi_offset ra, -8
+; RV64-NEXT:    addi s0, sp, 144
+; RV64-NEXT:    .cfi_def_cfa s0, 0
 ; RV64-NEXT:    csrr a1, vlenb
 ; RV64-NEXT:    slli a1, a1, 4
 ; RV64-NEXT:    sub sp, sp, a1
+; RV64-NEXT:    andi sp, sp, -128
 ; RV64-NEXT:    csrr a1, vlenb
 ; RV64-NEXT:    slli a1, a1, 3
 ; RV64-NEXT:    add a3, a0, a1
 ; RV64-NEXT:    vl8re32.v v24, (a3)
 ; RV64-NEXT:    vl8re32.v v0, (a0)
 ; RV64-NEXT:    addi a0, sp, 128
 ; RV64-NEXT:    add a0, a0, a1
 ; RV64-NEXT:    vs8r.v v16, (a0)
 ; RV64-NEXT:    addi a0, sp, 128
 ; RV64-NEXT:    li a3, 2
 ; RV64-NEXT:    addi a1, sp, 128
 ; RV64-NEXT:    vs8r.v v8, (a1)
 ; RV64-NEXT:    vmv8r.v v8, v0
 ; RV64-NEXT:    vmv8r.v v16, v24
 ; RV64-NEXT:    call ext2@plt
-; RV64-NEXT:    csrr a0, vlenb
-; RV64-NEXT:    slli a0, a0, 4
-; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, s0, -144
 ; RV64-NEXT:    ld ra, 136(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    addi sp, sp, 144
 ; RV64-NEXT:    ret
   %t = call fastcc <vscale x 32 x i32> @ext2(<vscale x 32 x i32> %y, <vscale x 32 x i32> %x, i32 %w, i32 2)
   ret <vscale x 32 x i32> %t
 }
 
 define fastcc <vscale x 32 x i32> @ret_nxv32i32_call_nxv32i32_nxv32i32_nxv32i32_i32(<vscale x 32 x i32> %x, <vscale x 32 x i32> %y, <vscale x 32 x i32> %z, i32 %w) {
 ; RV32-LABEL: ret_nxv32i32_call_nxv32i32_nxv32i32_nxv32i32_i32:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    addi sp, sp, -144
 ; RV32-NEXT:    .cfi_def_cfa_offset 144
 ; RV32-NEXT:    sw ra, 140(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    .cfi_offset ra, -4
+; RV32-NEXT:    addi s0, sp, 144
+; RV32-NEXT:    .cfi_def_cfa s0, 0
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    li a3, 48
 ; RV32-NEXT:    mul a1, a1, a3
 ; RV32-NEXT:    sub sp, sp, a1
+; RV32-NEXT:    andi sp, sp, -128
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 3
 ; RV32-NEXT:    add a3, a2, a1
 ; RV32-NEXT:    vl8re32.v v24, (a3)
 ; RV32-NEXT:    csrr a3, vlenb
 ; RV32-NEXT:    slli a3, a3, 3
 ; RV32-NEXT:    add a3, sp, a3
 ; RV32-NEXT:    addi a3, a3, 128

 ; RV32-NEXT:    addi a1, sp, 128
 ; RV32-NEXT:    vl8re8.v v8, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    csrr a1, vlenb
 ; RV32-NEXT:    slli a1, a1, 3
 ; RV32-NEXT:    add a1, sp, a1
 ; RV32-NEXT:    addi a1, a1, 128
 ; RV32-NEXT:    vl8re8.v v16, (a1) # Unknown-size Folded Reload
 ; RV32-NEXT:    call ext3@plt
-; RV32-NEXT:    csrr a0, vlenb
-; RV32-NEXT:    li a1, 48
-; RV32-NEXT:    mul a0, a0, a1
-; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, s0, -144
 ; RV32-NEXT:    lw ra, 140(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    addi sp, sp, 144
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: ret_nxv32i32_call_nxv32i32_nxv32i32_nxv32i32_i32:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    addi sp, sp, -144
 ; RV64-NEXT:    .cfi_def_cfa_offset 144
 ; RV64-NEXT:    sd ra, 136(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    .cfi_offset ra, -8
+; RV64-NEXT:    addi s0, sp, 144
+; RV64-NEXT:    .cfi_def_cfa s0, 0
 ; RV64-NEXT:    csrr a1, vlenb
 ; RV64-NEXT:    li a3, 48
 ; RV64-NEXT:    mul a1, a1, a3
 ; RV64-NEXT:    sub sp, sp, a1
+; RV64-NEXT:    andi sp, sp, -128
 ; RV64-NEXT:    csrr a1, vlenb
 ; RV64-NEXT:    slli a1, a1, 3
 ; RV64-NEXT:    add a3, a2, a1
 ; RV64-NEXT:    vl8re32.v v24, (a3)
 ; RV64-NEXT:    csrr a3, vlenb
 ; RV64-NEXT:    slli a3, a3, 3
 ; RV64-NEXT:    add a3, sp, a3
 ; RV64-NEXT:    addi a3, a3, 128

 ; RV64-NEXT:    addi a1, sp, 128
 ; RV64-NEXT:    vl8re8.v v8, (a1) # Unknown-size Folded Reload
 ; RV64-NEXT:    csrr a1, vlenb
 ; RV64-NEXT:    slli a1, a1, 3
 ; RV64-NEXT:    add a1, sp, a1
 ; RV64-NEXT:    addi a1, a1, 128
 ; RV64-NEXT:    vl8re8.v v16, (a1) # Unknown-size Folded Reload
 ; RV64-NEXT:    call ext3@plt
-; RV64-NEXT:    csrr a0, vlenb
-; RV64-NEXT:    li a1, 48
-; RV64-NEXT:    mul a0, a0, a1
-; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, s0, -144
 ; RV64-NEXT:    ld ra, 136(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    addi sp, sp, 144
 ; RV64-NEXT:    ret
   %t = call fastcc <vscale x 32 x i32> @ext3(<vscale x 32 x i32> %z, <vscale x 32 x i32> %y, <vscale x 32 x i32> %x, i32 %w, i32 42)
   ret <vscale x 32 x i32> %t
 }
 
 ; A test case where the normal calling convention would pass directly via the

 ; Calling the function above. Ensure we pass the arguments correctly.
 define fastcc <vscale x 32 x i32> @pass_vector_arg_indirect_stack(<vscale x 32 x i32> %x, <vscale x 32 x i32> %y, <vscale x 32 x i32> %z) {
 ; RV32-LABEL: pass_vector_arg_indirect_stack:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    addi sp, sp, -144
 ; RV32-NEXT:    .cfi_def_cfa_offset 144
 ; RV32-NEXT:    sw ra, 140(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    .cfi_offset ra, -4
+; RV32-NEXT:    addi s0, sp, 144
+; RV32-NEXT:    .cfi_def_cfa s0, 0
 ; RV32-NEXT:    csrr a0, vlenb
 ; RV32-NEXT:    slli a0, a0, 5
 ; RV32-NEXT:    sub sp, sp, a0
+; RV32-NEXT:    andi sp, sp, -128
 ; RV32-NEXT:    csrr a0, vlenb
 ; RV32-NEXT:    slli a0, a0, 3
 ; RV32-NEXT:    addi a1, sp, 128
 ; RV32-NEXT:    add a1, a1, a0
 ; RV32-NEXT:    vsetvli a2, zero, e32, m8, ta, mu
 ; RV32-NEXT:    vmv.v.i v8, 0
 ; RV32-NEXT:    vs8r.v v8, (a1)
 ; RV32-NEXT:    csrr a1, vlenb

 ; RV32-NEXT:    csrr a0, vlenb
 ; RV32-NEXT:    slli a0, a0, 4
 ; RV32-NEXT:    add a0, sp, a0
 ; RV32-NEXT:    addi a0, a0, 128
 ; RV32-NEXT:    vs8r.v v8, (a0)
 ; RV32-NEXT:    li a0, 0
 ; RV32-NEXT:    vmv.v.i v16, 0
 ; RV32-NEXT:    call vector_arg_indirect_stack@plt
-; RV32-NEXT:    csrr a0, vlenb
-; RV32-NEXT:    slli a0, a0, 5
-; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, s0, -144
 ; RV32-NEXT:    lw ra, 140(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    addi sp, sp, 144
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: pass_vector_arg_indirect_stack:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    addi sp, sp, -144
 ; RV64-NEXT:    .cfi_def_cfa_offset 144
 ; RV64-NEXT:    sd ra, 136(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    .cfi_offset ra, -8
+; RV64-NEXT:    addi s0, sp, 144
+; RV64-NEXT:    .cfi_def_cfa s0, 0
 ; RV64-NEXT:    csrr a0, vlenb
 ; RV64-NEXT:    slli a0, a0, 5
 ; RV64-NEXT:    sub sp, sp, a0
+; RV64-NEXT:    andi sp, sp, -128
 ; RV64-NEXT:    csrr a0, vlenb
 ; RV64-NEXT:    slli a0, a0, 3
 ; RV64-NEXT:    addi a1, sp, 128
 ; RV64-NEXT:    add a1, a1, a0
 ; RV64-NEXT:    vsetvli a2, zero, e32, m8, ta, mu
 ; RV64-NEXT:    vmv.v.i v8, 0
 ; RV64-NEXT:    vs8r.v v8, (a1)
 ; RV64-NEXT:    csrr a1, vlenb

 ; RV64-NEXT:    csrr a0, vlenb
 ; RV64-NEXT:    slli a0, a0, 4
 ; RV64-NEXT:    add a0, sp, a0
 ; RV64-NEXT:    addi a0, a0, 128
 ; RV64-NEXT:    vs8r.v v8, (a0)
 ; RV64-NEXT:    li a0, 0
 ; RV64-NEXT:    vmv.v.i v16, 0
 ; RV64-NEXT:    call vector_arg_indirect_stack@plt
-; RV64-NEXT:    csrr a0, vlenb
-; RV64-NEXT:    slli a0, a0, 5
-; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, s0, -144
 ; RV64-NEXT:    ld ra, 136(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    addi sp, sp, 144
 ; RV64-NEXT:    ret
   %s = call fastcc <vscale x 32 x i32> @vector_arg_indirect_stack(i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, <vscale x 32 x i32> zeroinitializer, <vscale x 32 x i32> zeroinitializer, <vscale x 32 x i32> zeroinitializer, i32 8)
   ret <vscale x 32 x i32> %s
 }

llvm/test/CodeGen/RISCV/rvv/calling-conv.ll

 ; Call the function above. Check that we set the arguments correctly.
 define <vscale x 32 x i32> @caller_scalable_vector_split_indirect(<vscale x 32 x i32> %x) {
 ; RV32-LABEL: caller_scalable_vector_split_indirect:
 ; RV32:       # %bb.0:
 ; RV32-NEXT:    addi sp, sp, -144
 ; RV32-NEXT:    .cfi_def_cfa_offset 144
 ; RV32-NEXT:    sw ra, 140(sp) # 4-byte Folded Spill
 ; RV32-NEXT:    .cfi_offset ra, -4
+; RV32-NEXT:    addi s0, sp, 144
+; RV32-NEXT:    .cfi_def_cfa s0, 0
 ; RV32-NEXT:    csrr a0, vlenb
 ; RV32-NEXT:    slli a0, a0, 4
 ; RV32-NEXT:    sub sp, sp, a0
+; RV32-NEXT:    andi sp, sp, -128
 ; RV32-NEXT:    csrr a0, vlenb
 ; RV32-NEXT:    slli a0, a0, 3
 ; RV32-NEXT:    addi a1, sp, 128
 ; RV32-NEXT:    add a0, a1, a0
 ; RV32-NEXT:    vs8r.v v16, (a0)
 ; RV32-NEXT:    addi a0, sp, 128
 ; RV32-NEXT:    vs8r.v v8, (a0)
 ; RV32-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; RV32-NEXT:    vmv.v.i v8, 0
 ; RV32-NEXT:    addi a0, sp, 128
 ; RV32-NEXT:    vmv.v.i v16, 0
 ; RV32-NEXT:    call callee_scalable_vector_split_indirect@plt
-; RV32-NEXT:    csrr a0, vlenb
-; RV32-NEXT:    slli a0, a0, 4
-; RV32-NEXT:    add sp, sp, a0
+; RV32-NEXT:    addi sp, s0, -144
 ; RV32-NEXT:    lw ra, 140(sp) # 4-byte Folded Reload
 ; RV32-NEXT:    addi sp, sp, 144
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: caller_scalable_vector_split_indirect:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    addi sp, sp, -144
 ; RV64-NEXT:    .cfi_def_cfa_offset 144
 ; RV64-NEXT:    sd ra, 136(sp) # 8-byte Folded Spill
 ; RV64-NEXT:    .cfi_offset ra, -8
+; RV64-NEXT:    addi s0, sp, 144
+; RV64-NEXT:    .cfi_def_cfa s0, 0
 ; RV64-NEXT:    csrr a0, vlenb
 ; RV64-NEXT:    slli a0, a0, 4
 ; RV64-NEXT:    sub sp, sp, a0
+; RV64-NEXT:    andi sp, sp, -128
 ; RV64-NEXT:    csrr a0, vlenb
 ; RV64-NEXT:    slli a0, a0, 3
 ; RV64-NEXT:    addi a1, sp, 128
 ; RV64-NEXT:    add a0, a1, a0
 ; RV64-NEXT:    vs8r.v v16, (a0)
 ; RV64-NEXT:    addi a0, sp, 128
 ; RV64-NEXT:    vs8r.v v8, (a0)
 ; RV64-NEXT:    vsetvli a0, zero, e32, m8, ta, mu
 ; RV64-NEXT:    vmv.v.i v8, 0
 ; RV64-NEXT:    addi a0, sp, 128
 ; RV64-NEXT:    vmv.v.i v16, 0
 ; RV64-NEXT:    call callee_scalable_vector_split_indirect@plt
-; RV64-NEXT:    csrr a0, vlenb
-; RV64-NEXT:    slli a0, a0, 4
-; RV64-NEXT:    add sp, sp, a0
+; RV64-NEXT:    addi sp, s0, -144
 ; RV64-NEXT:    ld ra, 136(sp) # 8-byte Folded Reload
 ; RV64-NEXT:    addi sp, sp, 144
 ; RV64-NEXT:    ret
   %c = alloca i64
   %a = call <vscale x 32 x i32> @callee_scalable_vector_split_indirect(<vscale x 32 x i32> zeroinitializer, <vscale x 32 x i32> %x)
   ret <vscale x 32 x i32> %a
 }

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-emergency-slot.mir

 # NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 # NOTE: Assertions gave been autogenerated by utils/update_llc_test_checks.py
 # RUN: llc -mtriple riscv64 -mattr=+v -target-abi=lp64 -start-before=prologepilog -o - \
 # RUN:     -verify-machineinstrs %s | FileCheck %s
 --- |
   target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
   target triple = "riscv64"
 
   define weak_odr dso_local void @fixedlen_vector_spillslot(i8* %ay) nounwind {
   ; CHECK-LABEL: fixedlen_vector_spillslot:
   ; CHECK:       # %bb.0: # %entry
   ; CHECK-NEXT:    addi sp, sp, -48
   ; CHECK-NEXT:    sd ra, 40(sp) # 8-byte Folded Spill
   ; CHECK-NEXT:    sd a0, 32(sp)
   ; CHECK-NEXT:    sd a0, 16(sp)
   ; CHECK-NEXT:    vsetivli a5, 1, e16, m1, ta, mu
-  ; CHECK-NEXT:    sd a1, 8(sp)
+  ; CHECK-NEXT:    sd a1, 0(sp)
   ; CHECK-NEXT:    addi a1, sp, 24
   ; CHECK-NEXT:    vs1r.v v25, (a1) # Unknown-size Folded Spill
-  ; CHECK-NEXT:    ld a1, 8(sp)
+  ; CHECK-NEXT:    ld a1, 0(sp)
   ; CHECK-NEXT:    call fixedlen_vector_spillslot@plt
   ; CHECK-NEXT:    ld ra, 40(sp) # 8-byte Folded Reload
   ; CHECK-NEXT:    addi sp, sp, 48
   ; CHECK-NEXT:    ret
   entry:
     ret void
   }
 

llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert-subvector.ll

 
 ; Check we don't mistakenly optimize this: we don't know whether this is
 ; inserted into the low or high split vector.
 define void @insert_v2i64_nxv16i64_hi(<2 x i64>* %psv, <vscale x 16 x i64>* %out) {
 ; CHECK-LABEL: insert_v2i64_nxv16i64_hi:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    addi sp, sp, -64
 ; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    addi s0, sp, 64
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
 ; CHECK-NEXT:    csrr a2, vlenb
 ; CHECK-NEXT:    slli a2, a2, 4
 ; CHECK-NEXT:    sub sp, sp, a2
+; CHECK-NEXT:    andi sp, sp, -64
 ; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
 ; CHECK-NEXT:    vle64.v v8, (a0)
 ; CHECK-NEXT:    addi a0, sp, 128
 ; CHECK-NEXT:    vse64.v v8, (a0)
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    addi a2, sp, 64
 ; CHECK-NEXT:    add a2, a2, a0
 ; CHECK-NEXT:    vl8re64.v v8, (a2)
 ; CHECK-NEXT:    addi a2, sp, 64
 ; CHECK-NEXT:    vl8re64.v v16, (a2)
 ; CHECK-NEXT:    add a0, a1, a0
 ; CHECK-NEXT:    vs8r.v v8, (a0)
 ; CHECK-NEXT:    vs8r.v v16, (a1)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, s0, -64
 ; CHECK-NEXT:    addi sp, sp, 64
 ; CHECK-NEXT:    ret
   %sv = load <2 x i64>, <2 x i64>* %psv
   %v = call <vscale x 16 x i64> @llvm.experimental.vector.insert.v2i64.nxv16i64(<vscale x 16 x i64> undef, <2 x i64> %sv, i64 8)
   store <vscale x 16 x i64> %v, <vscale x 16 x i64>* %out
   ret void
 }
 

llvm/test/CodeGen/RISCV/rvv/no-reserved-frame.ll

 ; CHECK-NEXT:    .cfi_offset ra, -8
 ; CHECK-NEXT:    .cfi_offset s0, -16
 ; CHECK-NEXT:    .cfi_offset s1, -24
 ; CHECK-NEXT:    addi s0, sp, 96
 ; CHECK-NEXT:    .cfi_def_cfa s0, 0
 ; CHECK-NEXT:    csrr a1, vlenb
 ; CHECK-NEXT:    slli a1, a1, 1
 ; CHECK-NEXT:    sub sp, sp, a1
-; CHECK-NEXT:    andi sp, sp, -8
+; CHECK-NEXT:    andi sp, sp, -16
 ; CHECK-NEXT:    mv s1, sp
 ; CHECK-NEXT:    lw t0, 44(s1)
 ; CHECK-NEXT:    lw a2, 40(s1)
 ; CHECK-NEXT:    lw a3, 36(s1)
 ; CHECK-NEXT:    lw a4, 32(s1)
 ; CHECK-NEXT:    lw a5, 28(s1)
 ; CHECK-NEXT:    lw a6, 24(s1)
 ; CHECK-NEXT:    lw a7, 20(s1)

llvm/test/CodeGen/RISCV/rvv/rvv-args-by-mem.ll

 
 define <vscale x 16 x i32> @foo(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i32 %6, i32 %7, <vscale x 16 x i32> %x) {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    addi sp, sp, -80
 ; CHECK-NEXT:    .cfi_def_cfa_offset 80
 ; CHECK-NEXT:    sd ra, 72(sp) # 8-byte Folded Spill
 ; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    addi s0, sp, 80
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
 ; CHECK-NEXT:    csrr t0, vlenb
 ; CHECK-NEXT:    slli t0, t0, 4
 ; CHECK-NEXT:    sub sp, sp, t0
-; CHECK-NEXT:    addi t0, sp, 64
+; CHECK-NEXT:    andi sp, sp, -64
+; CHECK-NEXT:    mv s1, sp
+; CHECK-NEXT:    addi t0, s1, 64
 ; CHECK-NEXT:    sd t0, 8(sp)
 ; CHECK-NEXT:    csrr t0, vlenb
 ; CHECK-NEXT:    slli t0, t0, 3
-; CHECK-NEXT:    add t0, sp, t0
+; CHECK-NEXT:    add t0, s1, t0
 ; CHECK-NEXT:    addi t0, t0, 64
 ; CHECK-NEXT:    sd t0, 0(sp)
-; CHECK-NEXT:    addi t0, sp, 64
+; CHECK-NEXT:    addi t0, s1, 64
 ; CHECK-NEXT:    vs8r.v v8, (t0)
 ; CHECK-NEXT:    csrr t0, vlenb
 ; CHECK-NEXT:    slli t0, t0, 3
-; CHECK-NEXT:    add t0, sp, t0
+; CHECK-NEXT:    add t0, s1, t0
 ; CHECK-NEXT:    addi t0, t0, 64
 ; CHECK-NEXT:    vs8r.v v8, (t0)
 ; CHECK-NEXT:    vmv8r.v v16, v8
 ; CHECK-NEXT:    call bar@plt
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 4
-; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, s0, -80
 ; CHECK-NEXT:    ld ra, 72(sp) # 8-byte Folded Reload
 ; CHECK-NEXT:    addi sp, sp, 80
 ; CHECK-NEXT:    ret
   %ret = call <vscale x 16 x i32> @bar(i32 %0, i32 %1, i32 %2, i32 %3, i32 %4, i32 %5, i32 %6, i32 %7, <vscale x 16 x i32> %x, <vscale x 16 x i32> %x, <vscale x 16 x i32> %x, <vscale x 16 x i32> %x)
   ret <vscale x 16 x i32> %ret
 }