llvm-project/llvm/test/CodeGen/RISCV/stack-realignment-with-variable-sized-objects.ll
Wang Pengcheng 3ac9fe69f7
[RISCV] CodeGen of RVE and ilp32e/lp64e ABIs (#76777)
This commit includes the necessary changes to clang and LLVM to support
codegen of `RVE` and the `ilp32e`/`lp64e` ABIs.

The differences between `RVE` and `RVI` are:
* `RVE` reduces the integer register count to 16(x0-x16).
* The ABI should be `ilp32e` for 32 bits and `lp64e` for 64 bits.

`RVE` can be combined with all current standard extensions.

The central changes in ilp32e/lp64e ABI, compared to ilp32/lp64 are:
* Only 6 integer argument registers (rather than 8).
* Only 2 callee-saved registers (rather than 12).
* A Stack Alignment of 32bits (rather than 128bits).
* ilp32e isn't compatible with D ISA extension.

If `ilp32e` or `lp64` is used with an ISA that has any of the registers
x16-x31 and f0-f31, then these registers are considered temporaries.

To be compatible with the implementation of ilp32e in GCC, we don't use
aligned registers to pass variadic arguments and set stack alignment\
to 4-bytes for types with length of 2*XLEN.

FastCC is also supported on RVE, while GHC isn't since there is only one
avaiable register.

Differential Revision: https://reviews.llvm.org/D70401
2024-01-16 20:44:30 +08:00

130 lines
4.9 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV32I
; RUN: llc -mtriple=riscv32 -target-abi ilp32e -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV32I-ILP32E
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV64I
; RUN: llc -mtriple=riscv64 -target-abi lp64e -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV64I-LP64E
declare void @callee(ptr, ptr)
define void @caller(i32 %n) {
; RV32I-LABEL: caller:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -64
; RV32I-NEXT: .cfi_def_cfa_offset 64
; RV32I-NEXT: sw ra, 60(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 56(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 52(sp) # 4-byte Folded Spill
; RV32I-NEXT: .cfi_offset ra, -4
; RV32I-NEXT: .cfi_offset s0, -8
; RV32I-NEXT: .cfi_offset s1, -12
; RV32I-NEXT: addi s0, sp, 64
; RV32I-NEXT: .cfi_def_cfa s0, 0
; RV32I-NEXT: andi sp, sp, -64
; RV32I-NEXT: mv s1, sp
; RV32I-NEXT: addi a0, a0, 15
; RV32I-NEXT: andi a0, a0, -16
; RV32I-NEXT: sub a0, sp, a0
; RV32I-NEXT: mv sp, a0
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: call callee
; RV32I-NEXT: addi sp, s0, -64
; RV32I-NEXT: lw ra, 60(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 56(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 52(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 64
; RV32I-NEXT: ret
;
; RV32I-ILP32E-LABEL: caller:
; RV32I-ILP32E: # %bb.0:
; RV32I-ILP32E-NEXT: addi sp, sp, -64
; RV32I-ILP32E-NEXT: .cfi_def_cfa_offset 64
; RV32I-ILP32E-NEXT: sw ra, 60(sp) # 4-byte Folded Spill
; RV32I-ILP32E-NEXT: sw s0, 56(sp) # 4-byte Folded Spill
; RV32I-ILP32E-NEXT: sw s1, 52(sp) # 4-byte Folded Spill
; RV32I-ILP32E-NEXT: .cfi_offset ra, -4
; RV32I-ILP32E-NEXT: .cfi_offset s0, -8
; RV32I-ILP32E-NEXT: .cfi_offset s1, -12
; RV32I-ILP32E-NEXT: addi s0, sp, 64
; RV32I-ILP32E-NEXT: .cfi_def_cfa s0, 0
; RV32I-ILP32E-NEXT: andi sp, sp, -64
; RV32I-ILP32E-NEXT: mv s1, sp
; RV32I-ILP32E-NEXT: addi a0, a0, 3
; RV32I-ILP32E-NEXT: andi a0, a0, -4
; RV32I-ILP32E-NEXT: sub a0, sp, a0
; RV32I-ILP32E-NEXT: mv sp, a0
; RV32I-ILP32E-NEXT: mv a1, s1
; RV32I-ILP32E-NEXT: call callee
; RV32I-ILP32E-NEXT: addi sp, s0, -64
; RV32I-ILP32E-NEXT: lw ra, 60(sp) # 4-byte Folded Reload
; RV32I-ILP32E-NEXT: lw s0, 56(sp) # 4-byte Folded Reload
; RV32I-ILP32E-NEXT: lw s1, 52(sp) # 4-byte Folded Reload
; RV32I-ILP32E-NEXT: addi sp, sp, 64
; RV32I-ILP32E-NEXT: ret
;
; RV64I-LABEL: caller:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -64
; RV64I-NEXT: .cfi_def_cfa_offset 64
; RV64I-NEXT: sd ra, 56(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 48(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: .cfi_offset ra, -8
; RV64I-NEXT: .cfi_offset s0, -16
; RV64I-NEXT: .cfi_offset s1, -24
; RV64I-NEXT: addi s0, sp, 64
; RV64I-NEXT: .cfi_def_cfa s0, 0
; RV64I-NEXT: andi sp, sp, -64
; RV64I-NEXT: mv s1, sp
; RV64I-NEXT: slli a0, a0, 32
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: addi a0, a0, 15
; RV64I-NEXT: andi a0, a0, -16
; RV64I-NEXT: sub a0, sp, a0
; RV64I-NEXT: mv sp, a0
; RV64I-NEXT: mv a1, s1
; RV64I-NEXT: call callee
; RV64I-NEXT: addi sp, s0, -64
; RV64I-NEXT: ld ra, 56(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 48(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 64
; RV64I-NEXT: ret
;
; RV64I-LP64E-LABEL: caller:
; RV64I-LP64E: # %bb.0:
; RV64I-LP64E-NEXT: addi sp, sp, -64
; RV64I-LP64E-NEXT: .cfi_def_cfa_offset 64
; RV64I-LP64E-NEXT: sd ra, 56(sp) # 8-byte Folded Spill
; RV64I-LP64E-NEXT: sd s0, 48(sp) # 8-byte Folded Spill
; RV64I-LP64E-NEXT: sd s1, 40(sp) # 8-byte Folded Spill
; RV64I-LP64E-NEXT: .cfi_offset ra, -8
; RV64I-LP64E-NEXT: .cfi_offset s0, -16
; RV64I-LP64E-NEXT: .cfi_offset s1, -24
; RV64I-LP64E-NEXT: addi s0, sp, 64
; RV64I-LP64E-NEXT: .cfi_def_cfa s0, 0
; RV64I-LP64E-NEXT: andi sp, sp, -64
; RV64I-LP64E-NEXT: mv s1, sp
; RV64I-LP64E-NEXT: slli a0, a0, 32
; RV64I-LP64E-NEXT: srli a0, a0, 32
; RV64I-LP64E-NEXT: addi a0, a0, 7
; RV64I-LP64E-NEXT: andi a0, a0, -8
; RV64I-LP64E-NEXT: sub a0, sp, a0
; RV64I-LP64E-NEXT: mv sp, a0
; RV64I-LP64E-NEXT: mv a1, s1
; RV64I-LP64E-NEXT: call callee
; RV64I-LP64E-NEXT: addi sp, s0, -64
; RV64I-LP64E-NEXT: ld ra, 56(sp) # 8-byte Folded Reload
; RV64I-LP64E-NEXT: ld s0, 48(sp) # 8-byte Folded Reload
; RV64I-LP64E-NEXT: ld s1, 40(sp) # 8-byte Folded Reload
; RV64I-LP64E-NEXT: addi sp, sp, 64
; RV64I-LP64E-NEXT: ret
%1 = alloca i8, i32 %n
%2 = alloca i32, align 64
call void @callee(ptr %1, ptr %2)
ret void
}