4554663bc0
This includes a fix for the tramp3d failure from the llvm-testsuite that caused the last revert. Hopefully the others failures were the same issue. Original commit message: For RISC-V, load/store(exclude vector load/store) instructions only has a 12 bit immediate operand. If the offset is out-of-range, it must make use of a temp register to make up this offset. If between these offsets, they have a small(IsInt<12>) relative offset, LocalStackSlotAllocation pass can find a value as frame base register's value, and replace the origin offset with this register's value plus the relative offset. Co-authored-by: luxufan <luxufan@iscas.ac.cn> Co-authored-by: Craig Topper <craig.topper@sifive.com> Differential Revision: https://reviews.llvm.org/D98101
95 lines
3.1 KiB
LLVM
95 lines
3.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s | FileCheck %s --check-prefix=RV32I
|
|
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s | FileCheck %s --check-prefix=RV64I
|
|
|
|
; This test case test the LocalStackSlotAllocation pass that use a base register
|
|
; for the frame index that its offset is out-of-range (for RISC-V. the immediate
|
|
; is 12 bits for the load store instruction (excludes vector load / store))
|
|
define void @use_frame_base_reg() {
|
|
; RV32I-LABEL: use_frame_base_reg:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: lui a0, 24
|
|
; RV32I-NEXT: addi a0, a0, 1712
|
|
; RV32I-NEXT: sub sp, sp, a0
|
|
; RV32I-NEXT: .cfi_def_cfa_offset 100016
|
|
; RV32I-NEXT: lui a0, 24
|
|
; RV32I-NEXT: addi a0, a0, 1704
|
|
; RV32I-NEXT: add a0, sp, a0
|
|
; RV32I-NEXT: lb a1, 4(a0)
|
|
; RV32I-NEXT: lb a0, 0(a0)
|
|
; RV32I-NEXT: lui a0, 24
|
|
; RV32I-NEXT: addi a0, a0, 1712
|
|
; RV32I-NEXT: add sp, sp, a0
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV64I-LABEL: use_frame_base_reg:
|
|
; RV64I: # %bb.0:
|
|
; RV64I-NEXT: lui a0, 24
|
|
; RV64I-NEXT: addiw a0, a0, 1712
|
|
; RV64I-NEXT: sub sp, sp, a0
|
|
; RV64I-NEXT: .cfi_def_cfa_offset 100016
|
|
; RV64I-NEXT: lui a0, 24
|
|
; RV64I-NEXT: addiw a0, a0, 1704
|
|
; RV64I-NEXT: add a0, sp, a0
|
|
; RV64I-NEXT: lb a1, 4(a0)
|
|
; RV64I-NEXT: lb a0, 0(a0)
|
|
; RV64I-NEXT: lui a0, 24
|
|
; RV64I-NEXT: addiw a0, a0, 1712
|
|
; RV64I-NEXT: add sp, sp, a0
|
|
; RV64I-NEXT: ret
|
|
|
|
%va = alloca i8, align 4
|
|
%va1 = alloca i8, align 4
|
|
%large = alloca [ 100000 x i8 ]
|
|
%argp.cur = load volatile i8, ptr %va, align 4
|
|
%argp.next = load volatile i8, ptr %va1, align 4
|
|
ret void
|
|
}
|
|
|
|
; Test containing a load with its own local offset. Make sure isFrameOffsetLegal
|
|
; considers it and does not create a virtual base register.
|
|
define void @load_with_offset() {
|
|
; RV32I-LABEL: load_with_offset:
|
|
; RV32I: # %bb.0:
|
|
; RV32I-NEXT: lui a0, 25
|
|
; RV32I-NEXT: addi a0, a0, -1792
|
|
; RV32I-NEXT: sub sp, sp, a0
|
|
; RV32I-NEXT: .cfi_def_cfa_offset 100608
|
|
; RV32I-NEXT: lui a0, 25
|
|
; RV32I-NEXT: add a0, sp, a0
|
|
; RV32I-NEXT: lb a0, -292(a0)
|
|
; RV32I-NEXT: lui a0, 24
|
|
; RV32I-NEXT: add a0, sp, a0
|
|
; RV32I-NEXT: lb a0, 1704(a0)
|
|
; RV32I-NEXT: lui a0, 25
|
|
; RV32I-NEXT: addi a0, a0, -1792
|
|
; RV32I-NEXT: add sp, sp, a0
|
|
; RV32I-NEXT: ret
|
|
;
|
|
; RV64I-LABEL: load_with_offset:
|
|
; RV64I: # %bb.0:
|
|
; RV64I-NEXT: lui a0, 25
|
|
; RV64I-NEXT: addiw a0, a0, -1792
|
|
; RV64I-NEXT: sub sp, sp, a0
|
|
; RV64I-NEXT: .cfi_def_cfa_offset 100608
|
|
; RV64I-NEXT: lui a0, 25
|
|
; RV64I-NEXT: add a0, sp, a0
|
|
; RV64I-NEXT: lb a0, -292(a0)
|
|
; RV64I-NEXT: lui a0, 24
|
|
; RV64I-NEXT: add a0, sp, a0
|
|
; RV64I-NEXT: lb a0, 1704(a0)
|
|
; RV64I-NEXT: lui a0, 25
|
|
; RV64I-NEXT: addiw a0, a0, -1792
|
|
; RV64I-NEXT: add sp, sp, a0
|
|
; RV64I-NEXT: ret
|
|
|
|
%va = alloca [100 x i8], align 4
|
|
%va1 = alloca [500 x i8], align 4
|
|
%large = alloca [100000 x i8]
|
|
%va_gep = getelementptr [100 x i8], ptr %va, i64 16
|
|
%va1_gep = getelementptr [100 x i8], ptr %va1, i64 0
|
|
%load = load volatile i8, ptr %va_gep, align 4
|
|
%load1 = load volatile i8, ptr %va1_gep, align 4
|
|
ret void
|
|
}
|