mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
103277308c
Summary:
When lowering global address, lower the base as a TargetGlobal first then
create an SDNode for the offset separately and chain it to the address calculation
This optimization will create a DAG where the base address of a global access will
be reused between different access. The offset can later be folded into the immediate
part of the memory access instruction.
With this optimization we generate:
lui a0, %hi(s)
addi a0, a0, %lo(s) ; shared base address.
addi a1, zero, 20 ; 2 instructions per access.
sw a1, 44(a0)
addi a1, zero, 10
sw a1, 8(a0)
addi a1, zero, 30
sw a1, 80(a0)
Instead of:
lui a0, %hi(s+44) ; 3 instructions per access.
addi a1, zero, 20
sw a1, %lo(s+44)(a0)
lui a0, %hi(s+8)
addi a1, zero, 10
sw a1, %lo(s+8)(a0)
lui a0, %hi(s+80)
addi a1, zero, 30
sw a1, %lo(s+80)(a0)
Which will save one instruction per access.
Reviewers: asb, apazos
Reviewed By: asb
Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang, apazos, asb, llvm-commits
Differential Revision: https://reviews.llvm.org/D46989
llvm-svn: 332641
44 lines
1.3 KiB
LLVM
44 lines
1.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
|
|
; RUN: | FileCheck -check-prefix=RV32I %s
|
|
|
|
%struct.Foo = type { i32, i32, i32, i16, i8 }
|
|
@foo = global %struct.Foo { i32 1, i32 2, i32 3, i16 4, i8 5 }, align 4
|
|
|
|
define i32 @callee(%struct.Foo* byval %f) nounwind {
|
|
; RV32I-LABEL: callee:
|
|
; RV32I: # %bb.0: # %entry
|
|
; RV32I-NEXT: lw a0, 0(a0)
|
|
; RV32I-NEXT: ret
|
|
entry:
|
|
%0 = getelementptr inbounds %struct.Foo, %struct.Foo* %f, i32 0, i32 0
|
|
%1 = load i32, i32* %0, align 4
|
|
ret i32 %1
|
|
}
|
|
|
|
|
|
define void @caller() nounwind {
|
|
; RV32I-LABEL: caller:
|
|
; RV32I: # %bb.0: # %entry
|
|
; RV32I-NEXT: addi sp, sp, -32
|
|
; RV32I-NEXT: sw ra, 28(sp)
|
|
; RV32I-NEXT: lui a0, %hi(foo)
|
|
; RV32I-NEXT: lw a1, %lo(foo)(a0)
|
|
; RV32I-NEXT: sw a1, 12(sp)
|
|
; RV32I-NEXT: addi a0, a0, %lo(foo)
|
|
; RV32I-NEXT: lw a1, 12(a0)
|
|
; RV32I-NEXT: sw a1, 24(sp)
|
|
; RV32I-NEXT: lw a1, 8(a0)
|
|
; RV32I-NEXT: sw a1, 20(sp)
|
|
; RV32I-NEXT: lw a0, 4(a0)
|
|
; RV32I-NEXT: sw a0, 16(sp)
|
|
; RV32I-NEXT: addi a0, sp, 12
|
|
; RV32I-NEXT: call callee
|
|
; RV32I-NEXT: lw ra, 28(sp)
|
|
; RV32I-NEXT: addi sp, sp, 32
|
|
; RV32I-NEXT: ret
|
|
entry:
|
|
%call = call i32 @callee(%struct.Foo* byval @foo)
|
|
ret void
|
|
}
|