maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/RISCV/hoist-global-addr-base.ll

169 lines
5.7 KiB
LLVM
Raw Normal View History

[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 < %s | FileCheck %s
%struct.S = type { [40 x i32], i32, i32, i32, [4100 x i32], i32, i32, i32 }
@s = common dso_local global %struct.S zeroinitializer, align 4
@foo = global [6 x i16] [i16 1, i16 2, i16 3, i16 4, i16 5, i16 0], align 2
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
@g = global [1048576 x i8] zeroinitializer, align 1
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
define dso_local void @multiple_stores() local_unnamed_addr {
; CHECK-LABEL: multiple_stores:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lui a0, %hi(s)
; CHECK-NEXT: addi a0, a0, %lo(s)
; CHECK-NEXT: addi a1, zero, 20
; CHECK-NEXT: sw a1, 164(a0)
; CHECK-NEXT: addi a1, zero, 10
; CHECK-NEXT: sw a1, 160(a0)
; CHECK-NEXT: ret
entry:
store i32 10, i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 1), align 4
store i32 20, i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 2), align 4
ret void
}
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
define dso_local void @control_flow_with_mem_access() local_unnamed_addr #0 {
; CHECK-LABEL: control_flow_with_mem_access:
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lui a0, %hi(s)
; CHECK-NEXT: addi a0, a0, %lo(s)
; CHECK-NEXT: lw a1, 164(a0)
; CHECK-NEXT: addi a2, zero, 1
; CHECK-NEXT: blt a1, a2, .LBB1_2
; CHECK-NEXT: # %bb.1: # %if.then
; CHECK-NEXT: addi a1, zero, 10
; CHECK-NEXT: sw a1, 160(a0)
; CHECK-NEXT: .LBB1_2: # %if.end
; CHECK-NEXT: ret
entry:
%0 = load i32, i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 2), align 4
%cmp = icmp sgt i32 %0, 0
br i1 %cmp, label %if.then, label %if.end
if.then: ; preds = %entry
store i32 10, i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 1), align 4
br label %if.end
if.end: ; preds = %if.then, %entry
ret void
}
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; This test checks for the case where the offset is only an LUI.
; without peephole this generates:
; lui a0, %hi(g)
; addi a0, a0, %lo(g)
; lui a1, 128 ---> offset
; add a0, a0, a1 ---> base + offset.
define i8* @big_offset_lui_tail() {
; CHECK-LABEL: big_offset_lui_tail:
; CHECK: # %bb.0:
; CHECK-NEXT: lui a0, %hi(g+524288)
; CHECK-NEXT: addi a0, a0, %lo(g+524288)
; CHECK-NEXT: ret
ret i8* getelementptr inbounds ([1048576 x i8], [1048576 x i8]* @g, i32 0, i32 524288)
}
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
define dso_local i32* @big_offset_one_use() local_unnamed_addr {
; CHECK-LABEL: big_offset_one_use:
; CHECK: # %bb.0: # %entry
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; CHECK-NEXT: lui a0, %hi(s+16572)
; CHECK-NEXT: addi a0, a0, %lo(s+16572)
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK-NEXT: ret
entry:
ret i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 5)
}
define dso_local i32* @small_offset_one_use() local_unnamed_addr {
; CHECK-LABEL: small_offset_one_use:
; CHECK: # %bb.0: # %entry
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; CHECK-NEXT: lui a0, %hi(s+160)
; CHECK-NEXT: addi a0, a0, %lo(s+160)
; CHECK-NEXT: ret
entry:
ret i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 1)
}
; TODO: In this case we get a better sequence if the offset didn't get didn't
; get merged back in %if.end and %if.then. The current peephole is not able to
; detect the shared global address node across blocks.
; Without the peephole we can generate:
;# %bb.0: # %entry
; lui a0, %hi(s)
; addi a0, a0, %lo(s)
; lw a1, 164(a0)
; beqz a1, .LBB0_2
;# %bb.1: # %if.end
; addi a0, a0, 168
; ret
;.LBB0_2: # %if.then
; addi a0, a0, 160
; ret
; Function Attrs: norecurse nounwind optsize readonly
define dso_local i32* @control_flow_no_mem(i32 %n) local_unnamed_addr #1 {
; CHECK-LABEL: control_flow_no_mem:
; CHECK: # %bb.0: # %entry
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK-NEXT: lui a0, %hi(s)
; CHECK-NEXT: addi a0, a0, %lo(s)
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; CHECK-NEXT: lw a0, 164(a0)
; CHECK-NEXT: beqz a0, .LBB5_2
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: lui a0, %hi(s+168)
; CHECK-NEXT: addi a0, a0, %lo(s+168)
; CHECK-NEXT: ret
; CHECK-NEXT: .LBB5_2: # %if.then
; CHECK-NEXT: lui a0, %hi(s+160)
; CHECK-NEXT: addi a0, a0, %lo(s+160)
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK-NEXT: ret
entry:
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
%0 = load i32, i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 2), align 4
%cmp = icmp eq i32 %0, 0
br i1 %cmp, label %if.then, label %if.end
if.then: ; preds = %entry
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
ret i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 1)
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
if.end: ; preds = %if.then, %entry
ret i32* getelementptr inbounds (%struct.S, %struct.S* @s, i32 0, i32 3)
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
}
;TODO: Offset shouln't be separated in this case. We get shorter sequence if it
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; is merged in the LUI %hi and the ADDI %lo, the "ADDI" could be folded in the
; immediate part of "lhu" genertating the sequence:
; lui a0, %hi(foo +8)
; lhu a0, %lo(foo+8)(a0)
; instead of:
; lui a0, %hi(foo)
; addi a0, a0, %lo(foo)
; lhu a0, 8(a0)
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
define dso_local i32 @load_half() nounwind {
; CHECK-LABEL: load_half:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sw ra, 12(sp)
; CHECK-NEXT: lui a0, %hi(foo)
; CHECK-NEXT: addi a0, a0, %lo(foo)
; CHECK-NEXT: lhu a0, 8(a0)
; CHECK-NEXT: addi a1, zero, 140
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; CHECK-NEXT: bne a0, a1, .LBB6_2
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK-NEXT: # %bb.1: # %if.end
; CHECK-NEXT: mv a0, zero
; CHECK-NEXT: lw ra, 12(sp)
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
[RISCV] Add peepholes for Global Address lowering patterns Summary: Base and offset are always separated when a GlobalAddress node is lowered (rL332641) as an optimization to reduce instruction count. However, this optimization is not profitable if the Global Address ends up being used in only instruction. This patch adds peephole optimizations that merge an offset of an address calculation into the LUI %%hi and ADD %lo of the lowering sequence. The peephole handles three patterns: 1) ADDI (ADDI (LUI %hi(global)) %lo(global)), offset ---> ADDI (LUI %hi(global + offset)) %lo(global + offset). This generates: lui a0, hi (global + offset) add a0, a0, lo (global + offset) Instead of lui a0, hi (global) addi a0, hi (global) addi a0, offset This pattern is for cases when the offset is small enough to fit in the immediate filed of ADDI (less than 12 bits). 2) ADD ((ADDI (LUI %hi(global)) %lo(global)), (LUI hi_offset)) ---> offset = hi_offset << 12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a0, hi(global + offset) addi a0, lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offset) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI but the lower 12 bits are all zeros. 3) ADD ((ADDI (LUI %hi(global)) %lo(global)), (ADDI lo_offset, (LUI hi_offset))) ---> offset = global + offhi20<<12 + offlo12 ADDI (LUI %hi(global + offset)) %lo(global + offset) Which generates the ASM: lui a1, %hi(global + offset) addi a1, %lo(global + offset) Instead of: lui a0, hi(global) addi a0, lo(global) lui a1, (offhi20) addi a1, (offlo12) add a0, a0, a1 This pattern is for cases when the offset doesn't fit in an immediate field of ADDI and both the lower 1 bits and high 20 bits are non zero. Reviewers: asb Reviewed By: asb Subscribers: rbar, johnrusso, simoncook, jordy.potman.lists, apazos, niosHD, kito-cheng, shiva0217, zzheng, edward-jones, mgrang llvm-svn: 333455
2018-05-30 03:34:54 +08:00
; CHECK-NEXT: .LBB6_2: # %if.then
[RISCV] Separate base from offset in lowerGlobalAddress 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
2018-05-18 02:14:53 +08:00
; CHECK-NEXT: call abort
entry:
%0 = load i16, i16* getelementptr inbounds ([6 x i16], [6 x i16]* @foo, i32 0, i32 4), align 2
%cmp = icmp eq i16 %0, 140
br i1 %cmp, label %if.end, label %if.then
if.then:
tail call void @abort()
unreachable
if.end:
ret i32 0
}
declare void @abort()