[AMDGPU][GlobalISel] Handle G_PTR_ADD when looking for constant offset

Look throught G_PTRTOINT and G_PTR_ADD nodes when looking for constant
offset for buffer stores. This also helps with merging of these instructions
later on.

Differential Revision: https://reviews.llvm.org/D95242
This commit is contained in:
Mirko Brkusanin 2021-01-28 11:08:11 +01:00
parent 54e570d94a
commit 4b422708ba
3 changed files with 95 additions and 1 deletions

View File

@ -41,6 +41,20 @@ AMDGPU::getBaseWithConstantOffset(MachineRegisterInfo &MRI, Register Reg) {
return std::make_pair(Def->getOperand(1).getReg(), Offset);
}
// Handle G_PTRTOINT (G_PTR_ADD base, const) case
if (Def->getOpcode() == TargetOpcode::G_PTRTOINT) {
MachineInstr *Base;
if (mi_match(Def->getOperand(1).getReg(), MRI,
m_GPtrAdd(m_MInstr(Base), m_ICst(Offset)))) {
// If Base was int converted to pointer, simply return int and offset.
if (Base->getOpcode() == TargetOpcode::G_INTTOPTR)
return std::make_pair(Base->getOperand(1).getReg(), Offset);
// Register returned here will be of pointer type.
return std::make_pair(Base->getOperand(0).getReg(), Offset);
}
}
return std::make_pair(Reg, 0);
}

View File

@ -3518,12 +3518,17 @@ AMDGPULegalizerInfo::splitBufferOffsets(MachineIRBuilder &B,
Register BaseReg;
unsigned TotalConstOffset;
const LLT S32 = LLT::scalar(32);
MachineRegisterInfo &MRI = *B.getMRI();
std::tie(BaseReg, TotalConstOffset) =
AMDGPU::getBaseWithConstantOffset(*B.getMRI(), OrigOffset);
AMDGPU::getBaseWithConstantOffset(MRI, OrigOffset);
unsigned ImmOffset = TotalConstOffset;
// If BaseReg is a pointer, convert it to int.
if (MRI.getType(BaseReg).isPointer())
BaseReg = B.buildPtrToInt(MRI.getType(OrigOffset), BaseReg).getReg(0);
// If the immediate value is too big for the immoffset field, put the value
// and -4096 into the immoffset field so that the value that is copied/added
// for the voffset field is a multiple of 4096, and it stands more chance

View File

@ -0,0 +1,75 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -march=amdgcn -verify-machineinstrs -o - %s | FileCheck %s
define amdgpu_cs void @test1(i32 %arg1, <4 x i32> inreg %arg2, i32, i32 addrspace(6)* inreg %arg3) {
; CHECK-LABEL: test1:
; CHECK: ; %bb.0: ; %.entry
; CHECK-NEXT: v_and_b32_e32 v3, 0x3ffffffc, v0
; CHECK-NEXT: v_mov_b32_e32 v0, 11
; CHECK-NEXT: v_mov_b32_e32 v1, 22
; CHECK-NEXT: v_mov_b32_e32 v2, 33
; CHECK-NEXT: v_lshlrev_b32_e32 v3, 2, v3
; CHECK-NEXT: v_add_i32_e32 v4, vcc, s4, v3
; CHECK-NEXT: v_mov_b32_e32 v3, 44
; CHECK-NEXT: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 offen
; CHECK-NEXT: s_endpgm
.entry:
%bs1 = and i32 %arg1, 1073741820
%ep1 = getelementptr i32, i32 addrspace(6)* %arg3, i32 %bs1
%ad1 = ptrtoint i32 addrspace(6)* %ep1 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 11, <4 x i32> %arg2, i32 %ad1, i32 0, i32 0)
%bs2 = or i32 %bs1, 1
%ep2 = getelementptr i32, i32 addrspace(6)* %arg3, i32 %bs2
%ad2 = ptrtoint i32 addrspace(6)* %ep2 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 22, <4 x i32> %arg2, i32 %ad2, i32 0, i32 0)
%bs3 = or i32 %bs1, 2
%ep3 = getelementptr i32, i32 addrspace(6)* %arg3, i32 %bs3
%ad3 = ptrtoint i32 addrspace(6)* %ep3 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 33, <4 x i32> %arg2, i32 %ad3, i32 0, i32 0)
%bs4 = or i32 %bs1, 3
%ep4 = getelementptr i32, i32 addrspace(6)* %arg3, i32 %bs4
%ad4 = ptrtoint i32 addrspace(6)* %ep4 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 44, <4 x i32> %arg2, i32 %ad4, i32 0, i32 0)
ret void
}
define amdgpu_cs void @test2(i32 %arg1, <4 x i32> inreg %arg2) {
; CHECK-LABEL: test2:
; CHECK: ; %bb.0: ; %.entry
; CHECK-NEXT: v_and_b32_e32 v3, 0x3ffffffc, v0
; CHECK-NEXT: v_mov_b32_e32 v0, 11
; CHECK-NEXT: v_mov_b32_e32 v1, 22
; CHECK-NEXT: v_mov_b32_e32 v2, 33
; CHECK-NEXT: v_lshlrev_b32_e32 v4, 2, v3
; CHECK-NEXT: v_mov_b32_e32 v3, 44
; CHECK-NEXT: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 offen
; CHECK-NEXT: s_endpgm
.entry:
%bs1 = and i32 %arg1, 1073741820
%ep1 = getelementptr <{ [64 x i32] }>, <{ [64 x i32] }> addrspace(6)* null, i32 0, i32 0, i32 %bs1
%ad1 = ptrtoint i32 addrspace(6)* %ep1 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 11, <4 x i32> %arg2, i32 %ad1, i32 0, i32 0)
%bs2 = or i32 %bs1, 1
%ep2 = getelementptr <{ [64 x i32] }>, <{ [64 x i32] }> addrspace(6)* null, i32 0, i32 0, i32 %bs2
%ad2 = ptrtoint i32 addrspace(6)* %ep2 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 22, <4 x i32> %arg2, i32 %ad2, i32 0, i32 0)
%bs3 = or i32 %bs1, 2
%ep3 = getelementptr <{ [64 x i32] }>, <{ [64 x i32] }> addrspace(6)* null, i32 0, i32 0, i32 %bs3
%ad3 = ptrtoint i32 addrspace(6)* %ep3 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 33, <4 x i32> %arg2, i32 %ad3, i32 0, i32 0)
%bs4 = or i32 %bs1, 3
%ep4 = getelementptr <{ [64 x i32] }>, <{ [64 x i32] }> addrspace(6)* null, i32 0, i32 0, i32 %bs4
%ad4 = ptrtoint i32 addrspace(6)* %ep4 to i32
call void @llvm.amdgcn.raw.buffer.store.i32(i32 44, <4 x i32> %arg2, i32 %ad4, i32 0, i32 0)
ret void
}
declare void @llvm.amdgcn.raw.buffer.store.i32(i32, <4 x i32>, i32, i32, i32 immarg)