bc78c09952
Introduces a string attribute, amdgpu-requires-module-lds, to allow eliding the module.lds block from kernels. Will allocate the block as before if the attribute is missing or has its default value of true. Patch uses the new attribute to detect the simplest possible instance of this, where a kernel makes no calls and thus cannot call any functions that use LDS. Tests updated to match, coverage was already good. Interesting cases is in lower-module-lds-offsets where annotating the kernel allows the backend to pick a different (in this case better) variable ordering than previously. A later patch will avoid moving kernel variables into module.lds when the kernel can have this attribute, allowing optimal ordering and locally unused variable elimination. Reviewed By: arsenm Differential Revision: https://reviews.llvm.org/D122091
53 lines
2.9 KiB
LLVM
53 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s | FileCheck -check-prefix=OPT %s
|
|
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck -check-prefix=OPT %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Check that module LDS is allocated at address 0 and kernel starts its
|
|
; allocation past module LDS when a call is present.
|
|
|
|
@lds.size.1.align.1 = internal unnamed_addr addrspace(3) global [1 x i8] undef, align 1
|
|
@lds.size.16.align.16 = internal unnamed_addr addrspace(3) global [16 x i8] undef, align 16
|
|
|
|
; GCN-LABEL: {{^}}k0:
|
|
; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0
|
|
; GCN-DAG: v_mov_b32_e32 [[ONE:v[0-9]+]], 1
|
|
; GCN: ds_write_b8 [[NULL]], [[ONE]]
|
|
; GCN: v_mov_b32_e32 [[TWO:v[0-9]+]], 2
|
|
; GCN: ds_write_b8 [[NULL]], [[TWO]] offset:16
|
|
define amdgpu_kernel void @k0() {
|
|
; OPT-LABEL: @k0(
|
|
; OPT-NEXT: call void @llvm.donothing() [ "ExplicitUse"([[LLVM_AMDGCN_MODULE_LDS_T:%.*]] addrspace(3)* @llvm.amdgcn.module.lds) ]
|
|
; OPT-NEXT: [[LDS_SIZE_1_ALIGN_1_BC:%.*]] = bitcast [1 x i8] addrspace(3)* getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], [[LLVM_AMDGCN_MODULE_LDS_T]] addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0) to i8 addrspace(3)*
|
|
; OPT-NEXT: store i8 1, i8 addrspace(3)* [[LDS_SIZE_1_ALIGN_1_BC]], align 1
|
|
; OPT-NEXT: [[LDS_SIZE_16_ALIGN_16_BC:%.*]] = bitcast [16 x i8] addrspace(3)* getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_K0_LDS_T:%.*]], [[LLVM_AMDGCN_KERNEL_K0_LDS_T]] addrspace(3)* @llvm.amdgcn.kernel.k0.lds, i32 0, i32 0) to i8 addrspace(3)*
|
|
; OPT-NEXT: store i8 2, i8 addrspace(3)* [[LDS_SIZE_16_ALIGN_16_BC]], align 16
|
|
; OPT-NEXT: call void @f0()
|
|
; OPT-NEXT: ret void
|
|
;
|
|
%lds.size.1.align.1.bc = bitcast [1 x i8] addrspace(3)* @lds.size.1.align.1 to i8 addrspace(3)*
|
|
store i8 1, i8 addrspace(3)* %lds.size.1.align.1.bc, align 1
|
|
%lds.size.16.align.16.bc = bitcast [16 x i8] addrspace(3)* @lds.size.16.align.16 to i8 addrspace(3)*
|
|
store i8 2, i8 addrspace(3)* %lds.size.16.align.16.bc, align 16
|
|
call void @f0()
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}f0:
|
|
; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0
|
|
; GCN-DAG: v_mov_b32_e32 [[TREE:v[0-9]+]], 3
|
|
; GCN: ds_write_b8 [[NULL]], [[TREE]]
|
|
define void @f0() {
|
|
; OPT-LABEL: @f0() {
|
|
; OPT-NEXT: [[LDS_SIZE_1_ALIGN_1_BC:%.*]] = bitcast [1 x i8] addrspace(3)* getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T:%.*]], [[LLVM_AMDGCN_MODULE_LDS_T]] addrspace(3)* @llvm.amdgcn.module.lds, i32 0, i32 0) to i8 addrspace(3)*
|
|
; OPT-NEXT: store i8 3, i8 addrspace(3)* [[LDS_SIZE_1_ALIGN_1_BC]], align 1
|
|
; OPT-NEXT: ret void
|
|
;
|
|
%lds.size.1.align.1.bc = bitcast [1 x i8] addrspace(3)* @lds.size.1.align.1 to i8 addrspace(3)*
|
|
store i8 3, i8 addrspace(3)* %lds.size.1.align.1.bc, align 1
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-elide-module-lds" }
|
|
; CHECK: attributes #0 = { "amdgpu-elide-module-lds" }
|