RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity
5cf4e36ce1
llvm-mirror/test/CodeGen/AMDGPU/replace-lds-by-ptr-use-multiple-lds.ll

67 lines
3.1 KiB
LLVM
Raw Normal View History

Disable ReplaceLDS pass, patch up tests to match Most tests passed with an extra argument to explicitly enable the pass. One does not, deleted it as part of this change. I can't see why the codegen would be different between default on and default off but switched on. It can be retrieved from the project history. This would be a revert, but git revert was not clean. Disabling the pass and leaving it in tree is less likely to cause breakage elsewhere than patching up the git revert conflicts on unfamiliar code. It'll be landed without review, as @hsmhsm is believed unavailable at present. Differential Revision: https://reviews.llvm.org/D104962
2021-06-26 02:36:41 +02:00
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-replace-lds-use-with-pointer -amdgpu-enable-lds-replace-with-pointer=true < %s | FileCheck %s
[AMDGPU] Replace non-kernel function uses of LDS globals by pointers. The main motivation behind pointer replacement of LDS use within non-kernel functions is - to *avoid* subsequent LDS lowering pass from directly packing LDS (assume large LDS) into a struct type which would otherwise cause allocating huge memory for struct instance within every kernel. Reviewed By: rampitec Differential Revision: https://reviews.llvm.org/D103225
2021-06-21 07:25:23 +02:00
; DESCRIPTION:
;
; There are three lds globals defined here, and these three lds are used within a single
; non-kernel function, and this non-kernel function is reachable from kernel. Hence pointer
; replacement is required for all three lds globals.
;
; Original LDS should exist.
; CHECK: @lds1 = internal addrspace(3) global [1 x i32] undef, align 4
; CHECK: @lds2 = internal addrspace(3) global [2 x i32] undef, align 4
; CHECK: @lds3 = internal addrspace(3) global [3 x i32] undef, align 4
@lds1 = internal addrspace(3) global [1 x i32] undef, align 4
@lds2 = internal addrspace(3) global [2 x i32] undef, align 4
@lds3 = internal addrspace(3) global [3 x i32] undef, align 4
; Pointers should be created.
; CHECK: @lds1.ptr = internal unnamed_addr addrspace(3) global i16 undef, align 2
; CHECK: @lds2.ptr = internal unnamed_addr addrspace(3) global i16 undef, align 2
; CHECK: @lds3.ptr = internal unnamed_addr addrspace(3) global i16 undef, align 2
; Pointer replacement code should be added.
define internal void @function() {
; CHECK-LABEL: entry:
; CHECK: %0 = load i16, i16 addrspace(3)* @lds3.ptr, align 2
; CHECK: %1 = getelementptr i8, i8 addrspace(3)* null, i16 %0
; CHECK: %2 = bitcast i8 addrspace(3)* %1 to [3 x i32] addrspace(3)*
; CHECK: %3 = load i16, i16 addrspace(3)* @lds2.ptr, align 2
; CHECK: %4 = getelementptr i8, i8 addrspace(3)* null, i16 %3
; CHECK: %5 = bitcast i8 addrspace(3)* %4 to [2 x i32] addrspace(3)*
; CHECK: %6 = load i16, i16 addrspace(3)* @lds1.ptr, align 2
; CHECK: %7 = getelementptr i8, i8 addrspace(3)* null, i16 %6
; CHECK: %8 = bitcast i8 addrspace(3)* %7 to [1 x i32] addrspace(3)*
; CHECK: %gep1 = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* %8, i32 0, i32 0
; CHECK: %gep2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* %5, i32 0, i32 0
; CHECK: %gep3 = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* %2, i32 0, i32 0
; CHECK: ret void
entry:
%gep1 = getelementptr inbounds [1 x i32], [1 x i32] addrspace(3)* @lds1, i32 0, i32 0
%gep2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @lds2, i32 0, i32 0
%gep3 = getelementptr inbounds [3 x i32], [3 x i32] addrspace(3)* @lds3, i32 0, i32 0
ret void
}
; Pointer initialization code shoud be added;
define protected amdgpu_kernel void @kernel() {
; CHECK-LABEL: entry:
; CHECK: %0 = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0)
; CHECK: %1 = icmp eq i32 %0, 0
; CHECK: br i1 %1, label %2, label %3
;
; CHECK-LABEL: 2:
; CHECK: store i16 ptrtoint ([3 x i32] addrspace(3)* @lds3 to i16), i16 addrspace(3)* @lds3.ptr, align 2
; CHECK: store i16 ptrtoint ([2 x i32] addrspace(3)* @lds2 to i16), i16 addrspace(3)* @lds2.ptr, align 2
; CHECK: store i16 ptrtoint ([1 x i32] addrspace(3)* @lds1 to i16), i16 addrspace(3)* @lds1.ptr, align 2
; CHECK: br label %3
;
; CHECK-LABEL: 3:
; CHECK: call void @llvm.amdgcn.wave.barrier()
; CHECK: call void @function()
; CHECK: ret void
entry:
call void @function()
ret void
}
Reference in New Issue Copy Permalink