mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
7d05776a25
Summary: The method attempts to find loads that can be legally clustered by looking for loads consuming the same chain glue token. However, the old code looks at _all_ users of values produced by the chain node -- including uses of the loaded/returned value of volatile loads or atomics. This could lead to circular dependencies which then failed during scheduling. With this change, we filter out users by getResNo, i.e. by which SDValue value they use, to ensure that we only look at users of the chain glue token. This appears to be a rather old bug, which is perhaps surprising. However, the test case is actually quite fragile (i.e., it is hidden by fairly small changes), and the test _must_ use volatile loads for the bug to manifest. Reviewers: arsenm, bogner, craig.topper, foad Subscribers: MatzeB, jvesely, wdng, hiraditya, javed.absar, jfb, kerbowa, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D74253
28 lines
1.0 KiB
LLVM
28 lines
1.0 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=gfx1010 -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
|
|
|
|
; This used to cause a circular chain dependency during
|
|
; SelectionDAG instruction scheduling.
|
|
|
|
; CHECK-LABEL: {{^}}_amdgpu_gs_main:
|
|
; CHECK: ds_read_b32
|
|
; CHECK: ds_read_b32
|
|
; CHECK: ds_read_b32
|
|
; CHECK: ds_read_b32
|
|
define amdgpu_gs float @_amdgpu_gs_main(i8 addrspace(3)* %arg0, i8 addrspace(3)* %arg1, i8 addrspace(3)* %arg2) #0 {
|
|
%tmp0 = bitcast i8 addrspace(3)* %arg0 to i32 addrspace(3)* addrspace(3)*
|
|
%tmp = load volatile i32 addrspace(3)*, i32 addrspace(3)* addrspace(3)* %tmp0, align 4
|
|
|
|
%tmp3 = load volatile i32, i32 addrspace(3)* %tmp, align 4
|
|
|
|
%tmp4a = bitcast i8 addrspace(3)* %arg1 to i32 addrspace(3)*
|
|
%tmp4 = load volatile i32, i32 addrspace(3)* %tmp4a, align 4
|
|
|
|
%tmp7a = getelementptr i32, i32 addrspace(3)* %tmp, i32 8
|
|
%tmp8 = load volatile i32, i32 addrspace(3)* %tmp7a, align 4
|
|
|
|
%tmp9 = add i32 %tmp3, %tmp8
|
|
%tmp10 = add i32 %tmp9, %tmp4
|
|
%tmp14 = bitcast i32 %tmp10 to float
|
|
ret float %tmp14
|
|
}
|