mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-24 05:23:45 +02:00
7b6e012d2f
In Memcpy lowering we had missed a dependence from the load of the operation to successor operations. This causes us to potentially construct an in initial DAG with a memory dependence not fully represented in the chain sub-DAG but rather require looking at the entire DAG breaking alias analysis by allowing incorrect repositioning of memory operations. To work around this, r200033 changed DAGCombiner::GatherAllAliases to be conservative if any possible issues to happen. Unfortunately this check forbade many non-problematic situations as well. For example, it's common for incoming argument lowering to add a non-aliasing load hanging off of EntryNode. Then, if GatherAllAliases visited EntryNode, it would find that other (unvisited) use of the EntryNode chain, and just give up entirely. Furthermore, the check was incomplete: it would not actually detect all such potentially problematic DAG constructions, because GatherAllAliases did not guarantee to visit all chain nodes going up to the root EntryNode. This is in general fine -- giving up early will just miss a potential optimization, not generate incorrect results. But, for this non-chain dependency detection code, it's possible that you could have a load attached to a higher-up chain node than any which were visited. If that load aliases your store, but the only dependency is through the value operand of a non-aliasing store, it would've been missed by this code, and potentially reordered. With the dependence added, this check can be removed and Alias Analysis can be much more aggressive. This fixes code quality regression in the Consecutive Store Merge cleanup (D14834). Test Change: ppc64-align-long-double.ll now may see multiple serializations of its stores Differential Revision: http://reviews.llvm.org/D18062 llvm-svn: 265836
37 lines
1.2 KiB
LLVM
37 lines
1.2 KiB
LLVM
; RUN: llc -mcpu=pwr7 -O0 -fast-isel=false -mattr=-vsx < %s | FileCheck %s
|
|
; RUN: llc -mcpu=pwr7 -O0 -fast-isel=false -mattr=+vsx < %s | FileCheck -check-prefix=CHECK-VSX %s
|
|
|
|
; Verify internal alignment of long double in a struct. The double
|
|
; argument comes in in GPR3; GPR4 is skipped; GPRs 5 and 6 contain
|
|
; the long double. Check that these are stored to proper locations
|
|
; in the parameter save area and loaded from there for return in FPR1/2.
|
|
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
|
|
target triple = "powerpc64-unknown-linux-gnu"
|
|
|
|
%struct.S = type { double, ppc_fp128 }
|
|
|
|
define ppc_fp128 @test(%struct.S* byval %x) nounwind {
|
|
entry:
|
|
%b = getelementptr inbounds %struct.S, %struct.S* %x, i32 0, i32 1
|
|
%0 = load ppc_fp128, ppc_fp128* %b, align 16
|
|
ret ppc_fp128 %0
|
|
}
|
|
|
|
; CHECK-DAG: std 6, 72(1)
|
|
; CHECK-DAG: std 5, 64(1)
|
|
; CHECK-DAG: std 4, 56(1)
|
|
; CHECK-DAG: std 3, 48(1)
|
|
; CHECK: lfd 1, 64(1)
|
|
; CHECK: lfd 2, 72(1)
|
|
|
|
; CHECK-VSX-DAG: std 6, 72(1)
|
|
; CHECK-VSX-DAG: std 5, 64(1)
|
|
; CHECK-VSX-DAG: std 4, 56(1)
|
|
; CHECK-VSX-DAG: std 3, 48(1)
|
|
; CHECK-VSX: li 3, 16
|
|
; CHECK-VSX: addi 4, 1, 48
|
|
; CHECK-VSX: lxsdx 1, 4, 3
|
|
; CHECK-VSX: li 3, 24
|
|
; CHECK-VSX: lxsdx 2, 4, 3
|