mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 11:13:28 +01:00
f1ba4465de
Previously we would use a bundle to hint the register allocator to not overwrite the pointers in a sequence of loads to avoid breaking soft clauses. This bundling was based on a fuzzy register pressure heuristic, so we could not guarantee using more registers than are really available. This would result in register allocator failing on unsatisfiable bundles. Use a kill to artificially extend the live ranges, so we can always succeed at register allocation even if it means extra spills in the worst case. This seems to capture most of the benefit of the bundle while avoiding most of the risk presented by the bundle. However the lit tests do show a handful of regressions. In some cases with sequences of volatile loads, unused load components end up getting reallocated to the next load which forces a wait between. There are also a few small scheduling regressions where a hazard used to be avoided, and one spill torture test which for some reason nearly doubles the stack usage. There is also a bit of noise from leftover kills (it may make sense for post-RA pseudos to strip all of these out).
66 lines
3.5 KiB
LLVM
66 lines
3.5 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -stop-after=si-form-memory-clauses < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}name:{{[ ]*}}vector_clause
|
|
; GCN: LOAD_DWORDX2
|
|
; GCN-NEXT: LOAD_DWORDX2
|
|
; GCN-NEXT: KILL
|
|
define amdgpu_kernel void @vector_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp2 = zext i32 %tmp to i64
|
|
%tmp3 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp2
|
|
%tmp4 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp3, align 16
|
|
%tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp2
|
|
%tmp6 = add nuw nsw i64 %tmp2, 1
|
|
%tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp6
|
|
%tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
|
|
%tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
|
|
%tmp10 = add nuw nsw i64 %tmp2, 2
|
|
%tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
|
|
%tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
|
|
%tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
|
|
%tmp14 = add nuw nsw i64 %tmp2, 3
|
|
%tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
|
|
%tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
|
|
%tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
|
|
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %tmp5, align 16
|
|
store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
|
|
store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
|
|
store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}name:{{[ ]*}}no_vector_clause
|
|
; GCN-NOT: BUNDLE
|
|
; GCN-NOT: KILL
|
|
define amdgpu_kernel void @no_vector_clause(<4 x i32> addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture %arg1) #0 {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp2 = zext i32 %tmp to i64
|
|
%tmp3 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp2
|
|
%tmp4 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp3, align 16
|
|
%tmp5 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp2
|
|
%tmp6 = add nuw nsw i64 %tmp2, 1
|
|
%tmp7 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp6
|
|
%tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
|
|
%tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
|
|
%tmp10 = add nuw nsw i64 %tmp2, 2
|
|
%tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
|
|
%tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
|
|
%tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
|
|
%tmp14 = add nuw nsw i64 %tmp2, 3
|
|
%tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
|
|
%tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
|
|
%tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
|
|
store <4 x i32> %tmp4, <4 x i32> addrspace(1)* %tmp5, align 16
|
|
store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
|
|
store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
|
|
store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|
|
|
|
attributes #0 = { "amdgpu-max-memory-clause"="1" }
|
|
|