maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/lds-m0-init-in-loop.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

50 lines
1.7 KiB
LLVM
Raw Normal View History

AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; Make sure that m0 is not reinitialized in the loop.
; GCN-LABEL: {{^}}copy_local_to_global_loop_m0_init:
AMDGPU: Implement AnalyzeBranch Original patch by Tom Stellard llvm-svn: 270295
2016-05-21 08:29:27 +08:00
; GCN: s_cbranch_scc1 BB0_3
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
; Initialize in preheader
; GCN: s_mov_b32 m0, -1
AMDGPU: Implement AnalyzeBranch Original patch by Tom Stellard llvm-svn: 270295
2016-05-21 08:29:27 +08:00
; GCN: BB0_2:
AMDGPU: Don't required structured CFG The structured CFG is just an aid to inserting exec mask modification instructions, once that is done we don't really need it anymore. We also do not analyze blocks with terminators that modify exec, so this should only be impacting true branches. llvm-svn: 288744
2016-12-06 09:02:51 +08:00
; GCN-NOT: m0
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
; GCN: ds_read_b32
AMDGPU: Don't required structured CFG The structured CFG is just an aid to inserting exec mask modification instructions, once that is done we don't really need it anymore. We also do not analyze blocks with terminators that modify exec, so this should only be impacting true branches. llvm-svn: 288744
2016-12-06 09:02:51 +08:00
; GCN-NOT: m0
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
; GCN: buffer_store_dword
AMDGPU/SI: Avoid moving PHIs to VALU when phi values are defined in scalar branches Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D23417 llvm-svn: 288095
2016-11-29 08:46:46 +08:00
; GCN: s_cbranch_scc0 BB0_2
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
AMDGPU: Implement AnalyzeBranch Original patch by Tom Stellard llvm-svn: 270295
2016-05-21 08:29:27 +08:00
; GCN: BB0_3:
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
; GCN-NEXT: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @copy_local_to_global_loop_m0_init(i32 addrspace(1)* noalias nocapture %out, i32 addrspace(3)* noalias nocapture readonly %in, i32 %n) #0 {
AMDGPU: Add test for m0 initialization in basic loop Initialization of m0 is emitted for each LDS operation, so every block with LDS usage ends up with one. MachineLICM used to fail to hoist this out of the loop, so every loop iteration with LDS usage in it would re-initialize it. This seems to be fixed now, so add a test to make sure that it stays this way. llvm-svn: 266156
2016-04-13 08:39:52 +08:00
bb:
%tmp = icmp sgt i32 %n, 0
br i1 %tmp, label %.lr.ph.preheader, label %._crit_edge
.lr.ph.preheader: ; preds = %bb
br label %.lr.ph
._crit_edge.loopexit: ; preds = %.lr.ph
br label %._crit_edge
._crit_edge: ; preds = %._crit_edge.loopexit, %bb
ret void
.lr.ph: ; preds = %.lr.ph, %.lr.ph.preheader
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%i.01 = phi i32 [ %tmp4, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%tmp1 = getelementptr inbounds i32, i32 addrspace(3)* %in, i32 %i.01
%tmp2 = load i32, i32 addrspace(3)* %tmp1, align 4
%tmp3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %indvars.iv
store i32 %tmp2, i32 addrspace(1)* %tmp3, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%tmp4 = add nuw nsw i32 %i.01, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge.loopexit, label %.lr.ph
}
attributes #0 = { nounwind }