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/multi-divergent-exit-region.ll

726 lines
26 KiB
LLVM
Raw Normal View History

AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; RUN: opt -mtriple=amdgcn-- -S -amdgpu-unify-divergent-exit-nodes -verify -structurizecfg -verify -si-annotate-control-flow %s | FileCheck -check-prefix=IR %s
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; Add an extra verifier runs. There were some cases where invalid IR
; was produced but happened to be fixed by the later passes.
; Make sure divergent control flow with multiple exits from a region
; is properly handled. UnifyFunctionExitNodes should be run before
; StructurizeCFG.
; IR-LABEL: @multi_divergent_region_exit_ret_ret(
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %1 = call { i1, i64 } @llvm.amdgcn.if(i1 %0)
; IR: %2 = extractvalue { i1, i64 } %1, 0
; IR: %3 = extractvalue { i1, i64 } %1, 1
; IR: br i1 %2, label %LeafBlock1, label %Flow
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: Flow:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %4 = phi i1 [ true, %LeafBlock1 ], [ false, %entry ]
; IR: %5 = phi i1 [ %10, %LeafBlock1 ], [ false, %entry ]
; IR: %6 = call { i1, i64 } @llvm.amdgcn.else(i64 %3)
; IR: %7 = extractvalue { i1, i64 } %6, 0
; IR: %8 = extractvalue { i1, i64 } %6, 1
; IR: br i1 %7, label %LeafBlock, label %Flow1
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: LeafBlock:
; IR: br label %Flow1
; IR: LeafBlock1:
; IR: br label %Flow{{$}}
; IR: Flow2:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
; IR: %12 = call { i1, i64 } @llvm.amdgcn.if(i1 %11)
; IR: %13 = extractvalue { i1, i64 } %12, 0
; IR: %14 = extractvalue { i1, i64 } %12, 1
; IR: br i1 %13, label %exit0, label %UnifiedReturnBlock
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit0:
; IR: store volatile i32 9, i32 addrspace(1)* undef
; IR: br label %UnifiedReturnBlock
; IR: Flow1:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %15 = phi i1 [ %SwitchLeaf, %LeafBlock ], [ %4, %Flow ]
; IR: %16 = phi i1 [ %9, %LeafBlock ], [ %5, %Flow ]
; IR: call void @llvm.amdgcn.end.cf(i64 %8)
; IR: %17 = call { i1, i64 } @llvm.amdgcn.if(i1 %16)
; IR: %18 = extractvalue { i1, i64 } %17, 0
; IR: %19 = extractvalue { i1, i64 } %17, 1
; IR: br i1 %18, label %exit1, label %Flow2
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit1:
; IR: store volatile i32 17, i32 addrspace(3)* undef
; IR: br label %Flow2
; IR: UnifiedReturnBlock:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: call void @llvm.amdgcn.end.cf(i64 %14)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: ret void
; GCN-LABEL: {{^}}multi_divergent_region_exit_ret_ret:
Bias physical register immediate assignments The machine scheduler currently biases register copies to/from physical registers to be closer to their point of use / def to minimize their live ranges. This change extends this to also physical register assignments from immediate values. This causes a reduction in reduction in overall register pressure and minor reduction in spills and indirectly fixes an out-of-registers assertion (PR39391). Most test changes are from minor instruction reorderings and register name selection changes and direct consequences of that. Reviewers: MatzeB, qcolombet, myatsina, pcc Subscribers: nemanjai, jvesely, nhaehnle, eraman, hiraditya, javed.absar, arphaman, jfb, jsji, llvm-commits Differential Revision: https://reviews.llvm.org/D54218 llvm-svn: 346894
2018-11-15 05:11:53 +08:00
; GCN-DAG: s_mov_b64 [[EXIT1:s\[[0-9]+:[0-9]+\]]], 0
; GCN-DAG: v_cmp_lt_i32_e32 vcc, 1,
; GCN-DAG: s_mov_b64 [[EXIT0:s\[[0-9]+:[0-9]+\]]], 0
; GCN-DAG: s_and_saveexec_b64
; GCN-DAG: s_xor_b64
AMDGPU: Rewrite SILowerI1Copies to always stay on SALU Summary: Instead of writing boolean values temporarily into 32-bit VGPRs if they are involved in PHIs or are observed from outside a loop, we use bitwise masking operations to combine lane masks in a way that is consistent with wave control flow. Move SIFixSGPRCopies to before this pass, since that pass incorrectly attempts to move SGPR phis to VGPRs. This should recover most of the code quality that was lost with the bug fix in "AMDGPU: Remove PHI loop condition optimization". There are still some relevant cases where code quality could be improved, in particular: - We often introduce redundant masks with EXEC. Ideally, we'd have a generic computeKnownBits-like analysis to determine whether masks are already masked by EXEC, so we can avoid this masking both here and when lowering uniform control flow. - The criterion we use to determine whether a def is observed from outside a loop is conservative: it doesn't check whether (loop) branch conditions are uniform. Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D53496 llvm-svn: 345719
2018-10-31 21:27:08 +08:00
; GCN: ; %LeafBlock1
; GCN-NEXT: s_mov_b64 [[EXIT0]], exec
; GCN-NEXT: v_cmp_ne_u32_e32 vcc, 2,
; GCN-NEXT: s_and_b64 [[EXIT1]], vcc, exec
; GCN: ; %Flow
; GCN-NEXT: s_or_saveexec_b64
; GCN-NEXT: s_xor_b64
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; FIXME: Why is this compare essentially repeated?
AMDGPU: Rewrite SILowerI1Copies to always stay on SALU Summary: Instead of writing boolean values temporarily into 32-bit VGPRs if they are involved in PHIs or are observed from outside a loop, we use bitwise masking operations to combine lane masks in a way that is consistent with wave control flow. Move SIFixSGPRCopies to before this pass, since that pass incorrectly attempts to move SGPR phis to VGPRs. This should recover most of the code quality that was lost with the bug fix in "AMDGPU: Remove PHI loop condition optimization". There are still some relevant cases where code quality could be improved, in particular: - We often introduce redundant masks with EXEC. Ideally, we'd have a generic computeKnownBits-like analysis to determine whether masks are already masked by EXEC, so we can avoid this masking both here and when lowering uniform control flow. - The criterion we use to determine whether a def is observed from outside a loop is conservative: it doesn't check whether (loop) branch conditions are uniform. Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D53496 llvm-svn: 345719
2018-10-31 21:27:08 +08:00
; GCN: ; %LeafBlock
; GCN-DAG: v_cmp_eq_u32_e32 vcc, 1,
; GCN-DAG: v_cmp_ne_u32_e64 [[TMP1:s\[[0-9]+:[0-9]+\]]], 1,
; GCN-DAG: s_andn2_b64 [[EXIT0]], [[EXIT0]], exec
; GCN-DAG: s_andn2_b64 [[EXIT1]], [[EXIT1]], exec
; GCN-DAG: s_and_b64 [[TMP0:s\[[0-9]+:[0-9]+\]]], vcc, exec
; GCN-DAG: s_and_b64 [[TMP1]], [[TMP1]], exec
; GCN-DAG: s_or_b64 [[EXIT0]], [[EXIT0]], [[TMP0]]
; GCN-DAG: s_or_b64 [[EXIT1]], [[EXIT1]], [[TMP1]]
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
AMDGPU: Don't use struct type for argument layout This was introducing unnecessary padding after the explicit arguments, depending on the alignment of the total struct type. Also has the side effect of avoiding creating an extra GEP for the offset from the base kernel argument to the explicit kernel argument offset. llvm-svn: 335999
2018-06-30 01:31:42 +08:00
; GCN: ; %Flow4
AMDGPU: Rewrite SILowerI1Copies to always stay on SALU Summary: Instead of writing boolean values temporarily into 32-bit VGPRs if they are involved in PHIs or are observed from outside a loop, we use bitwise masking operations to combine lane masks in a way that is consistent with wave control flow. Move SIFixSGPRCopies to before this pass, since that pass incorrectly attempts to move SGPR phis to VGPRs. This should recover most of the code quality that was lost with the bug fix in "AMDGPU: Remove PHI loop condition optimization". There are still some relevant cases where code quality could be improved, in particular: - We often introduce redundant masks with EXEC. Ideally, we'd have a generic computeKnownBits-like analysis to determine whether masks are already masked by EXEC, so we can avoid this masking both here and when lowering uniform control flow. - The criterion we use to determine whether a def is observed from outside a loop is conservative: it doesn't check whether (loop) branch conditions are uniform. Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D53496 llvm-svn: 345719
2018-10-31 21:27:08 +08:00
; GCN-NEXT: s_or_b64 exec, exec,
; GCN-NEXT: s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[EXIT1]]
; GCN-NEXT: s_xor_b64
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; GCN: ; %exit1
Bias physical register immediate assignments The machine scheduler currently biases register copies to/from physical registers to be closer to their point of use / def to minimize their live ranges. This change extends this to also physical register assignments from immediate values. This causes a reduction in reduction in overall register pressure and minor reduction in spills and indirectly fixes an out-of-registers assertion (PR39391). Most test changes are from minor instruction reorderings and register name selection changes and direct consequences of that. Reviewers: MatzeB, qcolombet, myatsina, pcc Subscribers: nemanjai, jvesely, nhaehnle, eraman, hiraditya, javed.absar, arphaman, jfb, jsji, llvm-commits Differential Revision: https://reviews.llvm.org/D54218 llvm-svn: 346894
2018-11-15 05:11:53 +08:00
; GCN-DAG: ds_write_b32
; GCN-DAG: s_andn2_b64 [[EXIT0]], [[EXIT0]], exec
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
AMDGPU: Rewrite SILowerI1Copies to always stay on SALU Summary: Instead of writing boolean values temporarily into 32-bit VGPRs if they are involved in PHIs or are observed from outside a loop, we use bitwise masking operations to combine lane masks in a way that is consistent with wave control flow. Move SIFixSGPRCopies to before this pass, since that pass incorrectly attempts to move SGPR phis to VGPRs. This should recover most of the code quality that was lost with the bug fix in "AMDGPU: Remove PHI loop condition optimization". There are still some relevant cases where code quality could be improved, in particular: - We often introduce redundant masks with EXEC. Ideally, we'd have a generic computeKnownBits-like analysis to determine whether masks are already masked by EXEC, so we can avoid this masking both here and when lowering uniform control flow. - The criterion we use to determine whether a def is observed from outside a loop is conservative: it doesn't check whether (loop) branch conditions are uniform. Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D53496 llvm-svn: 345719
2018-10-31 21:27:08 +08:00
; GCN: ; %Flow5
; GCN-NEXT: s_or_b64 exec, exec,
; GCN-NEXT; s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[EXIT0]]
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; GCN: ; %exit0
AMDGPU: Rewrite SILowerI1Copies to always stay on SALU Summary: Instead of writing boolean values temporarily into 32-bit VGPRs if they are involved in PHIs or are observed from outside a loop, we use bitwise masking operations to combine lane masks in a way that is consistent with wave control flow. Move SIFixSGPRCopies to before this pass, since that pass incorrectly attempts to move SGPR phis to VGPRs. This should recover most of the code quality that was lost with the bug fix in "AMDGPU: Remove PHI loop condition optimization". There are still some relevant cases where code quality could be improved, in particular: - We often introduce redundant masks with EXEC. Ideally, we'd have a generic computeKnownBits-like analysis to determine whether masks are already masked by EXEC, so we can avoid this masking both here and when lowering uniform control flow. - The criterion we use to determine whether a def is observed from outside a loop is conservative: it doesn't check whether (loop) branch conditions are uniform. Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D53496 llvm-svn: 345719
2018-10-31 21:27:08 +08:00
; GCN: buffer_store_dword
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; GCN: ; %UnifiedReturnBlock
; GCN-NEXT: s_endpgm
define amdgpu_kernel void @multi_divergent_region_exit_ret_ret(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%Pivot = icmp slt i32 %tmp16, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %tmp16, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
ret void
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
}
; IR-LABEL: @multi_divergent_region_exit_unreachable_unreachable(
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %1 = call { i1, i64 } @llvm.amdgcn.if(i1 %0)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %6 = call { i1, i64 } @llvm.amdgcn.else(i64 %3)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
; IR: %12 = call { i1, i64 } @llvm.amdgcn.if(i1 %11)
; IR: br i1 %13, label %exit0, label %UnifiedUnreachableBlock
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: UnifiedUnreachableBlock:
; IR-NEXT: unreachable
; FIXME: Probably should insert an s_endpgm anyway.
; GCN-LABEL: {{^}}multi_divergent_region_exit_unreachable_unreachable:
; GCN: ; %UnifiedUnreachableBlock
; GCN-NEXT: .Lfunc_end
define amdgpu_kernel void @multi_divergent_region_exit_unreachable_unreachable(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%Pivot = icmp slt i32 %tmp16, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %tmp16, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
unreachable
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
unreachable
}
; IR-LABEL: @multi_exit_region_divergent_ret_uniform_ret(
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %divergent.cond0 = icmp slt i32 %tmp16, 2
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: llvm.amdgcn.if
; IR: br i1
; IR: {{^}}Flow:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %4 = phi i1 [ true, %LeafBlock1 ], [ false, %entry ]
; IR: %5 = phi i1 [ %10, %LeafBlock1 ], [ false, %entry ]
; IR: %6 = call { i1, i64 } @llvm.amdgcn.else(i64 %3)
; IR: br i1 %7, label %LeafBlock, label %Flow1
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: {{^}}LeafBlock:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %divergent.cond1 = icmp eq i32 %tmp16, 1
; IR: %9 = xor i1 %divergent.cond1, true
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: br label %Flow1
; IR: LeafBlock1:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %uniform.cond0 = icmp eq i32 %arg3, 2
; IR: %10 = xor i1 %uniform.cond0, true
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: br label %Flow
; IR: Flow2:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
; IR: %12 = call { i1, i64 } @llvm.amdgcn.if(i1 %11)
; IR: br i1 %13, label %exit0, label %UnifiedReturnBlock
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit0:
; IR: store volatile i32 9, i32 addrspace(1)* undef
; IR: br label %UnifiedReturnBlock
; IR: {{^}}Flow1:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %15 = phi i1 [ %divergent.cond1, %LeafBlock ], [ %4, %Flow ]
; IR: %16 = phi i1 [ %9, %LeafBlock ], [ %5, %Flow ]
; IR: call void @llvm.amdgcn.end.cf(i64 %8)
; IR: %17 = call { i1, i64 } @llvm.amdgcn.if(i1 %16)
; IR: %18 = extractvalue { i1, i64 } %17, 0
; IR: %19 = extractvalue { i1, i64 } %17, 1
; IR: br i1 %18, label %exit1, label %Flow2
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit1:
; IR: store volatile i32 17, i32 addrspace(3)* undef
; IR: br label %Flow2
; IR: UnifiedReturnBlock:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: call void @llvm.amdgcn.end.cf(i64 %14)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: ret void
define amdgpu_kernel void @multi_exit_region_divergent_ret_uniform_ret(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2, i32 %arg3) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%divergent.cond0 = icmp slt i32 %tmp16, 2
br i1 %divergent.cond0, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%divergent.cond1 = icmp eq i32 %tmp16, 1
br i1 %divergent.cond1, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%uniform.cond0 = icmp eq i32 %arg3, 2
br i1 %uniform.cond0, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
ret void
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
}
; IR-LABEL: @multi_exit_region_uniform_ret_divergent_ret(
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %1 = call { i1, i64 } @llvm.amdgcn.if(i1 %0)
; IR: br i1 %2, label %LeafBlock1, label %Flow
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: Flow:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %4 = phi i1 [ true, %LeafBlock1 ], [ false, %entry ]
; IR: %5 = phi i1 [ %10, %LeafBlock1 ], [ false, %entry ]
; IR: %6 = call { i1, i64 } @llvm.amdgcn.else(i64 %3)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
; IR: %12 = call { i1, i64 } @llvm.amdgcn.if(i1 %11)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
define amdgpu_kernel void @multi_exit_region_uniform_ret_divergent_ret(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2, i32 %arg3) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%Pivot = icmp slt i32 %tmp16, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %arg3, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
ret void
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
}
; IR-LABEL: @multi_divergent_region_exit_ret_ret_return_value(
; IR: Flow2:
StructurizeCFG: Simplify inserted PHI nodes Summary: This improves subsequent divergence analysis in some cases. Change-Id: I5e95e7ec7fd3fa80d414d1a53a02fea23e3d67d3 Reviewers: arsenm, rampitec Subscribers: jvesely, wdng, llvm-commits Differential Revision: https://reviews.llvm.org/D53316 llvm-svn: 344697
2018-10-17 23:37:41 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: UnifiedReturnBlock:
StructurizeCFG: Simplify inserted PHI nodes Summary: This improves subsequent divergence analysis in some cases. Change-Id: I5e95e7ec7fd3fa80d414d1a53a02fea23e3d67d3 Reviewers: arsenm, rampitec Subscribers: jvesely, wdng, llvm-commits Differential Revision: https://reviews.llvm.org/D53316 llvm-svn: 344697
2018-10-17 23:37:41 +08:00
; IR: %UnifiedRetVal = phi float [ 2.000000e+00, %Flow2 ], [ 1.000000e+00, %exit0 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %14)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: ret float %UnifiedRetVal
define amdgpu_ps float @multi_divergent_region_exit_ret_ret_return_value(i32 %vgpr) #0 {
entry:
%Pivot = icmp slt i32 %vgpr, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %vgpr, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %vgpr, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store i32 9, i32 addrspace(1)* undef
ret float 1.0
exit1: ; preds = %LeafBlock, %LeafBlock1
store i32 17, i32 addrspace(3)* undef
ret float 2.0
}
; IR-LABEL: @uniform_branch_to_multi_divergent_region_exit_ret_ret_return_value(
; GCN-LABEL: {{^}}uniform_branch_to_multi_divergent_region_exit_ret_ret_return_value:
; GCN: s_cmp_gt_i32 s0, 1
; GCN: s_cbranch_scc0 [[FLOW:BB[0-9]+_[0-9]+]]
; GCN: v_cmp_ne_u32_e32 vcc, 7, v0
; GCN: {{^}}[[FLOW]]:
; GCN: s_cbranch_vccnz [[FLOW1:BB[0-9]+]]
; GCN: s_or_b64 exec, exec
StructurizeCFG: Simplify inserted PHI nodes Summary: This improves subsequent divergence analysis in some cases. Change-Id: I5e95e7ec7fd3fa80d414d1a53a02fea23e3d67d3 Reviewers: arsenm, rampitec Subscribers: jvesely, wdng, llvm-commits Differential Revision: https://reviews.llvm.org/D53316 llvm-svn: 344697
2018-10-17 23:37:41 +08:00
; GCN: v_mov_b32_e32 v0, 2.0
[AMDGPU] Don't force WQM for DS op Summary: Previously, all DS ops forced WQM in a pixel shader. That was a hack to allow for graphics frontends using ds_swizzle to implement explicit derivatives, on SI/CI at least where DPP is not available. But it forced WQM for _any_ DS op. With this commit, DS ops no longer force WQM. Both graphics frontends (Mesa and LLPC) need to change to issue an explicit llvm.amdgcn.wqm intrinsic call when calculating explicit derivatives. The required Mesa change is: "amd/common: use llvm.amdgcn.wqm for explicit derivatives". Subscribers: qcolombet, arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D46051 Change-Id: I9b745b626fa91bbd66456e6cf41ee07eeea42f81 llvm-svn: 331633
2018-05-07 21:21:26 +08:00
; GCN-NOT: s_and_b64 exec, exec
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; GCN: v_mov_b32_e32 v0, 1.0
; GCN: {{^BB[0-9]+_[0-9]+}}: ; %UnifiedReturnBlock
; GCN-NEXT: s_or_b64 exec, exec
[AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. -enable-si-insert-waitcnts=1 becomes the default -enable-si-insert-waitcnts=0 to use old pass Differential Revision: https://reviews.llvm.org/D33730 llvm-svn: 304551
2017-06-02 22:19:25 +08:00
; GCN-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; GCN-NEXT: ; return
define amdgpu_ps float @uniform_branch_to_multi_divergent_region_exit_ret_ret_return_value(i32 inreg %sgpr, i32 %vgpr) #0 {
entry:
%uniform.cond = icmp slt i32 %sgpr, 2
br i1 %uniform.cond, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%divergent.cond0 = icmp eq i32 %vgpr, 3
br i1 %divergent.cond0, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%divergent.cond1 = icmp eq i32 %vgpr, 7
br i1 %divergent.cond1, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store i32 9, i32 addrspace(1)* undef
ret float 1.0
exit1: ; preds = %LeafBlock, %LeafBlock1
store i32 17, i32 addrspace(3)* undef
ret float 2.0
}
; IR-LABEL: @multi_divergent_region_exit_ret_unreachable(
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %1 = call { i1, i64 } @llvm.amdgcn.if(i1 %0)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: Flow:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %4 = phi i1 [ true, %LeafBlock1 ], [ false, %entry ]
; IR: %5 = phi i1 [ %10, %LeafBlock1 ], [ false, %entry ]
; IR: %6 = call { i1, i64 } @llvm.amdgcn.else(i64 %3)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: Flow2:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ false, %exit1 ], [ %15, %Flow1 ]
; IR: call void @llvm.amdgcn.end.cf(i64 %19)
; IR: %12 = call { i1, i64 } @llvm.amdgcn.if(i1 %11)
; IR: br i1 %13, label %exit0, label %UnifiedReturnBlock
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit0:
; IR-NEXT: store volatile i32 17, i32 addrspace(3)* undef
; IR-NEXT: br label %UnifiedReturnBlock
; IR: Flow1:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %15 = phi i1 [ %SwitchLeaf, %LeafBlock ], [ %4, %Flow ]
; IR: %16 = phi i1 [ %9, %LeafBlock ], [ %5, %Flow ]
; IR: call void @llvm.amdgcn.end.cf(i64 %8)
; IR: %17 = call { i1, i64 } @llvm.amdgcn.if(i1 %16)
; IR: %18 = extractvalue { i1, i64 } %17, 0
; IR: %19 = extractvalue { i1, i64 } %17, 1
; IR: br i1 %18, label %exit1, label %Flow2
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: exit1:
; IR-NEXT: store volatile i32 9, i32 addrspace(1)* undef
; IR-NEXT: call void @llvm.amdgcn.unreachable()
; IR-NEXT: br label %Flow2
; IR: UnifiedReturnBlock:
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR-NEXT: call void @llvm.amdgcn.end.cf(i64 %14)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR-NEXT: ret void
define amdgpu_kernel void @multi_divergent_region_exit_ret_unreachable(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%Pivot = icmp slt i32 %tmp16, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %tmp16, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
unreachable
}
; The non-uniformity of the branch to the exiting blocks requires
; looking at transitive predecessors.
; IR-LABEL: @indirect_multi_divergent_region_exit_ret_unreachable(
; IR: exit0: ; preds = %Flow2
; IR-NEXT: store volatile i32 17, i32 addrspace(3)* undef
; IR-NEXT: br label %UnifiedReturnBlock
; IR: indirect.exit1:
; IR: %load = load volatile i32, i32 addrspace(1)* undef
; IR: store volatile i32 %load, i32 addrspace(1)* undef
; IR: store volatile i32 9, i32 addrspace(1)* undef
; IR: call void @llvm.amdgcn.unreachable()
; IR-NEXT: br label %Flow2
; IR: UnifiedReturnBlock: ; preds = %exit0, %Flow2
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR-NEXT: call void @llvm.amdgcn.end.cf(i64 %14)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR-NEXT: ret void
define amdgpu_kernel void @indirect_multi_divergent_region_exit_ret_unreachable(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
%Pivot = icmp slt i32 %tmp16, 2
br i1 %Pivot, label %LeafBlock, label %LeafBlock1
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %tmp16, 1
br i1 %SwitchLeaf, label %exit0, label %indirect.exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %indirect.exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
indirect.exit1:
%load = load volatile i32, i32 addrspace(1)* undef
store volatile i32 %load, i32 addrspace(1)* undef
br label %exit1
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
unreachable
}
; IR-LABEL: @multi_divergent_region_exit_ret_switch(
define amdgpu_kernel void @multi_divergent_region_exit_ret_switch(i32 addrspace(1)* nocapture %arg0, i32 addrspace(1)* nocapture %arg1, i32 addrspace(1)* nocapture %arg2) #0 {
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%tmp1 = add i32 0, %tmp
%tmp2 = zext i32 %tmp1 to i64
%tmp3 = add i64 0, %tmp2
%tmp4 = shl i64 %tmp3, 32
%tmp5 = ashr exact i64 %tmp4, 32
%tmp6 = getelementptr inbounds i32, i32 addrspace(1)* %arg0, i64 %tmp5
%tmp7 = load i32, i32 addrspace(1)* %tmp6, align 4
%tmp8 = sext i32 %tmp7 to i64
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg1, i64 %tmp8
%tmp10 = load i32, i32 addrspace(1)* %tmp9, align 4
%tmp13 = zext i32 %tmp10 to i64
%tmp14 = getelementptr inbounds i32, i32 addrspace(1)* %arg2, i64 %tmp13
%tmp16 = load i32, i32 addrspace(1)* %tmp14, align 16
switch i32 %tmp16, label %exit1
[ i32 1, label %LeafBlock
i32 2, label %LeafBlock1
i32 3, label %exit0 ]
LeafBlock: ; preds = %entry
%SwitchLeaf = icmp eq i32 %tmp16, 1
br i1 %SwitchLeaf, label %exit0, label %exit1
LeafBlock1: ; preds = %entry
%SwitchLeaf2 = icmp eq i32 %tmp16, 2
br i1 %SwitchLeaf2, label %exit0, label %exit1
exit0: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 17, i32 addrspace(3)* undef
ret void
exit1: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 9, i32 addrspace(1)* undef
unreachable
}
; IR-LABEL: @divergent_multi_ret_nest_in_uniform_triangle(
define amdgpu_kernel void @divergent_multi_ret_nest_in_uniform_triangle(i32 %arg0) #0 {
entry:
%uniform.cond0 = icmp eq i32 %arg0, 4
br i1 %uniform.cond0, label %divergent.multi.exit.region, label %uniform.ret
divergent.multi.exit.region:
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%divergent.cond0 = icmp eq i32 %id.x, 0
br i1 %divergent.cond0, label %divergent.ret0, label %divergent.ret1
divergent.ret0:
store volatile i32 11, i32 addrspace(3)* undef
ret void
divergent.ret1:
store volatile i32 42, i32 addrspace(3)* undef
ret void
uniform.ret:
store volatile i32 9, i32 addrspace(1)* undef
ret void
}
; IR-LABEL: @divergent_complex_multi_ret_nest_in_uniform_triangle(
define amdgpu_kernel void @divergent_complex_multi_ret_nest_in_uniform_triangle(i32 %arg0) #0 {
entry:
%uniform.cond0 = icmp eq i32 %arg0, 4
br i1 %uniform.cond0, label %divergent.multi.exit.region, label %uniform.ret
divergent.multi.exit.region:
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%divergent.cond0 = icmp eq i32 %id.x, 0
br i1 %divergent.cond0, label %divergent.if, label %divergent.ret1
divergent.if:
%vgpr0 = load volatile float, float addrspace(1)* undef
%divergent.cond1 = fcmp ogt float %vgpr0, 1.0
br i1 %divergent.cond1, label %divergent.then, label %divergent.endif
divergent.then:
%vgpr1 = load volatile float, float addrspace(1)* undef
%divergent.cond2 = fcmp olt float %vgpr1, 4.0
store volatile i32 33, i32 addrspace(1)* undef
br i1 %divergent.cond2, label %divergent.ret0, label %divergent.endif
divergent.endif:
store volatile i32 38, i32 addrspace(1)* undef
br label %divergent.ret0
divergent.ret0:
store volatile i32 11, i32 addrspace(3)* undef
ret void
divergent.ret1:
store volatile i32 42, i32 addrspace(3)* undef
ret void
uniform.ret:
store volatile i32 9, i32 addrspace(1)* undef
ret void
}
; IR-LABEL: @uniform_complex_multi_ret_nest_in_divergent_triangle(
; IR: Flow1: ; preds = %uniform.ret1, %uniform.multi.exit.region
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %8 = phi i1 [ false, %uniform.ret1 ], [ true, %uniform.multi.exit.region ]
; IR: br i1 %8, label %uniform.if, label %Flow2
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: Flow: ; preds = %uniform.then, %uniform.if
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR: %11 = phi i1 [ %10, %uniform.then ], [ %9, %uniform.if ]
; IR: br i1 %11, label %uniform.endif, label %uniform.ret0
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR: UnifiedReturnBlock: ; preds = %Flow3, %Flow2
Revert "StructurizeCFG: Directly invert cmp instructions" This reverts commit r300732. This breaks a few tests. I think the problem is related to adding more uses of the condition that don't yet exist at this point. llvm-svn: 301242
2017-04-25 04:25:01 +08:00
; IR-NEXT: call void @llvm.amdgcn.end.cf(i64 %6)
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
; IR-NEXT: ret void
define amdgpu_kernel void @uniform_complex_multi_ret_nest_in_divergent_triangle(i32 %arg0) #0 {
entry:
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%divergent.cond0 = icmp eq i32 %id.x, 0
br i1 %divergent.cond0, label %uniform.multi.exit.region, label %divergent.ret
uniform.multi.exit.region:
%uniform.cond0 = icmp eq i32 %arg0, 4
br i1 %uniform.cond0, label %uniform.if, label %uniform.ret1
uniform.if:
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%sgpr0 = load volatile i32, i32 addrspace(4)* undef
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
%uniform.cond1 = icmp slt i32 %sgpr0, 1
br i1 %uniform.cond1, label %uniform.then, label %uniform.endif
uniform.then:
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%sgpr1 = load volatile i32, i32 addrspace(4)* undef
AMDGPU: Unify divergent function exits. StructurizeCFG can't handle cases with multiple returns creating regions with multiple exits. Create a copy of UnifyFunctionExitNodes that only unifies exit nodes that skips exit nodes with uniform branch sources. llvm-svn: 298729
2017-03-25 03:52:05 +08:00
%uniform.cond2 = icmp sge i32 %sgpr1, 4
store volatile i32 33, i32 addrspace(1)* undef
br i1 %uniform.cond2, label %uniform.ret0, label %uniform.endif
uniform.endif:
store volatile i32 38, i32 addrspace(1)* undef
br label %uniform.ret0
uniform.ret0:
store volatile i32 11, i32 addrspace(3)* undef
ret void
uniform.ret1:
store volatile i32 42, i32 addrspace(3)* undef
ret void
divergent.ret:
store volatile i32 9, i32 addrspace(1)* undef
ret void
}
; IR-LABEL: @multi_divergent_unreachable_exit(
; IR: UnifiedUnreachableBlock:
; IR-NEXT: call void @llvm.amdgcn.unreachable()
; IR-NEXT: br label %UnifiedReturnBlock
; IR: UnifiedReturnBlock:
; IR-NEXT: call void @llvm.amdgcn.end.cf(i64
; IR-NEXT: ret void
define amdgpu_kernel void @multi_divergent_unreachable_exit() #0 {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
switch i32 %tmp, label %bb3 [
i32 2, label %bb1
i32 0, label %bb2
]
bb1: ; preds = %bb
unreachable
bb2: ; preds = %bb
unreachable
bb3: ; preds = %bb
switch i32 undef, label %bb5 [
i32 2, label %bb4
]
bb4: ; preds = %bb3
ret void
bb5: ; preds = %bb3
unreachable
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }