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/loop_break.ll

336 lines
12 KiB
LLVM
Raw Normal View History

AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=OPT %s
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; Uses llvm.amdgcn.break
; OPT-LABEL: @break_loop(
; OPT: bb1:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT: icmp slt i32
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT: load volatile
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT: icmp slt i32
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
; OPT: xor i1 %cmp1
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
; OPT: br label %Flow
; OPT: Flow:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT: call i64 @llvm.amdgcn.if.break(
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
; OPT: call i1 @llvm.amdgcn.loop(i64
; OPT: br i1 %{{[0-9]+}}, label %bb9, label %bb1
; OPT: bb9:
; OPT: call void @llvm.amdgcn.end.cf(i64
; GCN-LABEL: {{^}}break_loop:
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: s_mov_b64 [[OUTER_MASK:s\[[0-9]+:[0-9]+\]]], 0{{$}}
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
; GCN: [[LOOP_ENTRY:BB[0-9]+_[0-9]+]]: ; %bb1
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: v_cmp_lt_i32_e32 vcc, -1
; GCN: s_and_b64 vcc, exec, vcc
; GCN: s_or_b64 [[INNER_MASK:s\[[0-9]+:[0-9]+\]]], [[INNER_MASK]], exec
; GCN: s_cbranch_vccnz [[FLOW:BB[0-9]+_[0-9]+]]
; GCN: ; %bb4
; GCN: buffer_load_dword
; GCN: v_cmp_ge_i32_e32 vcc,
; GCN: s_andn2_b64 [[INNER_MASK]], [[INNER_MASK]], exec
; GCN: s_and_b64 [[TMP0:s\[[0-9]+:[0-9]+\]]], vcc, exec
; GCN: s_or_b64 [[INNER_MASK]], [[INNER_MASK]], [[TMP0]]
; GCN: [[FLOW]]: ; %Flow
; GCN: s_and_b64 [[TMP1:s\[[0-9]+:[0-9]+\]]], exec, [[INNER_MASK]]
; GCN: s_or_b64 [[TMP1]], [[TMP1]], [[OUTER_MASK]]
; GCN: s_mov_b64 [[OUTER_MASK]], [[TMP1]]
; GCN: s_andn2_b64 exec, exec, [[TMP1]]
; GCN-NEXT: s_cbranch_execnz [[LOOP_ENTRY]]
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; GCN: ; %bb.4: ; %bb9
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +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 @break_loop(i32 %arg) #0 {
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1:
%lsr.iv = phi i32 [ undef, %bb ], [ %lsr.iv.next, %bb4 ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %bb9
bb4:
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp slt i32 %tmp, %load
br i1 %cmp1, label %bb1, label %bb9
bb9:
ret void
}
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-LABEL: @undef_phi_cond_break_loop(
; OPT: bb1:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %phi.broken = phi i64 [ %0, %Flow ], [ 0, %bb ]
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %lsr.iv.next = add i32 %lsr.iv, 1
; OPT-NEXT: %cmp0 = icmp slt i32 %lsr.iv.next, 0
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %0 = call i64 @llvm.amdgcn.if.break(i1 %tmp3, i64 %phi.broken)
; OPT-NEXT: %1 = call i1 @llvm.amdgcn.loop(i64 %0)
; OPT-NEXT: br i1 %1, label %bb9, label %bb1
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT: bb9: ; preds = %Flow
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %0)
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
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 @undef_phi_cond_break_loop(i32 %arg) #0 {
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ undef, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; FIXME: ConstantExpr compare of address to null folds away
@lds = addrspace(3) global i32 undef
; OPT-LABEL: @constexpr_phi_cond_break_loop(
; OPT: bb1:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %phi.broken = phi i64 [ %0, %Flow ], [ 0, %bb ]
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %lsr.iv.next = add i32 %lsr.iv, 1
; OPT-NEXT: %cmp0 = icmp slt i32 %lsr.iv.next, 0
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ icmp ne (i32 addrspace(3)* inttoptr (i32 4 to i32 addrspace(3)*), i32 addrspace(3)* @lds), %bb1 ]
; OPT-NEXT: %0 = call i64 @llvm.amdgcn.if.break(i1 %tmp3, i64 %phi.broken)
; OPT-NEXT: %1 = call i1 @llvm.amdgcn.loop(i64 %0)
; OPT-NEXT: br i1 %1, label %bb9, label %bb1
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT: bb9: ; preds = %Flow
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %0)
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
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 @constexpr_phi_cond_break_loop(i32 %arg) #0 {
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ icmp ne (i32 addrspace(3)* inttoptr (i32 4 to i32 addrspace(3)*), i32 addrspace(3)* @lds), %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; OPT-LABEL: @true_phi_cond_break_loop(
; OPT: bb1:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %phi.broken = phi i64 [ %0, %Flow ], [ 0, %bb ]
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %lsr.iv.next = add i32 %lsr.iv, 1
; OPT-NEXT: %cmp0 = icmp slt i32 %lsr.iv.next, 0
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
; OPT-NEXT: %0 = call i64 @llvm.amdgcn.if.break(i1 %tmp3, i64 %phi.broken)
; OPT-NEXT: %1 = call i1 @llvm.amdgcn.loop(i64 %0)
; OPT-NEXT: br i1 %1, label %bb9, label %bb1
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT: bb9: ; preds = %Flow
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %0)
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
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 @true_phi_cond_break_loop(i32 %arg) #0 {
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; OPT-LABEL: @false_phi_cond_break_loop(
; OPT: bb1:
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %phi.broken = phi i64 [ %0, %Flow ], [ 0, %bb ]
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT-NOT: call
; OPT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ false, %bb1 ]
; OPT-NEXT: %0 = call i64 @llvm.amdgcn.if.break(i1 %tmp3, i64 %phi.broken)
; OPT-NEXT: %1 = call i1 @llvm.amdgcn.loop(i64 %0)
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: br i1 %1, label %bb9, label %bb1
; OPT: bb9: ; preds = %Flow
AMDGPU: Remove PHI loop condition optimization Summary: The optimization to early break out of loops if all threads are dead was never fully implemented. But the PHI node analyzing is actually causing a number of problems, so remove all the extra code for it. (This does actually regress code quality in a few places because it ends up relying more heavily on phi's of i1, which we don't do a great job with. However, since it fixes real bugs in the wild, we should take this change. I have some prototype changes to improve i1 lowering in general -- not just for control flow -- which should help recover the code quality, I just need to make those changes fit for general consumption. -- Nicolai) Change-Id: I6fc6c6c8961857ac6009fcfb9f7e5e48dc23fbb1 Patch-by: Christian König <christian.koenig@amd.com> Reviewers: arsenm, rampitec, tpr Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D53359 llvm-svn: 345718
2018-10-31 21:26:48 +08:00
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %0)
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
; OPT-NEXT: store volatile i32 7
; OPT-NEXT: ret void
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 @false_phi_cond_break_loop(i32 %arg) #0 {
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ false, %bb1 ]
br i1 %tmp3, label %bb9, label %bb1
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
; Swap order of branches in flow block so that the true phi is
; continue.
; OPT-LABEL: @invert_true_phi_cond_break_loop(
; OPT: bb1:
; OPT-NEXT: %phi.broken = phi i64 [ %1, %Flow ], [ 0, %bb ]
; OPT-NEXT: %lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
; OPT-NEXT: %lsr.iv.next = add i32 %lsr.iv, 1
; OPT-NEXT: %cmp0 = icmp slt i32 %lsr.iv.next, 0
; OPT-NEXT: br i1 %cmp0, label %bb4, label %Flow
; OPT: bb4:
; OPT-NEXT: %load = load volatile i32, i32 addrspace(1)* undef, align 4
; OPT-NEXT: %cmp1 = icmp sge i32 %tmp, %load
; OPT-NEXT: br label %Flow
; OPT: Flow:
; OPT-NEXT: %tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
; OPT-NEXT: %tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
; OPT-NEXT: %0 = xor i1 %tmp3, true
; OPT-NEXT: %1 = call i64 @llvm.amdgcn.if.break(i1 %0, i64 %phi.broken)
; OPT-NEXT: %2 = call i1 @llvm.amdgcn.loop(i64 %1)
; OPT-NEXT: br i1 %2, label %bb9, label %bb1
; OPT: bb9:
; OPT-NEXT: call void @llvm.amdgcn.end.cf(i64 %1)
; OPT-NEXT: store volatile i32 7, i32 addrspace(3)* undef
; OPT-NEXT: ret void
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 @invert_true_phi_cond_break_loop(i32 %arg) #0 {
AMDGPU: Fix handling of constant phi input loop conditions If the loop condition was an i1 phi with a constantexpr input, this would add a loop intrinsic fed by a phi dependent on a call to if.break in the same block. Insert the call in the loop header. llvm-svn: 298121
2017-03-18 04:52:21 +08:00
bb:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%tmp = sub i32 %id, %arg
br label %bb1
bb1: ; preds = %Flow, %bb
%lsr.iv = phi i32 [ undef, %bb ], [ %tmp2, %Flow ]
%lsr.iv.next = add i32 %lsr.iv, 1
%cmp0 = icmp slt i32 %lsr.iv.next, 0
br i1 %cmp0, label %bb4, label %Flow
bb4: ; preds = %bb1
%load = load volatile i32, i32 addrspace(1)* undef, align 4
%cmp1 = icmp sge i32 %tmp, %load
br label %Flow
Flow: ; preds = %bb4, %bb1
%tmp2 = phi i32 [ %lsr.iv.next, %bb4 ], [ undef, %bb1 ]
%tmp3 = phi i1 [ %cmp1, %bb4 ], [ true, %bb1 ]
br i1 %tmp3, label %bb1, label %bb9
bb9: ; preds = %Flow
store volatile i32 7, i32 addrspace(3)* undef
ret void
}
AMDGPU: Add missing test coverage for control flow breaks None of the current lit tests hit si_break handling. llvm-svn: 276129
2016-07-20 23:20:35 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }