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/ARM/fcmp-xo.ll

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

101 lines
3.4 KiB
LLVM
Raw Normal View History

[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=thumbv7m-arm-none-eabi -mattr=+execute-only,+fp-armv8 | FileCheck %s --check-prefixes=CHECK,VMOVSR
; RUN: llc < %s -mtriple=thumbv7m-arm-none-eabi -mattr=+execute-only,+fp-armv8,+neon,+neonfp | FileCheck %s --check-prefixes=CHECK,NEON
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
define arm_aapcs_vfpcc float @foo0(float %a0) local_unnamed_addr {
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-LABEL: foo0:
; CHECK: @ %bb.0:
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; CHECK-NEXT: vcmp.f32 s0, #0
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vmov.f32 s2, #5.000000e-01
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmrs APSR_nzcv, fpscr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vmov.f32 s4, #-5.000000e-01
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: it mi
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vmovmi.f32 s2, s4
; CHECK-NEXT: vmov.f32 s0, s2
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: bx lr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
%1 = fcmp nsz olt float %a0, 0.000000e+00
[ARM] Support float literals under XO Follow up patch of r328313 to support the UseVMOVSR constraint. Removed some unneeded instructions from the test and removed some stray comments. Differential Revision: https://reviews.llvm.org/D44941 llvm-svn: 328691
2018-03-28 18:02:26 +08:00
%2 = select i1 %1, float -5.000000e-01, float 5.000000e-01
ret float %2
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
}
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
define arm_aapcs_vfpcc float @float1(float %a0) local_unnamed_addr {
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-LABEL: float1:
; CHECK: @ %bb.0: @ %.end
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vmov.f32 s2, #1.000000e+00
; CHECK-NEXT: vmov.f32 s4, #5.000000e-01
; CHECK-NEXT: vmov.f32 s6, #-5.000000e-01
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; CHECK-NEXT: vcmp.f32 s2, s0
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmrs APSR_nzcv, fpscr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vselgt.f32 s0, s6, s4
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: bx lr
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
br i1 undef, label %.end, label %1
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
%2 = fcmp nsz olt float %a0, 1.000000e+00
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
%3 = select i1 %2, float -5.000000e-01, float 5.000000e-01
br label %.end
.end:
[ARM] Support float literals under XO Follow up patch of r328313 to support the UseVMOVSR constraint. Removed some unneeded instructions from the test and removed some stray comments. Differential Revision: https://reviews.llvm.org/D44941 llvm-svn: 328691
2018-03-28 18:02:26 +08:00
%4 = phi float [ undef, %0 ], [ %3, %1]
ret float %4
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
}
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
define arm_aapcs_vfpcc float @float128(float %a0) local_unnamed_addr {
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; VMOVSR-LABEL: float128:
; VMOVSR: @ %bb.0:
; VMOVSR-NEXT: mov.w r0, #1124073472
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; VMOVSR-NEXT: vmov.f32 s4, #5.000000e-01
; VMOVSR-NEXT: vmov s2, r0
; VMOVSR-NEXT: vmov.f32 s6, #-5.000000e-01
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; VMOVSR-NEXT: vcmp.f32 s2, s0
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; VMOVSR-NEXT: vmrs APSR_nzcv, fpscr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; VMOVSR-NEXT: vselgt.f32 s0, s6, s4
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; VMOVSR-NEXT: bx lr
;
; NEON-LABEL: float128:
; NEON: @ %bb.0:
; NEON-NEXT: mov.w r0, #1124073472
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; NEON-NEXT: vmov.f32 s2, #5.000000e-01
; NEON-NEXT: vmov d3, r0, r0
; NEON-NEXT: vmov.f32 s4, #-5.000000e-01
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; NEON-NEXT: vcmp.f32 s6, s0
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; NEON-NEXT: vmrs APSR_nzcv, fpscr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; NEON-NEXT: vselgt.f32 s0, s4, s2
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; NEON-NEXT: bx lr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
%1 = fcmp nsz olt float %a0, 128.000000e+00
[ARM] Support float literals under XO Follow up patch of r328313 to support the UseVMOVSR constraint. Removed some unneeded instructions from the test and removed some stray comments. Differential Revision: https://reviews.llvm.org/D44941 llvm-svn: 328691
2018-03-28 18:02:26 +08:00
%2 = select i1 %1, float -5.000000e-01, float 5.000000e-01
ret float %2
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
}
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
define arm_aapcs_vfpcc double @double1(double %a0) local_unnamed_addr {
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-LABEL: double1:
; CHECK: @ %bb.0:
; CHECK-NEXT: vmov.f64 d18, #1.000000e+00
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; CHECK-NEXT: vcmp.f64 d18, d0
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmrs APSR_nzcv, fpscr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: vmov.f64 d16, #5.000000e-01
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmov.f64 d17, #-5.000000e-01
; CHECK-NEXT: vselgt.f64 d0, d17, d16
; CHECK-NEXT: bx lr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
%1 = fcmp nsz olt double %a0, 1.000000e+00
[ARM] Support float literals under XO Follow up patch of r328313 to support the UseVMOVSR constraint. Removed some unneeded instructions from the test and removed some stray comments. Differential Revision: https://reviews.llvm.org/D44941 llvm-svn: 328691
2018-03-28 18:02:26 +08:00
%2 = select i1 %1, double -5.000000e-01, double 5.000000e-01
ret double %2
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
}
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
define arm_aapcs_vfpcc double @double128(double %a0) local_unnamed_addr {
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-LABEL: double128:
; CHECK: @ %bb.0:
; CHECK-NEXT: movs r0, #0
; CHECK-NEXT: movs r1, #0
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
; CHECK-NEXT: movt r0, #16480
; CHECK-NEXT: vmov.f64 d16, #5.000000e-01
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmov d18, r1, r0
[ARM] Generate vcmp instead of vcmpe Based on the discussion in http://lists.llvm.org/pipermail/llvm-dev/2019-October/135574.html, the conclusion was reached that the ARM backend should produce vcmp instead of vcmpe instructions by default, i.e. not be producing an Invalid Operation exception when either arguments in a floating point compare are quiet NaNs. In the future, after constrained floating point intrinsics for floating point compare have been introduced, vcmpe instructions probably should be produced for those intrinsics - depending on the exact semantics they'll be defined to have. This patch logically consists of the following parts: - Revert http://llvm.org/viewvc/llvm-project?rev=294945&view=rev and http://llvm.org/viewvc/llvm-project?rev=294968&view=rev, which implemented fine-tuning for when to produce vcmpe (i.e. not do it for equality comparisons). The complexity introduced by those patches isn't needed anymore if we just always produce vcmp instead. Maybe these patches need to be reintroduced again once support is needed to map potential LLVM-IR constrained floating point compare intrinsics to the ARM instruction set. - Simply select vcmp, instead of vcmpe, see simple changes in lib/Target/ARM/ARMInstrVFP.td - Adapt lots of tests that tested for vcmpe (instead of vcmp). For all of these test, the intent of what is tested for isn't related to whether the vcmp should produce an Invalid Operation exception or not. Fixes PR43374. Differential Revision: https://reviews.llvm.org/D68463 llvm-svn: 374025
2019-10-08 16:25:42 +08:00
; CHECK-NEXT: vcmp.f64 d18, d0
[ARM] Regenerate execute-only float comparison tests Prep work for PR40800 (Add UNDEF handling to SelectionDAG::FoldSetCC) llvm-svn: 357293
2019-03-30 02:21:19 +08:00
; CHECK-NEXT: vmrs APSR_nzcv, fpscr
; CHECK-NEXT: vmov.f64 d17, #-5.000000e-01
; CHECK-NEXT: vselgt.f64 d0, d17, d16
; CHECK-NEXT: bx lr
[SelectionDAG] Add fcmp UNDEF handling to SelectionDAG::FoldSetCC Second half of PR40800, this patch adds DAG undef handling to fcmp instructions to match the behavior in llvm::ConstantFoldCompareInstruction, this permits constant folding of vector comparisons where some elements had been reduced to UNDEF (by SimplifyDemandedVectorElts etc.). This involves a lot of tweaking to reduced tests as bugpoint loves to reduce fcmp arguments to undef........ Differential Revision: https://reviews.llvm.org/D60006 llvm-svn: 357765
2019-04-05 22:56:21 +08:00
%1 = fcmp nsz olt double %a0, 128.000000e+00
[ARM] Support float literals under XO Follow up patch of r328313 to support the UseVMOVSR constraint. Removed some unneeded instructions from the test and removed some stray comments. Differential Revision: https://reviews.llvm.org/D44941 llvm-svn: 328691
2018-03-28 18:02:26 +08:00
%2 = select i1 %1, double -5.000000e-01, double 5.000000e-01
ret double %2
[ARM] Support float literals under XO When targeting execute-only and fp-armv8, float constants in a compare resulted in instruction selection failures. This is now fixed by using vmov.f32 where possible, otherwise the floating point constant is lowered into a integer constant that is moved into a floating point register. This patch also restores using fpcmp with immediate 0 under fp-armv8. Change-Id: Ie87229706f4ed879a0c0cf66631b6047ed6c6443 llvm-svn: 328313
2018-03-23 21:02:03 +08:00
}