[llvm] 46bfc2b - [NFC][ARM] Add tests

Sam Parker via llvm-commits llvm-commits at lists.llvm.org
Fri Feb 28 03:24:19 PST 2020


Author: Sam Parker
Date: 2020-02-28T11:24:02Z
New Revision: 46bfc2bc01e01013522075271531c1687ea4f468

URL: https://github.com/llvm/llvm-project/commit/46bfc2bc01e01013522075271531c1687ea4f468
DIFF: https://github.com/llvm/llvm-project/commit/46bfc2bc01e01013522075271531c1687ea4f468.diff

LOG: [NFC][ARM] Add tests

Added: 
    llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir
    llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-cond-iter-count.mir

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir
new file mode 100644
index 000000000000..9cedc94ab98a
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-block-cond-iter-count.mir
@@ -0,0 +1,456 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
+
+--- |
+  define dso_local arm_aapcs_vfpcc void @multi_cond_iter_count(i32* nocapture %0, i32* nocapture readonly %1, i32 %2, i32 %3) local_unnamed_addr #0 {
+    %5 = icmp eq i32 %3, 2
+    %6 = select i1 %5, i32 2, i32 4
+    %7 = icmp eq i32 %3, 4
+    %8 = select i1 %7, i32 1, i32 %6
+    %9 = shl i32 %2, %8
+    %10 = icmp eq i32 %9, 0
+    br i1 %10, label %64, label %11
+
+  11:                                               ; preds = %4
+    %12 = getelementptr i32, i32* %0, i32 %9
+    %13 = getelementptr i32, i32* %1, i32 %9
+    %14 = icmp ugt i32* %13, %0
+    %15 = icmp ugt i32* %12, %1
+    %16 = and i1 %14, %15
+    %17 = add i32 %9, 3
+    %18 = lshr i32 %17, 2
+    %19 = shl nuw i32 %18, 2
+    %20 = add i32 %19, -4
+    %21 = lshr i32 %20, 2
+    %22 = add nuw nsw i32 %21, 1
+    br i1 %16, label %23, label %32
+
+  23:                                               ; preds = %11
+    %24 = add i32 %9, -1
+    %25 = and i32 %9, 2
+    %26 = icmp ult i32 %24, 3
+    %27 = add i32 %9, -4
+    %28 = sub i32 %27, %25
+    %29 = lshr i32 %28, 2
+    %30 = add nuw nsw i32 %29, 1
+    br i1 %26, label %49, label %31
+
+  31:                                               ; preds = %23
+    call void @llvm.set.loop.iterations.i32(i32 %30)
+    br label %65
+
+  32:                                               ; preds = %11
+    call void @llvm.set.loop.iterations.i32(i32 %22)
+    br label %33
+
+  33:                                               ; preds = %33, %32
+    %34 = phi i32* [ %46, %33 ], [ %0, %32 ]
+    %35 = phi i32* [ %45, %33 ], [ %1, %32 ]
+    %36 = phi i32 [ %22, %32 ], [ %47, %33 ]
+    %37 = phi i32 [ %9, %32 ], [ %41, %33 ]
+    %38 = bitcast i32* %34 to <4 x i32>*
+    %39 = bitcast i32* %35 to <4 x i32>*
+    %40 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %37)
+    %41 = sub i32 %37, 4
+    %42 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %39, i32 4, <4 x i1> %40, <4 x i32> undef)
+    %43 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %38, i32 4, <4 x i1> %40, <4 x i32> undef)
+    %44 = mul nsw <4 x i32> %43, %42
+    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %44, <4 x i32>* %38, i32 4, <4 x i1> %40)
+    %45 = getelementptr i32, i32* %35, i32 4
+    %46 = getelementptr i32, i32* %34, i32 4
+    %47 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %36, i32 1)
+    %48 = icmp ne i32 %47, 0
+    br i1 %48, label %33, label %64
+
+  49:                                               ; preds = %65, %23
+    %50 = phi i32 [ 0, %23 ], [ %107, %65 ]
+    %51 = icmp eq i32 %25, 0
+    br i1 %51, label %64, label %52
+
+  52:                                               ; preds = %49
+    %53 = getelementptr inbounds i32, i32* %1, i32 %50
+    %54 = load i32, i32* %53, align 4
+    %55 = getelementptr inbounds i32, i32* %0, i32 %50
+    %56 = load i32, i32* %55, align 4
+    %57 = mul nsw i32 %56, %54
+    store i32 %57, i32* %55, align 4
+    %58 = add nuw i32 %50, 1
+    %59 = getelementptr inbounds i32, i32* %1, i32 %58
+    %60 = load i32, i32* %59, align 4
+    %61 = getelementptr inbounds i32, i32* %0, i32 %58
+    %62 = load i32, i32* %61, align 4
+    %63 = mul nsw i32 %62, %60
+    store i32 %63, i32* %61, align 4
+    br label %64
+
+  64:                                               ; preds = %33, %52, %49, %4
+    ret void
+
+  65:                                               ; preds = %65, %31
+    %66 = phi i32 [ %108, %65 ], [ 0, %31 ]
+    %67 = phi i32 [ 0, %31 ], [ %107, %65 ]
+    %68 = phi i32 [ %30, %31 ], [ %109, %65 ]
+    %69 = bitcast i32* %0 to i8*
+    %70 = bitcast i32* %1 to i8*
+    %71 = getelementptr i8, i8* %70, i32 %66
+    %72 = bitcast i8* %71 to i32*
+    %73 = bitcast i32* %72 to i32*
+    %74 = load i32, i32* %73, align 4
+    %75 = getelementptr i8, i8* %69, i32 %66
+    %76 = bitcast i8* %75 to i32*
+    %77 = bitcast i32* %76 to i32*
+    %78 = load i32, i32* %77, align 4
+    %79 = mul nsw i32 %78, %74
+    store i32 %79, i32* %77, align 4
+    %80 = getelementptr i8, i8* %70, i32 %66
+    %81 = bitcast i8* %80 to i32*
+    %82 = getelementptr i32, i32* %81, i32 1
+    %83 = load i32, i32* %82, align 4
+    %84 = getelementptr i8, i8* %69, i32 %66
+    %85 = bitcast i8* %84 to i32*
+    %86 = getelementptr i32, i32* %85, i32 1
+    %87 = load i32, i32* %86, align 4
+    %88 = mul nsw i32 %87, %83
+    store i32 %88, i32* %86, align 4
+    %89 = getelementptr i8, i8* %70, i32 %66
+    %90 = bitcast i8* %89 to i32*
+    %91 = getelementptr i32, i32* %90, i32 2
+    %92 = load i32, i32* %91, align 4
+    %93 = getelementptr i8, i8* %69, i32 %66
+    %94 = bitcast i8* %93 to i32*
+    %95 = getelementptr i32, i32* %94, i32 2
+    %96 = load i32, i32* %95, align 4
+    %97 = mul nsw i32 %96, %92
+    store i32 %97, i32* %95, align 4
+    %98 = getelementptr i8, i8* %70, i32 %66
+    %99 = bitcast i8* %98 to i32*
+    %100 = getelementptr i32, i32* %99, i32 3
+    %101 = load i32, i32* %100, align 4
+    %102 = getelementptr i8, i8* %69, i32 %66
+    %103 = bitcast i8* %102 to i32*
+    %104 = getelementptr i32, i32* %103, i32 3
+    %105 = load i32, i32* %104, align 4
+    %106 = mul nsw i32 %105, %101
+    store i32 %106, i32* %104, align 4
+    %107 = add nuw i32 %67, 4
+    %108 = add i32 %66, 16
+    %109 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %68, i32 1)
+    %110 = icmp ne i32 %109, 0
+    br i1 %110, label %65, label %49
+  }
+
+  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #1
+  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #2
+  declare void @llvm.set.loop.iterations.i32(i32) #3
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32) #3
+  declare <4 x i1> @llvm.arm.mve.vctp32(i32) #4
+
+...
+---
+name:            multi_cond_iter_count
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+  - { reg: '$r3', virtual-reg: '' }
+frameInfo:
+  stackSize:       32
+  offsetAdjustment: -24
+  maxAlignment:    4
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 2, name: '', type: spill-slot, offset: -12, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r6', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 3, name: '', type: spill-slot, offset: -16, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 4, name: '', type: spill-slot, offset: -20, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 5, name: '', type: spill-slot, offset: -24, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r10', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 6, name: '', type: spill-slot, offset: -28, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r9', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 7, name: '', type: spill-slot, offset: -32, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r8', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: multi_cond_iter_count
+  ; CHECK: bb.0 (%ir-block.4):
+  ; CHECK:   successors: %bb.4(0x30000000), %bb.1(0x50000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r4, $r5, $r6, $r8, $r9, $r10
+  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 20
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r6, -12
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r5, -16
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r4, -20
+  ; CHECK:   dead $r7 = frame-setup tADDrSPi $sp, 3, 14 /* CC::al */, $noreg
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa $r7, 8
+  ; CHECK:   $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r8, killed $r9, killed $r10
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r10, -24
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r9, -28
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r8, -32
+  ; CHECK:   tCMPi8 renamable $r3, 2, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   $r12 = tMOVr $r3, 14 /* CC::al */, $noreg
+  ; CHECK:   t2IT 1, 8, implicit-def $itstate
+  ; CHECK:   $r12 = t2MOVi 4, 1 /* CC::ne */, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+  ; CHECK:   tCMPi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 0, 8, implicit-def $itstate
+  ; CHECK:   $r12 = t2MOVi 1, 0 /* CC::eq */, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+  ; CHECK:   renamable $r3 = t2LSLrr killed renamable $r2, killed renamable $r12, 14 /* CC::al */, $noreg, def $cpsr
+  ; CHECK:   tBcc %bb.4, 0 /* CC::eq */, killed $cpsr
+  ; CHECK: bb.1 (%ir-block.11):
+  ; CHECK:   successors: %bb.2(0x55555555), %bb.5(0x2aaaaaab)
+  ; CHECK:   liveins: $r0, $r1, $r3
+  ; CHECK:   renamable $r2 = t2ADDrs renamable $r1, renamable $r3, 18, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   tCMPr killed renamable $r2, renamable $r0, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 8, 4, implicit-def $itstate
+  ; CHECK:   renamable $r2 = t2ADDrs renamable $r0, renamable $r3, 18, 8 /* CC::hi */, $cpsr, $noreg, implicit $itstate
+  ; CHECK:   tCMPr killed renamable $r2, renamable $r1, 8 /* CC::hi */, killed $cpsr, implicit-def $cpsr, implicit killed $itstate
+  ; CHECK:   tBcc %bb.5, 8 /* CC::hi */, killed $cpsr
+  ; CHECK: bb.2 (%ir-block.32):
+  ; CHECK:   successors: %bb.3(0x80000000)
+  ; CHECK:   liveins: $r0, $r1, $r3
+  ; CHECK:   $r2 = tMOVr $r0, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r3
+  ; CHECK: bb.3 (%ir-block.33):
+  ; CHECK:   successors: %bb.3(0x7c000000), %bb.4(0x04000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2
+  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg
+  ; CHECK:   renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 0, $noreg
+  ; CHECK:   renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 0, killed $noreg
+  ; CHECK:   $r0 = tMOVr $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.3
+  ; CHECK: bb.4 (%ir-block.64):
+  ; CHECK:   $sp = t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r8, def $r9, def $r10
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
+  ; CHECK: bb.5 (%ir-block.23):
+  ; CHECK:   successors: %bb.6(0x40000000), %bb.7(0x40000000)
+  ; CHECK:   liveins: $r0, $r1, $r3
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi3 renamable $r3, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r12 = t2ANDri renamable $r3, 2, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   tCMPi8 killed renamable $r2, 3, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   tBcc %bb.7, 2 /* CC::hs */, killed $cpsr
+  ; CHECK: bb.6:
+  ; CHECK:   successors: %bb.9(0x80000000)
+  ; CHECK:   liveins: $r0, $r1, $r12
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
+  ; CHECK:   tB %bb.9, 14 /* CC::al */, $noreg
+  ; CHECK: bb.7 (%ir-block.31):
+  ; CHECK:   successors: %bb.8(0x80000000)
+  ; CHECK:   liveins: $r0, $r1, $r3, $r12
+  ; CHECK:   renamable $r2 = t2BICri killed renamable $r3, 2, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r2, 19, 14 /* CC::al */, $noreg, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = tMOVi8 0, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = t2DLS killed renamable $lr
+  ; CHECK: bb.8 (%ir-block.65):
+  ; CHECK:   successors: %bb.8(0x7c000000), %bb.9(0x04000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3, $r12
+  ; CHECK:   renamable $r4 = tLDRr renamable $r1, $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r3, dead $cpsr = nuw tADDi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r5 = tLDRr renamable $r0, $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r4, dead $cpsr = nsw tMUL killed renamable $r5, killed renamable $r4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r5, dead $cpsr = tADDrr renamable $r0, renamable $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   $r10, $r8 = t2LDRDi8 $r5, 4, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r9 = t2LDRi12 renamable $r5, 12, 14 /* CC::al */, $noreg
+  ; CHECK:   tSTRr killed renamable $r4, renamable $r0, $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tADDi8 killed renamable $r2, 16, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r6 = tLDRi renamable $r4, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r6 = nsw t2MUL killed renamable $r10, killed renamable $r6, 14 /* CC::al */, $noreg
+  ; CHECK:   tSTRi killed renamable $r6, renamable $r5, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r6 = tLDRi renamable $r4, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r6 = nsw t2MUL killed renamable $r8, killed renamable $r6, 14 /* CC::al */, $noreg
+  ; CHECK:   tSTRi killed renamable $r6, renamable $r5, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r4 = tLDRi killed renamable $r4, 3, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r4 = nsw t2MUL killed renamable $r9, killed renamable $r4, 14 /* CC::al */, $noreg
+  ; CHECK:   tSTRi killed renamable $r4, killed renamable $r5, 3, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = t2LEUpdate killed renamable $lr, %bb.8
+  ; CHECK: bb.9 (%ir-block.49):
+  ; CHECK:   successors: %bb.4(0x40000000), %bb.10(0x40000000)
+  ; CHECK:   liveins: $r0, $r1, $r3, $r12
+  ; CHECK:   t2CMPri killed renamable $r12, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   tBcc %bb.4, 0 /* CC::eq */, killed $cpsr
+  ; CHECK: bb.10 (%ir-block.52):
+  ; CHECK:   liveins: $r0, $r1, $r3
+  ; CHECK:   renamable $r12 = t2LDRs renamable $r1, renamable $r3, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2 = t2LDRs renamable $r0, renamable $r3, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r12 = nsw t2MUL killed renamable $r2, killed renamable $r12, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r2, dead $cpsr = tADDi3 renamable $r3, 1, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $lr = t2LDRs renamable $r0, renamable $r2, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   t2STRs killed renamable $r12, renamable $r0, killed renamable $r3, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r1 = t2LDRs killed renamable $r1, renamable $r2, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   renamable $r1 = nsw t2MUL killed renamable $lr, killed renamable $r1, 14 /* CC::al */, $noreg
+  ; CHECK:   t2STRs killed renamable $r1, killed renamable $r0, killed renamable $r2, 2, 14 /* CC::al */, $noreg
+  ; CHECK:   $sp = t2LDMIA_UPD $sp, 14 /* CC::al */, $noreg, def $r8, def $r9, def $r10
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
+  bb.0 (%ir-block.4):
+    successors: %bb.4(0x30000000), %bb.1(0x50000000)
+    liveins: $r0, $r1, $r2, $r3, $r4, $r5, $r6, $lr, $r8, $r9, $r10
+
+    frame-setup tPUSH 14, $noreg, killed $r4, killed $r5, killed $r6, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 20
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    frame-setup CFI_INSTRUCTION offset $r6, -12
+    frame-setup CFI_INSTRUCTION offset $r5, -16
+    frame-setup CFI_INSTRUCTION offset $r4, -20
+    $r7 = frame-setup tADDrSPi $sp, 3, 14, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa $r7, 8
+    $sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r8, killed $r9, killed $r10
+    frame-setup CFI_INSTRUCTION offset $r10, -24
+    frame-setup CFI_INSTRUCTION offset $r9, -28
+    frame-setup CFI_INSTRUCTION offset $r8, -32
+    tCMPi8 renamable $r3, 2, 14, $noreg, implicit-def $cpsr
+    $r12 = tMOVr $r3, 14, $noreg
+    t2IT 1, 8, implicit-def $itstate
+    $r12 = t2MOVi 4, 1, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+    tCMPi8 killed renamable $r3, 4, 14, $noreg, implicit-def $cpsr
+    t2IT 0, 8, implicit-def $itstate
+    $r12 = t2MOVi 1, 0, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+    renamable $r3 = t2LSLrr killed renamable $r2, killed renamable $r12, 14, $noreg, def $cpsr
+    tBcc %bb.4, 0, killed $cpsr
+
+  bb.1 (%ir-block.11):
+    successors: %bb.2(0x80000000), %bb.5(0x40000000)
+    liveins: $r0, $r1, $r3
+
+    renamable $r2 = t2ADDrs renamable $r1, renamable $r3, 18, 14, $noreg, $noreg
+    tCMPr killed renamable $r2, renamable $r0, 14, $noreg, implicit-def $cpsr
+    t2IT 8, 4, implicit-def $itstate
+    renamable $r2 = t2ADDrs renamable $r0, renamable $r3, 18, 8, $cpsr, $noreg, implicit $itstate
+    tCMPr killed renamable $r2, renamable $r1, 8, killed $cpsr, implicit-def $cpsr, implicit killed $itstate
+    tBcc %bb.5, 8, killed $cpsr
+
+  bb.2 (%ir-block.32):
+    successors: %bb.3(0x80000000)
+    liveins: $r0, $r1, $r3
+
+    renamable $r2, dead $cpsr = tADDi3 renamable $r3, 3, 14, $noreg
+    renamable $r2 = t2BICri killed renamable $r2, 3, 14, $noreg, $noreg
+    renamable $r12 = t2SUBri killed renamable $r2, 4, 14, $noreg, $noreg
+    renamable $r2, dead $cpsr = tMOVi8 1, 14, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $r2, killed renamable $r12, 19, 14, $noreg, $noreg
+    $r2 = tMOVr $r0, 14, $noreg
+    t2DoLoopStart renamable $lr
+
+  bb.3 (%ir-block.33):
+    successors: %bb.3(0x7c000000), %bb.4(0x04000000)
+    liveins: $lr, $r0, $r1, $r2, $r3
+
+    renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg
+    MVE_VPST 4, implicit $vpr
+    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr
+    renamable $r2, renamable $q1 = MVE_VLDRWU32_post killed renamable $r2, 16, 1, renamable $vpr
+    renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14, $noreg
+    renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+    MVE_VPST 8, implicit $vpr
+    MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    $r0 = tMOVr $r2, 14, $noreg
+    t2LoopEnd renamable $lr, %bb.3, implicit-def dead $cpsr
+    tB %bb.4, 14, $noreg
+
+  bb.4 (%ir-block.64):
+    $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r8, def $r9, def $r10
+    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
+
+  bb.5 (%ir-block.23):
+    successors: %bb.6(0x40000000), %bb.7(0x40000000)
+    liveins: $r0, $r1, $r3
+
+    renamable $r2, dead $cpsr = tSUBi3 renamable $r3, 1, 14, $noreg
+    renamable $r12 = t2ANDri renamable $r3, 2, 14, $noreg, $noreg
+    tCMPi8 killed renamable $r2, 3, 14, $noreg, implicit-def $cpsr
+    tBcc %bb.7, 2, killed $cpsr
+
+  bb.6:
+    successors: %bb.9(0x80000000)
+    liveins: $r0, $r1, $r12
+
+    renamable $r3, dead $cpsr = tMOVi8 0, 14, $noreg
+    tB %bb.9, 14, $noreg
+
+  bb.7 (%ir-block.31):
+    successors: %bb.8(0x80000000)
+    liveins: $r0, $r1, $r3, $r12
+
+    renamable $r2 = t2BICri killed renamable $r3, 2, 14, $noreg, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r2, 19, 14, $noreg, $noreg
+    renamable $r2, dead $cpsr = tMOVi8 0, 14, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 0, 14, $noreg
+    t2DoLoopStart renamable $lr
+
+  bb.8 (%ir-block.65):
+    successors: %bb.8(0x7c000000), %bb.9(0x04000000)
+    liveins: $lr, $r0, $r1, $r2, $r3, $r12
+
+    renamable $r4 = tLDRr renamable $r1, $r2, 14, $noreg
+    renamable $r3, dead $cpsr = nuw tADDi8 killed renamable $r3, 4, 14, $noreg
+    renamable $r5 = tLDRr renamable $r0, $r2, 14, $noreg
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    renamable $r4, dead $cpsr = nsw tMUL killed renamable $r5, killed renamable $r4, 14, $noreg
+    renamable $r5, dead $cpsr = tADDrr renamable $r0, renamable $r2, 14, $noreg
+    $r10, $r8 = t2LDRDi8 $r5, 4, 14, $noreg
+    renamable $r9 = t2LDRi12 renamable $r5, 12, 14, $noreg
+    tSTRr killed renamable $r4, renamable $r0, $r2, 14, $noreg
+    renamable $r4, dead $cpsr = tADDrr renamable $r1, renamable $r2, 14, $noreg
+    renamable $r2, dead $cpsr = tADDi8 killed renamable $r2, 16, 14, $noreg
+    renamable $r6 = tLDRi renamable $r4, 1, 14, $noreg
+    renamable $r6 = nsw t2MUL killed renamable $r10, killed renamable $r6, 14, $noreg
+    tSTRi killed renamable $r6, renamable $r5, 1, 14, $noreg
+    renamable $r6 = tLDRi renamable $r4, 2, 14, $noreg
+    renamable $r6 = nsw t2MUL killed renamable $r8, killed renamable $r6, 14, $noreg
+    tSTRi killed renamable $r6, renamable $r5, 2, 14, $noreg
+    renamable $r4 = tLDRi killed renamable $r4, 3, 14, $noreg
+    renamable $r4 = nsw t2MUL killed renamable $r9, killed renamable $r4, 14, $noreg
+    tSTRi killed renamable $r4, killed renamable $r5, 3, 14, $noreg
+    t2LoopEnd renamable $lr, %bb.8, implicit-def dead $cpsr
+    tB %bb.9, 14, $noreg
+
+  bb.9 (%ir-block.49):
+    successors: %bb.4(0x40000000), %bb.10(0x40000000)
+    liveins: $r0, $r1, $r3, $r12
+
+    t2CMPri killed renamable $r12, 0, 14, $noreg, implicit-def $cpsr
+    tBcc %bb.4, 0, killed $cpsr
+
+  bb.10 (%ir-block.52):
+    liveins: $r0, $r1, $r3
+
+    renamable $r12 = t2LDRs renamable $r1, renamable $r3, 2, 14, $noreg
+    renamable $r2 = t2LDRs renamable $r0, renamable $r3, 2, 14, $noreg
+    renamable $r12 = nsw t2MUL killed renamable $r2, killed renamable $r12, 14, $noreg
+    renamable $r2, dead $cpsr = tADDi3 renamable $r3, 1, 14, $noreg
+    renamable $lr = t2LDRs renamable $r0, renamable $r2, 2, 14, $noreg
+    t2STRs killed renamable $r12, renamable $r0, killed renamable $r3, 2, 14, $noreg
+    renamable $r1 = t2LDRs killed renamable $r1, renamable $r2, 2, 14, $noreg
+    renamable $r1 = nsw t2MUL killed renamable $lr, killed renamable $r1, 14, $noreg
+    t2STRs killed renamable $r1, killed renamable $r0, killed renamable $r2, 2, 14, $noreg
+    $sp = t2LDMIA_UPD $sp, 14, $noreg, def $r8, def $r9, def $r10
+    tPOP_RET 14, $noreg, def $r4, def $r5, def $r6, def $r7, def $pc
+
+...

diff  --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-cond-iter-count.mir b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-cond-iter-count.mir
new file mode 100644
index 000000000000..7732793b8db3
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/multi-cond-iter-count.mir
@@ -0,0 +1,160 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
+
+--- |
+  define dso_local arm_aapcs_vfpcc void @multi_cond_iter_count(i32* noalias nocapture %0, i32* nocapture readonly %1, i32 %2, i32 %3) {
+    %5 = icmp eq i32 %3, 2
+    %6 = select i1 %5, i32 2, i32 4
+    %7 = icmp eq i32 %3, 4
+    %8 = select i1 %7, i32 1, i32 %6
+    %9 = shl i32 %2, %8
+    %10 = icmp eq i32 %9, 0
+    %11 = add i32 %9, 3
+    %12 = lshr i32 %11, 2
+    %13 = shl nuw i32 %12, 2
+    %14 = add i32 %13, -4
+    %15 = lshr i32 %14, 2
+    %16 = add nuw nsw i32 %15, 1
+    br i1 %10, label %34, label %17
+
+  17:                                               ; preds = %4
+    call void @llvm.set.loop.iterations.i32(i32 %16)
+    br label %18
+
+  18:                                               ; preds = %18, %17
+    %19 = phi i32* [ %31, %18 ], [ %0, %17 ]
+    %20 = phi i32* [ %30, %18 ], [ %1, %17 ]
+    %21 = phi i32 [ %16, %17 ], [ %32, %18 ]
+    %22 = phi i32 [ %9, %17 ], [ %26, %18 ]
+    %23 = bitcast i32* %19 to <4 x i32>*
+    %24 = bitcast i32* %20 to <4 x i32>*
+    %25 = call <4 x i1> @llvm.arm.mve.vctp32(i32 %22)
+    %26 = sub i32 %22, 4
+    %27 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %24, i32 4, <4 x i1> %25, <4 x i32> undef)
+    %28 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %23, i32 4, <4 x i1> %25, <4 x i32> undef)
+    %29 = mul nsw <4 x i32> %28, %27
+    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %29, <4 x i32>* %23, i32 4, <4 x i1> %25)
+    %30 = getelementptr i32, i32* %20, i32 4
+    %31 = getelementptr i32, i32* %19, i32 4
+    %32 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %21, i32 1)
+    %33 = icmp ne i32 %32, 0
+    br i1 %33, label %18, label %34
+
+  34:                                               ; preds = %18, %4
+    ret void
+  }
+  declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
+  declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
+  declare void @llvm.set.loop.iterations.i32(i32)
+  declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
+  declare <4 x i1> @llvm.arm.mve.vctp32(i32)
+
+...
+---
+name:            multi_cond_iter_count
+alignment:       2
+tracksRegLiveness: true
+registers:       []
+liveins:
+  - { reg: '$r0', virtual-reg: '' }
+  - { reg: '$r1', virtual-reg: '' }
+  - { reg: '$r2', virtual-reg: '' }
+  - { reg: '$r3', virtual-reg: '' }
+frameInfo:
+  stackSize:       8
+  offsetAdjustment: 0
+  maxAlignment:    4
+fixedStack:      []
+stack:
+  - { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+  - { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
+      stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
+      debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+callSites:       []
+constants:       []
+machineFunctionInfo: {}
+body:             |
+  ; CHECK-LABEL: name: multi_cond_iter_count
+  ; CHECK: bb.0 (%ir-block.4):
+  ; CHECK:   successors: %bb.1(0x80000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r2, $r3
+  ; CHECK:   frame-setup tPUSH 14 /* CC::al */, $noreg, killed $lr, implicit-def $sp, implicit $sp
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_offset 8
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $lr, -4
+  ; CHECK:   frame-setup CFI_INSTRUCTION offset $r7, -8
+  ; CHECK:   dead $r7 = frame-setup tMOVr $sp, 14 /* CC::al */, $noreg
+  ; CHECK:   frame-setup CFI_INSTRUCTION def_cfa_register $r7
+  ; CHECK:   tCMPi8 renamable $r3, 2, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   $r12 = tMOVr $r3, 14 /* CC::al */, $noreg
+  ; CHECK:   t2IT 1, 8, implicit-def $itstate
+  ; CHECK:   $r12 = t2MOVi 4, 1 /* CC::ne */, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+  ; CHECK:   tCMPi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg, implicit-def $cpsr
+  ; CHECK:   t2IT 0, 8, implicit-def $itstate
+  ; CHECK:   $r12 = t2MOVi 1, 0 /* CC::eq */, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+  ; CHECK:   renamable $r2 = t2LSLrr killed renamable $r2, killed renamable $r12, 14 /* CC::al */, $noreg, def $cpsr
+  ; CHECK:   t2IT 0, 8, implicit-def $itstate
+  ; CHECK:   tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r7, def $pc, implicit killed $itstate
+  ; CHECK:   $r3 = tMOVr $r0, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = MVE_DLSTP_32 killed renamable $r2
+  ; CHECK: bb.1 (%ir-block.18):
+  ; CHECK:   successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+  ; CHECK:   liveins: $lr, $r0, $r1, $r3
+  ; CHECK:   renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg
+  ; CHECK:   renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 0, $noreg
+  ; CHECK:   renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+  ; CHECK:   MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 0, killed $noreg
+  ; CHECK:   $r0 = tMOVr $r3, 14 /* CC::al */, $noreg
+  ; CHECK:   $lr = MVE_LETP killed renamable $lr, %bb.1
+  ; CHECK: bb.2 (%ir-block.34):
+  ; CHECK:   tPOP_RET 14 /* CC::al */, $noreg, def $r7, def $pc
+  bb.0 (%ir-block.4):
+    successors: %bb.1(0x80000000)
+    liveins: $r0, $r1, $r2, $r3, $lr
+
+    frame-setup tPUSH 14, $noreg, killed $lr, implicit-def $sp, implicit $sp
+    frame-setup CFI_INSTRUCTION def_cfa_offset 8
+    frame-setup CFI_INSTRUCTION offset $lr, -4
+    frame-setup CFI_INSTRUCTION offset $r7, -8
+    $r7 = frame-setup tMOVr $sp, 14, $noreg
+    frame-setup CFI_INSTRUCTION def_cfa_register $r7
+    tCMPi8 renamable $r3, 2, 14, $noreg, implicit-def $cpsr
+    $r12 = tMOVr $r3, 14, $noreg
+    t2IT 1, 8, implicit-def $itstate
+    $r12 = t2MOVi 4, 1, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+    tCMPi8 killed renamable $r3, 4, 14, $noreg, implicit-def $cpsr
+    t2IT 0, 8, implicit-def $itstate
+    $r12 = t2MOVi 1, 0, killed $cpsr, $noreg, implicit killed renamable $r12, implicit killed $itstate
+    renamable $r2 = t2LSLrr killed renamable $r2, killed renamable $r12, 14, $noreg, def $cpsr
+    t2IT 0, 8, implicit-def $itstate
+    tPOP_RET 0, killed $cpsr, def $r7, def $pc, implicit killed $itstate
+    renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14, $noreg
+    renamable $r3 = t2BICri killed renamable $r3, 3, 14, $noreg, $noreg
+    renamable $r12 = t2SUBri killed renamable $r3, 4, 14, $noreg, $noreg
+    renamable $r3, dead $cpsr = tMOVi8 1, 14, $noreg
+    renamable $lr = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14, $noreg, $noreg
+    $r3 = tMOVr $r0, 14, $noreg
+    t2DoLoopStart renamable $lr
+
+  bb.1 (%ir-block.18):
+    successors: %bb.1(0x7c000000), %bb.2(0x04000000)
+    liveins: $lr, $r0, $r1, $r2, $r3
+
+    renamable $vpr = MVE_VCTP32 renamable $r2, 0, $noreg
+    MVE_VPST 4, implicit $vpr
+    renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr
+    renamable $r3, renamable $q1 = MVE_VLDRWU32_post killed renamable $r3, 16, 1, renamable $vpr
+    renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 4, 14, $noreg
+    renamable $q0 = nsw MVE_VMULi32 killed renamable $q1, killed renamable $q0, 0, $noreg, undef renamable $q0
+    MVE_VPST 8, implicit $vpr
+    MVE_VSTRWU32 killed renamable $q0, killed renamable $r0, 0, 1, killed renamable $vpr
+    renamable $lr = t2LoopDec killed renamable $lr, 1
+    $r0 = tMOVr $r3, 14, $noreg
+    t2LoopEnd renamable $lr, %bb.1, implicit-def dead $cpsr
+    tB %bb.2, 14, $noreg
+
+  bb.2 (%ir-block.34):
+    tPOP_RET 14, $noreg, def $r7, def $pc
+
+...


        


More information about the llvm-commits mailing list