; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-pc-linux -x86-cmov-converter=true -verify-machineinstrs -disable-block-placement < %s | FileCheck -allow-deprecated-dag-overlap %s
; RUN: llc -mtriple=x86_64-pc-linux -x86-cmov-converter=true -x86-cmov-converter-force-all=true -verify-machineinstrs -disable-block-placement < %s | FileCheck -allow-deprecated-dag-overlap %s -check-prefix=CHECK-FORCEALL
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; This test checks that x86-cmov-converter optimization transform CMOV
;; instruction into branches when it is profitable.
;; There are 5 cases below:
;; 1. CmovInCriticalPath:
;; CMOV depends on the condition and it is in the hot path.
;; Thus, it worths transforming.
;;
;; 2. CmovNotInCriticalPath:
;; Similar test like in (1), just that CMOV is not in the hot path.
;; Thus, it does not worth transforming.
;;
;; 3. MaxIndex:
;; Maximum calculation algorithm that is looking for the max index,
;; calculating CMOV value is cheaper than calculating CMOV condition.
;; Thus, it worths transforming.
;;
;; 4. MaxValue:
;; Maximum calculation algorithm that is looking for the max value,
;; calculating CMOV value is not cheaper than calculating CMOV condition.
;; Thus, it does not worth transforming.
;;
;; 5. BinarySearch:
;; Usually, binary search CMOV is not predicted.
;; Thus, it does not worth transforming.
;;
;; Test was created using the following command line:
;; > clang -S -O2 -m64 -fno-vectorize -fno-unroll-loops -emit-llvm foo.c -o -
;; Where foo.c is:
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;void CmovInHotPath(int n, int a, int b, int *c, int *d) {
;; for (int i = 0; i < n; i++) {
;; int t = c[i] + 1;
;; if (cptr a > b)
;; t = 10;
;; c[i] = (c[i] + 1) * t;
;; }
;;}
;;
;;
;;void CmovNotInHotPath(int n, int a, int b, int *c, int *d) {
;; for (int i = 0; i < n; i++) {
;; int t = c[i];
;; if (cptr a > b)
;; t = 10;
;; c[i] = t;
;; d[i] /= b;
;; }
;;}
;;
;;
;;int MaxIndex(int n, int *a) {
;; int t = 0;
;; for (int i = 1; i < n; i++) {
;; if (a[i] > a[t])
;; t = i;
;; }
;; return t;
;;}
;;
;;
;;int MaxValue(int n, int *a) {
;; int t = a[0];
;; for (int i = 1; i < n; i++) {
;; if (a[i] > t)
;; t = a[i];
;; }
;; return t;
;;}
;;
;;typedef struct Node Node;
;;struct Node {
;; unsigned Val;
;; Node *Right;
;; Node *Left;
;;};
;;
;;unsigned BinarySearch(unsigned Mask, Node *Curr, Node *Next) {
;; while (Curr->Val > Next->Val) {
;; Curr = Next;
;; if (Mask & (0x1 << Curr->Val))
;; Next = Curr->Right;
;; else
;; Next = Curr->Left;
;; }
;; return Curr->Val;
;;}
;;
;;
;;void SmallGainPerLoop(int n, int a, int b, int *c, int *d) {
;; for (int i = 0; i < n; i++) {
;; int t = c[i];
;; if (cptr a > b)
;; t = 10;
;; c[i] = t;
;; }
;;}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
%struct.Node = type { i32, ptr, ptr }
define void @CmovInHotPath(i32 %n, i32 %a, i32 %b, ptr nocapture %c, ptr nocapture readnone %d) #0 {
; CHECK-LABEL: CmovInHotPath:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: jle .LBB0_5
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: movl %edi, %r8d
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: .LBB0_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rcx,%rdi,4), %eax
; CHECK-NEXT: leal 1(%rax), %r9d
; CHECK-NEXT: imull %esi, %eax
; CHECK-NEXT: movl $10, %r10d
; CHECK-NEXT: cmpl %edx, %eax
; CHECK-NEXT: jg .LBB0_4
; CHECK-NEXT: # %bb.3: # %for.body
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: movl %r9d, %r10d
; CHECK-NEXT: .LBB0_4: # %for.body
; CHECK-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: imull %r9d, %r10d
; CHECK-NEXT: movl %r10d, (%rcx,%rdi,4)
; CHECK-NEXT: addq $1, %rdi
; CHECK-NEXT: cmpq %rdi, %r8
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: .LBB0_5: # %for.cond.cleanup
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: CmovInHotPath:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: testl %edi, %edi
; CHECK-FORCEALL-NEXT: jle .LBB0_5
; CHECK-FORCEALL-NEXT: # %bb.1: # %for.body.preheader
; CHECK-FORCEALL-NEXT: movl %edi, %r8d
; CHECK-FORCEALL-NEXT: xorl %edi, %edi
; CHECK-FORCEALL-NEXT: .LBB0_2: # %for.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rcx,%rdi,4), %eax
; CHECK-FORCEALL-NEXT: leal 1(%rax), %r9d
; CHECK-FORCEALL-NEXT: imull %esi, %eax
; CHECK-FORCEALL-NEXT: movl $10, %r10d
; CHECK-FORCEALL-NEXT: cmpl %edx, %eax
; CHECK-FORCEALL-NEXT: jg .LBB0_4
; CHECK-FORCEALL-NEXT: # %bb.3: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %r9d, %r10d
; CHECK-FORCEALL-NEXT: .LBB0_4: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB0_2 Depth=1
; CHECK-FORCEALL-NEXT: imull %r9d, %r10d
; CHECK-FORCEALL-NEXT: movl %r10d, (%rcx,%rdi,4)
; CHECK-FORCEALL-NEXT: addq $1, %rdi
; CHECK-FORCEALL-NEXT: cmpq %rdi, %r8
; CHECK-FORCEALL-NEXT: jne .LBB0_2
; CHECK-FORCEALL-NEXT: .LBB0_5: # %for.cond.cleanup
; CHECK-FORCEALL-NEXT: retq
entry:
%cmp14 = icmp sgt i32 %n, 0
br i1 %cmp14, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %c, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%add = add nsw i32 %0, 1
%mul = mul nsw i32 %0, %a
%cmp3 = icmp sgt i32 %mul, %b
%. = select i1 %cmp3, i32 10, i32 %add
%mul7 = mul nsw i32 %., %add
store i32 %mul7, ptr %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
define void @CmovNotInHotPath(i32 %n, i32 %a, i32 %b, ptr nocapture %c, ptr nocapture %d) #0 {
; CHECK-LABEL: CmovNotInHotPath:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: testl %edi, %edi
; CHECK-NEXT: jle .LBB1_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: movl %edx, %r9d
; CHECK-NEXT: movl %edi, %r10d
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: movl $10, %r11d
; CHECK-NEXT: .LBB1_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rcx,%rdi,4), %eax
; CHECK-NEXT: movl %eax, %edx
; CHECK-NEXT: imull %esi, %edx
; CHECK-NEXT: cmpl %r9d, %edx
; CHECK-NEXT: cmovgl %r11d, %eax
; CHECK-NEXT: movl %eax, (%rcx,%rdi,4)
; CHECK-NEXT: movl (%r8,%rdi,4), %eax
; CHECK-NEXT: cltd
; CHECK-NEXT: idivl %r9d
; CHECK-NEXT: movl %eax, (%r8,%rdi,4)
; CHECK-NEXT: addq $1, %rdi
; CHECK-NEXT: cmpq %rdi, %r10
; CHECK-NEXT: jne .LBB1_2
; CHECK-NEXT: .LBB1_3: # %for.cond.cleanup
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: CmovNotInHotPath:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: testl %edi, %edi
; CHECK-FORCEALL-NEXT: jle .LBB1_5
; CHECK-FORCEALL-NEXT: # %bb.1: # %for.body.preheader
; CHECK-FORCEALL-NEXT: movl %edx, %r9d
; CHECK-FORCEALL-NEXT: movl %edi, %r10d
; CHECK-FORCEALL-NEXT: xorl %edi, %edi
; CHECK-FORCEALL-NEXT: .LBB1_2: # %for.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rcx,%rdi,4), %r11d
; CHECK-FORCEALL-NEXT: movl %r11d, %eax
; CHECK-FORCEALL-NEXT: imull %esi, %eax
; CHECK-FORCEALL-NEXT: movl $10, %edx
; CHECK-FORCEALL-NEXT: cmpl %r9d, %eax
; CHECK-FORCEALL-NEXT: jg .LBB1_4
; CHECK-FORCEALL-NEXT: # %bb.3: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB1_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %r11d, %edx
; CHECK-FORCEALL-NEXT: .LBB1_4: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB1_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %edx, (%rcx,%rdi,4)
; CHECK-FORCEALL-NEXT: movl (%r8,%rdi,4), %eax
; CHECK-FORCEALL-NEXT: cltd
; CHECK-FORCEALL-NEXT: idivl %r9d
; CHECK-FORCEALL-NEXT: movl %eax, (%r8,%rdi,4)
; CHECK-FORCEALL-NEXT: addq $1, %rdi
; CHECK-FORCEALL-NEXT: cmpq %rdi, %r10
; CHECK-FORCEALL-NEXT: jne .LBB1_2
; CHECK-FORCEALL-NEXT: .LBB1_5: # %for.cond.cleanup
; CHECK-FORCEALL-NEXT: retq
entry:
%cmp18 = icmp sgt i32 %n, 0
br i1 %cmp18, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %c, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%mul = mul nsw i32 %0, %a
%cmp3 = icmp sgt i32 %mul, %b
%. = select i1 %cmp3, i32 10, i32 %0
store i32 %., ptr %arrayidx, align 4
%arrayidx7 = getelementptr inbounds i32, ptr %d, i64 %indvars.iv
%1 = load i32, ptr %arrayidx7, align 4
%div = sdiv i32 %1, %b
store i32 %div, ptr %arrayidx7, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
define i32 @MaxIndex(i32 %n, ptr nocapture readonly %a) #0 {
; CHECK-LABEL: MaxIndex:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl $2, %edi
; CHECK-NEXT: jl .LBB2_5
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: movl %edi, %r8d
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: movl $1, %edx
; CHECK-NEXT: .LBB2_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rsi,%rdx,4), %r9d
; CHECK-NEXT: movslq %edi, %rcx
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: cmpl (%rsi,%rcx,4), %r9d
; CHECK-NEXT: jg .LBB2_4
; CHECK-NEXT: # %bb.3: # %for.body
; CHECK-NEXT: # in Loop: Header=BB2_2 Depth=1
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: .LBB2_4: # %for.body
; CHECK-NEXT: # in Loop: Header=BB2_2 Depth=1
; CHECK-NEXT: addq $1, %rdx
; CHECK-NEXT: movl %eax, %edi
; CHECK-NEXT: cmpq %rdx, %r8
; CHECK-NEXT: jne .LBB2_2
; CHECK-NEXT: .LBB2_5: # %for.cond.cleanup
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: MaxIndex:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: xorl %eax, %eax
; CHECK-FORCEALL-NEXT: cmpl $2, %edi
; CHECK-FORCEALL-NEXT: jl .LBB2_5
; CHECK-FORCEALL-NEXT: # %bb.1: # %for.body.preheader
; CHECK-FORCEALL-NEXT: movl %edi, %r8d
; CHECK-FORCEALL-NEXT: xorl %edi, %edi
; CHECK-FORCEALL-NEXT: movl $1, %edx
; CHECK-FORCEALL-NEXT: .LBB2_2: # %for.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rsi,%rdx,4), %r9d
; CHECK-FORCEALL-NEXT: movslq %edi, %rcx
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: cmpl (%rsi,%rcx,4), %r9d
; CHECK-FORCEALL-NEXT: jg .LBB2_4
; CHECK-FORCEALL-NEXT: # %bb.3: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB2_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: .LBB2_4: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB2_2 Depth=1
; CHECK-FORCEALL-NEXT: addq $1, %rdx
; CHECK-FORCEALL-NEXT: movl %eax, %edi
; CHECK-FORCEALL-NEXT: cmpq %rdx, %r8
; CHECK-FORCEALL-NEXT: jne .LBB2_2
; CHECK-FORCEALL-NEXT: .LBB2_5: # %for.cond.cleanup
; CHECK-FORCEALL-NEXT: retq
entry:
%cmp14 = icmp sgt i32 %n, 1
br i1 %cmp14, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
%t.0.lcssa = phi i32 [ 0, %entry ], [ %i.0.t.0, %for.body ]
ret i32 %t.0.lcssa
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 1, %for.body.preheader ]
%t.015 = phi i32 [ %i.0.t.0, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%idxprom1 = sext i32 %t.015 to i64
%arrayidx2 = getelementptr inbounds i32, ptr %a, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%cmp3 = icmp sgt i32 %0, %1
%2 = trunc i64 %indvars.iv to i32
%i.0.t.0 = select i1 %cmp3, i32 %2, i32 %t.015
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
; TODO: If cmov instruction is marked as unpredicatable, do not convert it to branch.
define i32 @MaxIndex_unpredictable(i32 %n, ptr nocapture readonly %a) #0 {
; CHECK-LABEL: MaxIndex_unpredictable:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl $2, %edi
; CHECK-NEXT: jl .LBB3_5
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: movl %edi, %r8d
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: movl $1, %edx
; CHECK-NEXT: .LBB3_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rsi,%rdx,4), %r9d
; CHECK-NEXT: movslq %edi, %rcx
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: cmpl (%rsi,%rcx,4), %r9d
; CHECK-NEXT: jg .LBB3_4
; CHECK-NEXT: # %bb.3: # %for.body
; CHECK-NEXT: # in Loop: Header=BB3_2 Depth=1
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: .LBB3_4: # %for.body
; CHECK-NEXT: # in Loop: Header=BB3_2 Depth=1
; CHECK-NEXT: addq $1, %rdx
; CHECK-NEXT: movl %eax, %edi
; CHECK-NEXT: cmpq %rdx, %r8
; CHECK-NEXT: jne .LBB3_2
; CHECK-NEXT: .LBB3_5: # %for.cond.cleanup
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: MaxIndex_unpredictable:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: xorl %eax, %eax
; CHECK-FORCEALL-NEXT: cmpl $2, %edi
; CHECK-FORCEALL-NEXT: jl .LBB3_5
; CHECK-FORCEALL-NEXT: # %bb.1: # %for.body.preheader
; CHECK-FORCEALL-NEXT: movl %edi, %r8d
; CHECK-FORCEALL-NEXT: xorl %edi, %edi
; CHECK-FORCEALL-NEXT: movl $1, %edx
; CHECK-FORCEALL-NEXT: .LBB3_2: # %for.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rsi,%rdx,4), %r9d
; CHECK-FORCEALL-NEXT: movslq %edi, %rcx
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: cmpl (%rsi,%rcx,4), %r9d
; CHECK-FORCEALL-NEXT: jg .LBB3_4
; CHECK-FORCEALL-NEXT: # %bb.3: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB3_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: .LBB3_4: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB3_2 Depth=1
; CHECK-FORCEALL-NEXT: addq $1, %rdx
; CHECK-FORCEALL-NEXT: movl %eax, %edi
; CHECK-FORCEALL-NEXT: cmpq %rdx, %r8
; CHECK-FORCEALL-NEXT: jne .LBB3_2
; CHECK-FORCEALL-NEXT: .LBB3_5: # %for.cond.cleanup
; CHECK-FORCEALL-NEXT: retq
entry:
%cmp14 = icmp sgt i32 %n, 1
br i1 %cmp14, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
%t.0.lcssa = phi i32 [ 0, %entry ], [ %i.0.t.0, %for.body ]
ret i32 %t.0.lcssa
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 1, %for.body.preheader ]
%t.015 = phi i32 [ %i.0.t.0, %for.body ], [ 0, %for.body.preheader ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%idxprom1 = sext i32 %t.015 to i64
%arrayidx2 = getelementptr inbounds i32, ptr %a, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%cmp3 = icmp sgt i32 %0, %1
%2 = trunc i64 %indvars.iv to i32
%i.0.t.0 = select i1 %cmp3, i32 %2, i32 %t.015, !unpredictable !0
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
define i32 @MaxValue(i32 %n, ptr nocapture readonly %a) #0 {
; CHECK-LABEL: MaxValue:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl (%rsi), %eax
; CHECK-NEXT: cmpl $2, %edi
; CHECK-NEXT: jl .LBB4_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: movl %edi, %ecx
; CHECK-NEXT: movl $1, %edx
; CHECK-NEXT: .LBB4_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rsi,%rdx,4), %edi
; CHECK-NEXT: cmpl %eax, %edi
; CHECK-NEXT: cmovgl %edi, %eax
; CHECK-NEXT: addq $1, %rdx
; CHECK-NEXT: cmpq %rdx, %rcx
; CHECK-NEXT: jne .LBB4_2
; CHECK-NEXT: .LBB4_3: # %for.cond.cleanup
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: MaxValue:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl (%rsi), %ecx
; CHECK-FORCEALL-NEXT: cmpl $2, %edi
; CHECK-FORCEALL-NEXT: jge .LBB4_3
; CHECK-FORCEALL-NEXT: # %bb.1:
; CHECK-FORCEALL-NEXT: movl %ecx, %eax
; CHECK-FORCEALL-NEXT: .LBB4_2: # %for.cond.cleanup
; CHECK-FORCEALL-NEXT: retq
; CHECK-FORCEALL-NEXT: .LBB4_3: # %for.body.preheader
; CHECK-FORCEALL-NEXT: movl %edi, %edi
; CHECK-FORCEALL-NEXT: movl $1, %edx
; CHECK-FORCEALL-NEXT: .LBB4_4: # %for.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rsi,%rdx,4), %eax
; CHECK-FORCEALL-NEXT: cmpl %ecx, %eax
; CHECK-FORCEALL-NEXT: jg .LBB4_6
; CHECK-FORCEALL-NEXT: # %bb.5: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB4_4 Depth=1
; CHECK-FORCEALL-NEXT: movl %ecx, %eax
; CHECK-FORCEALL-NEXT: .LBB4_6: # %for.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB4_4 Depth=1
; CHECK-FORCEALL-NEXT: addq $1, %rdx
; CHECK-FORCEALL-NEXT: movl %eax, %ecx
; CHECK-FORCEALL-NEXT: cmpq %rdx, %rdi
; CHECK-FORCEALL-NEXT: je .LBB4_2
; CHECK-FORCEALL-NEXT: jmp .LBB4_4
entry:
%0 = load i32, ptr %a, align 4
%cmp13 = icmp sgt i32 %n, 1
br i1 %cmp13, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
%t.0.lcssa = phi i32 [ %0, %entry ], [ %.t.0, %for.body ]
ret i32 %t.0.lcssa
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 1, %for.body.preheader ]
%t.014 = phi i32 [ %.t.0, %for.body ], [ %0, %for.body.preheader ]
%arrayidx1 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%1 = load i32, ptr %arrayidx1, align 4
%cmp2 = icmp sgt i32 %1, %t.014
%.t.0 = select i1 %cmp2, i32 %1, i32 %t.014
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
define i32 @BinarySearch(i32 %Mask, ptr nocapture readonly %Curr, ptr nocapture readonly %Next) #0 {
; CHECK-LABEL: BinarySearch:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl (%rsi), %eax
; CHECK-NEXT: jmp .LBB5_2
; CHECK-NEXT: .LBB5_1: # %while.body
; CHECK-NEXT: # in Loop: Header=BB5_2 Depth=1
; CHECK-NEXT: movl %ecx, %eax
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: btl %eax, %edi
; CHECK-NEXT: setae %cl
; CHECK-NEXT: movq 8(%rdx,%rcx,8), %rdx
; CHECK-NEXT: .LBB5_2: # %while.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movl (%rdx), %ecx
; CHECK-NEXT: cmpl %ecx, %eax
; CHECK-NEXT: ja .LBB5_1
; CHECK-NEXT: # %bb.3: # %while.end
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: BinarySearch:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl (%rsi), %eax
; CHECK-FORCEALL-NEXT: jmp .LBB5_2
; CHECK-FORCEALL-NEXT: .LBB5_1: # %while.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB5_2 Depth=1
; CHECK-FORCEALL-NEXT: movl %ecx, %eax
; CHECK-FORCEALL-NEXT: xorl %ecx, %ecx
; CHECK-FORCEALL-NEXT: btl %eax, %edi
; CHECK-FORCEALL-NEXT: setae %cl
; CHECK-FORCEALL-NEXT: movq 8(%rdx,%rcx,8), %rdx
; CHECK-FORCEALL-NEXT: .LBB5_2: # %while.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movl (%rdx), %ecx
; CHECK-FORCEALL-NEXT: cmpl %ecx, %eax
; CHECK-FORCEALL-NEXT: ja .LBB5_1
; CHECK-FORCEALL-NEXT: # %bb.3: # %while.end
; CHECK-FORCEALL-NEXT: retq
entry:
%0 = load i32, ptr %Curr, align 8
%1 = load i32, ptr %Next, align 8
%cmp10 = icmp ugt i32 %0, %1
br i1 %cmp10, label %while.body, label %while.end
while.body: ; preds = %entry, %while.body
%2 = phi i32 [ %4, %while.body ], [ %1, %entry ]
%Next.addr.011 = phi ptr [ %3, %while.body ], [ %Next, %entry ]
%shl = shl i32 1, %2
%and = and i32 %shl, %Mask
%tobool = icmp eq i32 %and, 0
%Left = getelementptr inbounds %struct.Node, ptr %Next.addr.011, i64 0, i32 2
%Right = getelementptr inbounds %struct.Node, ptr %Next.addr.011, i64 0, i32 1
%Left.sink = select i1 %tobool, ptr %Left, ptr %Right
%3 = load ptr, ptr %Left.sink, align 8
%4 = load i32, ptr %3, align 8
%cmp = icmp ugt i32 %2, %4
br i1 %cmp, label %while.body, label %while.end
while.end: ; preds = %while.body, %entry
%.lcssa = phi i32 [ %0, %entry ], [ %2, %while.body ]
ret i32 %.lcssa
}
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; The following test checks that x86-cmov-converter optimization transforms
;; CMOV instructions into branch correctly.
;;
;; MBB:
;; cond = cmp ...
;; v1 = CMOVgt t1, f1, cond
;; v2 = CMOVle s1, f2, cond
;;
;; Where: t1 = 11, f1 = 22, f2 = a
;;
;; After CMOV transformation
;; -------------------------
;; MBB:
;; cond = cmp ...
;; ja %SinkMBB
;;
;; FalseMBB:
;; jmp %SinkMBB
;;
;; SinkMBB:
;; %v1 = phi[%f1, %FalseMBB], [%t1, %MBB]
;; %v2 = phi[%f1, %FalseMBB], [%f2, %MBB] ; For CMOV with OppCC switch
;; ; true-value with false-value
;; ; Phi instruction cannot use
;; ; previous Phi instruction result
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
define void @Transform(ptr%arr, ptr%arr2, i32 %a, i32 %b, i32 %c, i32 %n) #0 {
; CHECK-LABEL: Transform:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movb $1, %al
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB6_5
; CHECK-NEXT: # %bb.1: # %while.body.preheader
; CHECK-NEXT: movl %edx, %r8d
; CHECK-NEXT: xorl %esi, %esi
; CHECK-NEXT: .LBB6_2: # %while.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: movslq %esi, %rsi
; CHECK-NEXT: movl (%rdi,%rsi,4), %eax
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: divl %r8d
; CHECK-NEXT: movl %eax, %edx
; CHECK-NEXT: movl $11, %eax
; CHECK-NEXT: movl %r8d, %ecx
; CHECK-NEXT: cmpl %r8d, %edx
; CHECK-NEXT: ja .LBB6_4
; CHECK-NEXT: # %bb.3: # %while.body
; CHECK-NEXT: # in Loop: Header=BB6_2 Depth=1
; CHECK-NEXT: movl $22, %eax
; CHECK-NEXT: movl $22, %ecx
; CHECK-NEXT: .LBB6_4: # %while.body
; CHECK-NEXT: # in Loop: Header=BB6_2 Depth=1
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: divl %ecx
; CHECK-NEXT: movl %edx, (%rdi,%rsi,4)
; CHECK-NEXT: addl $1, %esi
; CHECK-NEXT: cmpl %r9d, %esi
; CHECK-NEXT: ja .LBB6_2
; CHECK-NEXT: .LBB6_5: # %while.end
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: Transform:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movb $1, %al
; CHECK-FORCEALL-NEXT: testb %al, %al
; CHECK-FORCEALL-NEXT: jne .LBB6_5
; CHECK-FORCEALL-NEXT: # %bb.1: # %while.body.preheader
; CHECK-FORCEALL-NEXT: movl %edx, %r8d
; CHECK-FORCEALL-NEXT: xorl %esi, %esi
; CHECK-FORCEALL-NEXT: .LBB6_2: # %while.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: movslq %esi, %rsi
; CHECK-FORCEALL-NEXT: movl (%rdi,%rsi,4), %eax
; CHECK-FORCEALL-NEXT: xorl %edx, %edx
; CHECK-FORCEALL-NEXT: divl %r8d
; CHECK-FORCEALL-NEXT: movl %eax, %edx
; CHECK-FORCEALL-NEXT: movl $11, %eax
; CHECK-FORCEALL-NEXT: movl %r8d, %ecx
; CHECK-FORCEALL-NEXT: cmpl %r8d, %edx
; CHECK-FORCEALL-NEXT: ja .LBB6_4
; CHECK-FORCEALL-NEXT: # %bb.3: # %while.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB6_2 Depth=1
; CHECK-FORCEALL-NEXT: movl $22, %eax
; CHECK-FORCEALL-NEXT: movl $22, %ecx
; CHECK-FORCEALL-NEXT: .LBB6_4: # %while.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB6_2 Depth=1
; CHECK-FORCEALL-NEXT: xorl %edx, %edx
; CHECK-FORCEALL-NEXT: divl %ecx
; CHECK-FORCEALL-NEXT: movl %edx, (%rdi,%rsi,4)
; CHECK-FORCEALL-NEXT: addl $1, %esi
; CHECK-FORCEALL-NEXT: cmpl %r9d, %esi
; CHECK-FORCEALL-NEXT: ja .LBB6_2
; CHECK-FORCEALL-NEXT: .LBB6_5: # %while.end
; CHECK-FORCEALL-NEXT: retq
entry:
%cmp10 = icmp ugt i32 0, %n
br i1 %cmp10, label %while.body, label %while.end
while.body: ; preds = %entry, %while.body
%i = phi i32 [ %i_inc, %while.body ], [ 0, %entry ]
%arr_i = getelementptr inbounds i32, ptr %arr, i32 %i
%x = load i32, ptr %arr_i, align 4
%div = udiv i32 %x, %a
%cond = icmp ugt i32 %div, %a
%condOpp = icmp ule i32 %div, %a
%s1 = select i1 %cond, i32 11, i32 22
%s2 = select i1 %condOpp, i32 %s1, i32 %a
%sum = urem i32 %s1, %s2
store i32 %sum, ptr %arr_i, align 4
%i_inc = add i32 %i, 1
%cmp = icmp ugt i32 %i_inc, %n
br i1 %cmp, label %while.body, label %while.end
while.end: ; preds = %while.body, %entry
ret void
}
; Test that we always will convert a cmov with a memory operand into a branch,
; even outside of a loop.
define i32 @test_cmov_memoperand(i32 %a, i32 %b, i32 %x, ptr %y) #0 {
; CHECK-LABEL: test_cmov_memoperand:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB7_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %eax
; CHECK-NEXT: .LBB7_2: # %entry
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB7_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %eax
; CHECK-FORCEALL-NEXT: .LBB7_2: # %entry
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%load = load i32, ptr %y
%z = select i1 %cond, i32 %x, i32 %load
ret i32 %z
}
; TODO: If cmov instruction is marked as unpredicatable, do not convert it to branch.
define i32 @test_cmov_memoperand_unpredictable(i32 %a, i32 %b, i32 %x, ptr %y) #0 {
; CHECK-LABEL: test_cmov_memoperand_unpredictable:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB8_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %eax
; CHECK-NEXT: .LBB8_2: # %entry
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_unpredictable:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB8_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %eax
; CHECK-FORCEALL-NEXT: .LBB8_2: # %entry
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%load = load i32, ptr %y
%z = select i1 %cond, i32 %x, i32 %load, !unpredictable !0
ret i32 %z
}
; Test that we can convert a group of cmovs where only one has a memory
; operand.
define i32 @test_cmov_memoperand_in_group(i32 %a, i32 %b, i32 %x, ptr %y.ptr) #0 {
; CHECK-LABEL: test_cmov_memoperand_in_group:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: movl %edx, %r8d
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB9_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %r8d
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: movl %esi, %edx
; CHECK-NEXT: .LBB9_2: # %entry
; CHECK-NEXT: addl %r8d, %eax
; CHECK-NEXT: addl %edx, %eax
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_in_group:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: movl %edx, %r8d
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB9_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %r8d
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: movl %esi, %edx
; CHECK-FORCEALL-NEXT: .LBB9_2: # %entry
; CHECK-FORCEALL-NEXT: addl %r8d, %eax
; CHECK-FORCEALL-NEXT: addl %edx, %eax
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%y = load i32, ptr %y.ptr
%z1 = select i1 %cond, i32 %x, i32 %a
%z2 = select i1 %cond, i32 %x, i32 %y
%z3 = select i1 %cond, i32 %x, i32 %b
%s1 = add i32 %z1, %z2
%s2 = add i32 %s1, %z3
ret i32 %s2
}
; Same as before but with operands reversed in the select with a load.
define i32 @test_cmov_memoperand_in_group2(i32 %a, i32 %b, i32 %x, ptr %y.ptr) #0 {
; CHECK-LABEL: test_cmov_memoperand_in_group2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edx, %eax
; CHECK-NEXT: movl %edx, %r8d
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: jbe .LBB10_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %r8d
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: movl %esi, %edx
; CHECK-NEXT: .LBB10_2: # %entry
; CHECK-NEXT: addl %r8d, %eax
; CHECK-NEXT: addl %edx, %eax
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_in_group2:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edx, %eax
; CHECK-FORCEALL-NEXT: movl %edx, %r8d
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: jbe .LBB10_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %r8d
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: movl %esi, %edx
; CHECK-FORCEALL-NEXT: .LBB10_2: # %entry
; CHECK-FORCEALL-NEXT: addl %r8d, %eax
; CHECK-FORCEALL-NEXT: addl %edx, %eax
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%y = load i32, ptr %y.ptr
%z2 = select i1 %cond, i32 %a, i32 %x
%z1 = select i1 %cond, i32 %y, i32 %x
%z3 = select i1 %cond, i32 %b, i32 %x
%s1 = add i32 %z1, %z2
%s2 = add i32 %s1, %z3
ret i32 %s2
}
; Test that we don't convert a group of cmovs with conflicting directions of
; loads.
define i32 @test_cmov_memoperand_conflicting_dir(i32 %a, i32 %b, i32 %x, ptr %y1.ptr, ptr %y2.ptr) #0 {
; CHECK-LABEL: test_cmov_memoperand_conflicting_dir:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: movl (%rcx), %eax
; CHECK-NEXT: cmoval %edx, %eax
; CHECK-NEXT: cmoval (%r8), %edx
; CHECK-NEXT: addl %edx, %eax
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_conflicting_dir:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: movl (%rcx), %eax
; CHECK-FORCEALL-NEXT: cmoval %edx, %eax
; CHECK-FORCEALL-NEXT: cmoval (%r8), %edx
; CHECK-FORCEALL-NEXT: addl %edx, %eax
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%y1 = load i32, ptr %y1.ptr
%y2 = load i32, ptr %y2.ptr
%z1 = select i1 %cond, i32 %x, i32 %y1
%z2 = select i1 %cond, i32 %y2, i32 %x
%s1 = add i32 %z1, %z2
ret i32 %s1
}
; Test that we can convert a group of cmovs where only one has a memory
; operand and where that memory operand's registers come from a prior cmov in
; the group.
define i32 @test_cmov_memoperand_in_group_reuse_for_addr(i32 %a, i32 %b, ptr %x, ptr %y) #0 {
; CHECK-LABEL: test_cmov_memoperand_in_group_reuse_for_addr:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB12_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %eax
; CHECK-NEXT: .LBB12_2: # %entry
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_in_group_reuse_for_addr:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB12_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %eax
; CHECK-FORCEALL-NEXT: .LBB12_2: # %entry
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%p = select i1 %cond, ptr %x, ptr %y
%load = load i32, ptr %p
%z = select i1 %cond, i32 %a, i32 %load
ret i32 %z
}
; Test that we can convert a group of two cmovs with memory operands where one
; uses the result of the other as part of the address.
define i32 @test_cmov_memoperand_in_group_reuse_for_addr2(i32 %a, i32 %b, ptr %x, ptr %y) #0 {
; CHECK-LABEL: test_cmov_memoperand_in_group_reuse_for_addr2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB13_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movq (%rcx), %rax
; CHECK-NEXT: movl (%rax), %eax
; CHECK-NEXT: .LBB13_2: # %entry
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_in_group_reuse_for_addr2:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB13_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movq (%rcx), %rax
; CHECK-FORCEALL-NEXT: movl (%rax), %eax
; CHECK-FORCEALL-NEXT: .LBB13_2: # %entry
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%load1 = load ptr, ptr %y
%p = select i1 %cond, ptr %x, ptr %load1
%load2 = load i32, ptr %p
%z = select i1 %cond, i32 %a, i32 %load2
ret i32 %z
}
; Test that we can convert a group of cmovs where only one has a memory
; operand and where that memory operand's registers come from a prior cmov and
; where that cmov gets *its* input from a prior cmov in the group.
define i32 @test_cmov_memoperand_in_group_reuse_for_addr3(i32 %a, i32 %b, ptr %x, ptr %y, ptr %z) #0 {
; CHECK-LABEL: test_cmov_memoperand_in_group_reuse_for_addr3:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: ja .LBB14_2
; CHECK-NEXT: # %bb.1: # %entry
; CHECK-NEXT: movl (%rcx), %eax
; CHECK-NEXT: .LBB14_2: # %entry
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_cmov_memoperand_in_group_reuse_for_addr3:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movl %edi, %eax
; CHECK-FORCEALL-NEXT: cmpl %esi, %edi
; CHECK-FORCEALL-NEXT: ja .LBB14_2
; CHECK-FORCEALL-NEXT: # %bb.1: # %entry
; CHECK-FORCEALL-NEXT: movl (%rcx), %eax
; CHECK-FORCEALL-NEXT: .LBB14_2: # %entry
; CHECK-FORCEALL-NEXT: retq
entry:
%cond = icmp ugt i32 %a, %b
%p = select i1 %cond, ptr %x, ptr %y
%p2 = select i1 %cond, ptr %z, ptr %p
%load = load i32, ptr %p2
%r = select i1 %cond, i32 %a, i32 %load
ret i32 %r
}
@begin = external global ptr
@end = external global ptr
define void @test_memoperand_loop(i32 %data) #0 {
; CHECK-LABEL: test_memoperand_loop:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: movq begin@GOTPCREL(%rip), %r8
; CHECK-NEXT: movq (%r8), %rax
; CHECK-NEXT: movq end@GOTPCREL(%rip), %rcx
; CHECK-NEXT: movq (%rcx), %rdx
; CHECK-NEXT: xorl %esi, %esi
; CHECK-NEXT: movq %rax, %rcx
; CHECK-NEXT: .LBB15_1: # %loop.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: addq $8, %rcx
; CHECK-NEXT: cmpq %rdx, %rcx
; CHECK-NEXT: ja .LBB15_3
; CHECK-NEXT: # %bb.2: # %loop.body
; CHECK-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-NEXT: movq (%r8), %rcx
; CHECK-NEXT: .LBB15_3: # %loop.body
; CHECK-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-NEXT: movl %edi, (%rcx)
; CHECK-NEXT: addq $8, %rcx
; CHECK-NEXT: cmpq %rdx, %rcx
; CHECK-NEXT: ja .LBB15_5
; CHECK-NEXT: # %bb.4: # %loop.body
; CHECK-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-NEXT: movq %rax, %rcx
; CHECK-NEXT: .LBB15_5: # %loop.body
; CHECK-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-NEXT: movl %edi, (%rcx)
; CHECK-NEXT: addl $1, %esi
; CHECK-NEXT: cmpl $1024, %esi # imm = 0x400
; CHECK-NEXT: jl .LBB15_1
; CHECK-NEXT: # %bb.6: # %exit
; CHECK-NEXT: retq
;
; CHECK-FORCEALL-LABEL: test_memoperand_loop:
; CHECK-FORCEALL: # %bb.0: # %entry
; CHECK-FORCEALL-NEXT: movq begin@GOTPCREL(%rip), %r8
; CHECK-FORCEALL-NEXT: movq (%r8), %rax
; CHECK-FORCEALL-NEXT: movq end@GOTPCREL(%rip), %rcx
; CHECK-FORCEALL-NEXT: movq (%rcx), %rdx
; CHECK-FORCEALL-NEXT: xorl %esi, %esi
; CHECK-FORCEALL-NEXT: movq %rax, %rcx
; CHECK-FORCEALL-NEXT: .LBB15_1: # %loop.body
; CHECK-FORCEALL-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-FORCEALL-NEXT: addq $8, %rcx
; CHECK-FORCEALL-NEXT: cmpq %rdx, %rcx
; CHECK-FORCEALL-NEXT: ja .LBB15_3
; CHECK-FORCEALL-NEXT: # %bb.2: # %loop.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-FORCEALL-NEXT: movq (%r8), %rcx
; CHECK-FORCEALL-NEXT: .LBB15_3: # %loop.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-FORCEALL-NEXT: movl %edi, (%rcx)
; CHECK-FORCEALL-NEXT: addq $8, %rcx
; CHECK-FORCEALL-NEXT: cmpq %rdx, %rcx
; CHECK-FORCEALL-NEXT: ja .LBB15_5
; CHECK-FORCEALL-NEXT: # %bb.4: # %loop.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-FORCEALL-NEXT: movq %rax, %rcx
; CHECK-FORCEALL-NEXT: .LBB15_5: # %loop.body
; CHECK-FORCEALL-NEXT: # in Loop: Header=BB15_1 Depth=1
; CHECK-FORCEALL-NEXT: movl %edi, (%rcx)
; CHECK-FORCEALL-NEXT: addl $1, %esi
; CHECK-FORCEALL-NEXT: cmpl $1024, %esi # imm = 0x400
; CHECK-FORCEALL-NEXT: jl .LBB15_1
; CHECK-FORCEALL-NEXT: # %bb.6: # %exit
; CHECK-FORCEALL-NEXT: retq
entry:
%begin = load ptr, ptr @begin, align 8
%end = load ptr, ptr @end, align 8
br label %loop.body
loop.body:
%phi.iv = phi i32 [ 0, %entry ], [ %iv.next, %loop.body ]
%phi.ptr = phi ptr [ %begin, %entry ], [ %dst2, %loop.body ]
%gep1 = getelementptr inbounds i32, ptr%phi.ptr, i64 2
%cmp1 = icmp ugt ptr %gep1, %end
%begin_dup = load ptr, ptr @begin, align 8
%dst1 = select i1 %cmp1, ptr %gep1, ptr %begin_dup
store i32 %data, ptr%dst1, align 4
%gep2 = getelementptr inbounds i32, ptr%dst1, i64 2
%cmp2 = icmp ugt ptr %gep2, %end
%dst2 = select i1 %cmp2, ptr %gep2, ptr %begin
store i32 %data, ptr%dst2, align 4
%iv.next = add i32 %phi.iv, 1
%cond = icmp slt i32 %iv.next, 1024
br i1 %cond, label %loop.body, label %exit
exit:
ret void
}
attributes #0 = {"target-cpu"="x86-64" "tune-cpu"="x86-64"}
!0 = !{}