}
define void @fpcmp_unanalyzable_branch(i1 %cond) {
+; This function's CFG contains an unanalyzable branch that is likely to be
+; split due to having a different high-probability predecessor.
+; CHECK: fpcmp_unanalyzable_branch
+; CHECK: %entry
+; CHECK: %exit
+; CHECK-NOT: %if.then
+; CHECK-NOT: %if.end
+; CHECK-NOT: jne
+; CHECK-NOT: jnp
+; CHECK: jne
+; CHECK-NEXT: jnp
+; CHECK-NEXT: %if.then
+
entry:
- br i1 %cond, label %entry.if.then_crit_edge, label %lor.lhs.false
+; Note that this branch must be strongly biased toward
+; 'entry.if.then_crit_edge' to ensure that we would try to form a chain for
+; 'entry' -> 'entry.if.then_crit_edge' -> 'if.then'. It is the last edge in that
+; chain which would violate the unanalyzable branch in 'exit', but we won't even
+; try this trick unless 'if.then' is believed to almost always be reached from
+; 'entry.if.then_crit_edge'.
+ br i1 %cond, label %entry.if.then_crit_edge, label %lor.lhs.false, !prof !1
entry.if.then_crit_edge:
%.pre14 = load i8* undef, align 1, !tbaa !0
if.end:
ret void
}
+
+!1 = metadata !{metadata !"branch_weights", i32 1000, i32 1}
+
+declare i32 @f()
+declare i32 @g()
+declare i32 @h(i32 %x)
+
+define i32 @test_global_cfg_break_profitability() {
+; Check that our metrics for the profitability of a CFG break are global rather
+; than local. A successor may be very hot, but if the current block isn't, it
+; doesn't matter. Within this test the 'then' block is slightly warmer than the
+; 'else' block, but not nearly enough to merit merging it with the exit block
+; even though the probability of 'then' branching to the 'exit' block is very
+; high.
+; CHECK: test_global_cfg_break_profitability
+; CHECK: calll {{_?}}f
+; CHECK: calll {{_?}}g
+; CHECK: calll {{_?}}h
+; CHECK: ret
+
+entry:
+ br i1 undef, label %then, label %else, !prof !2
+
+then:
+ %then.result = call i32 @f()
+ br label %exit
+
+else:
+ %else.result = call i32 @g()
+ br label %exit
+
+exit:
+ %result = phi i32 [ %then.result, %then ], [ %else.result, %else ]
+ %result2 = call i32 @h(i32 %result)
+ ret i32 %result
+}
+
+!2 = metadata !{metadata !"branch_weights", i32 3, i32 1}
+
+declare i32 @__gxx_personality_v0(...)
+
+define void @test_eh_lpad_successor() {
+; Some times the landing pad ends up as the first successor of an invoke block.
+; When this happens, a strange result used to fall out of updateTerminators: we
+; didn't correctly locate the fallthrough successor, assuming blindly that the
+; first one was the fallthrough successor. As a result, we would add an
+; erroneous jump to the landing pad thinking *that* was the default successor.
+; CHECK: test_eh_lpad_successor
+; CHECK: %entry
+; CHECK-NOT: jmp
+; CHECK: %loop
+
+entry:
+ invoke i32 @f() to label %preheader unwind label %lpad
+
+preheader:
+ br label %loop
+
+lpad:
+ %lpad.val = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
+ cleanup
+ resume { i8*, i32 } %lpad.val
+
+loop:
+ br label %loop
+}
+
+declare void @fake_throw() noreturn
+
+define void @test_eh_throw() {
+; For blocks containing a 'throw' (or similar functionality), we have
+; a no-return invoke. In this case, only EH successors will exist, and
+; fallthrough simply won't occur. Make sure we don't crash trying to update
+; terminators for such constructs.
+;
+; CHECK: test_eh_throw
+; CHECK: %entry
+; CHECK: %cleanup
+
+entry:
+ invoke void @fake_throw() to label %continue unwind label %cleanup
+
+continue:
+ unreachable
+
+cleanup:
+ %0 = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
+ cleanup
+ unreachable
+}
+
+define void @test_unnatural_cfg_backwards_inner_loop() {
+; Test that when we encounter an unnatural CFG structure after having formed
+; a chain for an inner loop which happened to be laid out backwards we don't
+; attempt to merge onto the wrong end of the inner loop just because we find it
+; first. This was reduced from a crasher in GCC's single source.
+;
+; CHECK: test_unnatural_cfg_backwards_inner_loop
+; CHECK: %entry
+; CHECK: %body
+; CHECK: %loop1
+; CHECK: %loop2b
+; CHECK: %loop2a
+
+entry:
+ br i1 undef, label %loop2a, label %body
+
+body:
+ br label %loop2a
+
+loop1:
+ %next.load = load i32** undef
+ br i1 %comp.a, label %loop2a, label %loop2b
+
+loop2a:
+ %var = phi i32* [ null, %entry ], [ null, %body ], [ %next.phi, %loop1 ]
+ %next.var = phi i32* [ null, %entry ], [ undef, %body ], [ %next.load, %loop1 ]
+ %comp.a = icmp eq i32* %var, null
+ br label %loop3
+
+loop2b:
+ %gep = getelementptr inbounds i32* %var.phi, i32 0
+ %next.ptr = bitcast i32* %gep to i32**
+ store i32* %next.phi, i32** %next.ptr
+ br label %loop3
+
+loop3:
+ %var.phi = phi i32* [ %next.phi, %loop2b ], [ %var, %loop2a ]
+ %next.phi = phi i32* [ %next.load, %loop2b ], [ %next.var, %loop2a ]
+ br label %loop1
+}
+
+define void @unanalyzable_branch_to_loop_header() {
+; Ensure that we can handle unanalyzable branches into loop headers. We
+; pre-form chains for unanalyzable branches, and will find the tail end of that
+; at the start of the loop. This function uses floating point comparison
+; fallthrough because that happens to always produce unanalyzable branches on
+; x86.
+;
+; CHECK: unanalyzable_branch_to_loop_header
+; CHECK: %entry
+; CHECK: %loop
+; CHECK: %exit
+
+entry:
+ %cmp = fcmp une double 0.000000e+00, undef
+ br i1 %cmp, label %loop, label %exit
+
+loop:
+ %cond = icmp eq i8 undef, 42
+ br i1 %cond, label %exit, label %loop
+
+exit:
+ ret void
+}
+
projects / oota-llvm.git / blobdiff