RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
Code Issues Projects Releases Wiki Activity
llvm-mirror/test/Transforms/SimplifyCFG/sink-common-code.ll

568 lines
12 KiB
LLVM
Raw Normal View History

SimplifyCFG: sink common codes from IF, ELSE blocks down to END block. We already have HoistThenElseCodeToIf, this patch implements SinkThenElseCodeToEnd. When END block has only two predecessors and each predecessor terminates with unconditional branches, we compare instructions in IF and ELSE blocks backwards and check whether we can sink the common instructions down. rdar://12191395 llvm-svn: 164325
2012-09-20 22:37:36 +00:00
; RUN: opt < %s -simplifycfg -S | FileCheck %s
define zeroext i1 @test1(i1 zeroext %flag, i32 %blksA, i32 %blksB, i32 %nblks) {
entry:
br i1 %flag, label %if.then, label %if.else
[SimplifyCFG] Revise common code sinking - Fix the case where more than 1 common instructions derived from the same operand cannot be sunk. When a pair of value has more than 1 derived values in both branches, only 1 derived value could be sunk. - Replace BB1 -> (BB2, PN) map with joint value map, i.e. map of (BB1, BB2) -> PN, which is more accurate to track common ops. llvm-svn: 224757
2014-12-23 08:26:55 +00:00
; CHECK-LABEL: test1
SimplifyCFG: sink common codes from IF, ELSE blocks down to END block. We already have HoistThenElseCodeToIf, this patch implements SinkThenElseCodeToEnd. When END block has only two predecessors and each predecessor terminates with unconditional branches, we compare instructions in IF and ELSE blocks backwards and check whether we can sink the common instructions down. rdar://12191395 llvm-svn: 164325
2012-09-20 22:37:36 +00:00
; CHECK: add
; CHECK: select
; CHECK: icmp
; CHECK-NOT: br
if.then:
%cmp = icmp uge i32 %blksA, %nblks
%frombool1 = zext i1 %cmp to i8
br label %if.end
if.else:
%add = add i32 %nblks, %blksB
%cmp2 = icmp ule i32 %add, %blksA
%frombool3 = zext i1 %cmp2 to i8
br label %if.end
if.end:
%obeys.0 = phi i8 [ %frombool1, %if.then ], [ %frombool3, %if.else ]
%tobool4 = icmp ne i8 %obeys.0, 0
ret i1 %tobool4
}
define zeroext i1 @test2(i1 zeroext %flag, i32 %blksA, i32 %blksB, i32 %nblks) {
entry:
br i1 %flag, label %if.then, label %if.else
[SimplifyCFG] Revise common code sinking - Fix the case where more than 1 common instructions derived from the same operand cannot be sunk. When a pair of value has more than 1 derived values in both branches, only 1 derived value could be sunk. - Replace BB1 -> (BB2, PN) map with joint value map, i.e. map of (BB1, BB2) -> PN, which is more accurate to track common ops. llvm-svn: 224757
2014-12-23 08:26:55 +00:00
; CHECK-LABEL: test2
SimplifyCFG: sink common codes from IF, ELSE blocks down to END block. We already have HoistThenElseCodeToIf, this patch implements SinkThenElseCodeToEnd. When END block has only two predecessors and each predecessor terminates with unconditional branches, we compare instructions in IF and ELSE blocks backwards and check whether we can sink the common instructions down. rdar://12191395 llvm-svn: 164325
2012-09-20 22:37:36 +00:00
; CHECK: add
; CHECK: select
; CHECK: icmp
; CHECK-NOT: br
if.then:
%cmp = icmp uge i32 %blksA, %nblks
%frombool1 = zext i1 %cmp to i8
br label %if.end
if.else:
%add = add i32 %nblks, %blksB
%cmp2 = icmp uge i32 %blksA, %add
%frombool3 = zext i1 %cmp2 to i8
br label %if.end
if.end:
%obeys.0 = phi i8 [ %frombool1, %if.then ], [ %frombool3, %if.else ]
%tobool4 = icmp ne i8 %obeys.0, 0
ret i1 %tobool4
}
[SimplifyCFG] Revise common code sinking - Fix the case where more than 1 common instructions derived from the same operand cannot be sunk. When a pair of value has more than 1 derived values in both branches, only 1 derived value could be sunk. - Replace BB1 -> (BB2, PN) map with joint value map, i.e. map of (BB1, BB2) -> PN, which is more accurate to track common ops. llvm-svn: 224757
2014-12-23 08:26:55 +00:00
declare i32 @foo(i32, i32) nounwind readnone
define i32 @test3(i1 zeroext %flag, i32 %x, i32 %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%x0 = call i32 @foo(i32 %x, i32 0) nounwind readnone
%y0 = call i32 @foo(i32 %x, i32 1) nounwind readnone
br label %if.end
if.else:
%x1 = call i32 @foo(i32 %y, i32 0) nounwind readnone
%y1 = call i32 @foo(i32 %y, i32 1) nounwind readnone
br label %if.end
if.end:
%xx = phi i32 [ %x0, %if.then ], [ %x1, %if.else ]
%yy = phi i32 [ %y0, %if.then ], [ %y1, %if.else ]
%ret = add i32 %xx, %yy
ret i32 %ret
}
; CHECK-LABEL: test3
; CHECK: select
; CHECK: call
; CHECK: call
; CHECK: add
; CHECK-NOT: br
[SimplifyCFG] Rewrite SinkThenElseCodeToEnd [Recommitting now an unrelated assertion in SROA is sorted out] The new version has several advantages: 1) IMSHO it's more readable and neater 2) It handles loads and stores properly 3) It can handle any number of incoming blocks rather than just two. I'll be taking advantage of this in a followup patch. With this change we can now finally sink load-modify-store idioms such as: if (a) return *b += 3; else return *b += 4; => %z = load i32, i32* %y %.sink = select i1 %a, i32 5, i32 7 %b = add i32 %z, %.sink store i32 %b, i32* %y ret i32 %b When this works for switches it'll be even more powerful. Round 4. This time we should handle all instructions correctly, and not replace any operands that need to be constant with variables. This was really hard to determine safely, so the helper function should be put into the Instruction API. I'll do that as a followup. llvm-svn: 279460
2016-08-22 19:07:15 +00:00
define i32 @test4(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%a = add i32 %x, 5
store i32 %a, i32* %y
br label %if.end
if.else:
%b = add i32 %x, 7
store i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test4
; CHECK: select
; CHECK: store
; CHECK-NOT: store
define i32 @test5(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%a = add i32 %x, 5
store volatile i32 %a, i32* %y
br label %if.end
if.else:
%b = add i32 %x, 7
store i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test5
; CHECK: store volatile
; CHECK: store
define i32 @test6(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%a = add i32 %x, 5
store volatile i32 %a, i32* %y
br label %if.end
if.else:
%b = add i32 %x, 7
store volatile i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test6
; CHECK: select
; CHECK: store volatile
; CHECK-NOT: store
define i32 @test7(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%z = load volatile i32, i32* %y
%a = add i32 %z, 5
store volatile i32 %a, i32* %y
br label %if.end
if.else:
%w = load volatile i32, i32* %y
%b = add i32 %w, 7
store volatile i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test7
; CHECK-DAG: select
; CHECK-DAG: load volatile
; CHECK: store volatile
; CHECK-NOT: load
; CHECK-NOT: store
; %z and %w are in different blocks. We shouldn't sink the add because
; there may be intervening memory instructions.
define i32 @test8(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
%z = load volatile i32, i32* %y
br i1 %flag, label %if.then, label %if.else
if.then:
%a = add i32 %z, 5
store volatile i32 %a, i32* %y
br label %if.end
if.else:
%w = load volatile i32, i32* %y
%b = add i32 %w, 7
store volatile i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test8
; CHECK: add
; CHECK: add
; The extra store in %if.then means %z and %w are not equivalent.
define i32 @test9(i1 zeroext %flag, i32 %x, i32* %y, i32* %p) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
store i32 7, i32* %p
%z = load volatile i32, i32* %y
store i32 6, i32* %p
%a = add i32 %z, 5
store volatile i32 %a, i32* %y
br label %if.end
if.else:
%w = load volatile i32, i32* %y
%b = add i32 %w, 7
store volatile i32 %b, i32* %y
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test9
; CHECK: add
; CHECK: add
%struct.anon = type { i32, i32 }
; The GEP indexes a struct type so cannot have a variable last index.
define i32 @test10(i1 zeroext %flag, i32 %x, i32* %y, %struct.anon* %s) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%dummy = add i32 %x, 5
%gepa = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 0
store volatile i32 %x, i32* %gepa
br label %if.end
if.else:
%dummy1 = add i32 %x, 6
%gepb = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 1
store volatile i32 %x, i32* %gepb
br label %if.end
if.end:
ret i32 1
}
; CHECK-LABEL: test10
; CHECK: getelementptr
; CHECK: getelementptr
; CHECK: phi
; CHECK: store volatile
; The shufflevector's mask operand cannot be merged in a PHI.
define i32 @test11(i1 zeroext %flag, i32 %w, <2 x i32> %x, <2 x i32> %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%dummy = add i32 %w, 5
%sv1 = shufflevector <2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 0, i32 1>
br label %if.end
if.else:
%dummy1 = add i32 %w, 6
%sv2 = shufflevector <2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 1, i32 0>
br label %if.end
if.end:
%p = phi <2 x i32> [ %sv1, %if.then ], [ %sv2, %if.else ]
ret i32 1
}
; CHECK-LABEL: test11
; CHECK: shufflevector
; CHECK: shufflevector
; We can't common an intrinsic!
define i32 @test12(i1 zeroext %flag, i32 %w, i32 %x, i32 %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%dummy = add i32 %w, 5
%sv1 = call i32 @llvm.ctlz.i32(i32 %x)
br label %if.end
if.else:
%dummy1 = add i32 %w, 6
%sv2 = call i32 @llvm.cttz.i32(i32 %x)
br label %if.end
if.end:
%p = phi i32 [ %sv1, %if.then ], [ %sv2, %if.else ]
ret i32 1
}
declare i32 @llvm.ctlz.i32(i32 %x) readnone
declare i32 @llvm.cttz.i32(i32 %x) readnone
; CHECK-LABEL: test12
; CHECK: call i32 @llvm.ctlz
; CHECK: call i32 @llvm.cttz
[SimplifyCFG] Properly CSE metadata in SinkThenElseCodeToEnd This was missing, meaning the metadata in sunk instructions was potentially bogus and could cause miscompiles. llvm-svn: 280072
2016-08-30 10:56:08 +00:00
; The TBAA metadata should be properly combined.
define i32 @test13(i1 zeroext %flag, i32 %x, i32* %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%z = load volatile i32, i32* %y
%a = add i32 %z, 5
store volatile i32 %a, i32* %y, !tbaa !3
br label %if.end
if.else:
%w = load volatile i32, i32* %y
%b = add i32 %w, 7
store volatile i32 %b, i32* %y, !tbaa !4
br label %if.end
if.end:
ret i32 1
}
!0 = !{ !"an example type tree" }
!1 = !{ !"int", !0 }
!2 = !{ !"float", !0 }
!3 = !{ !"const float", !2, i64 0 }
!4 = !{ !"special float", !2, i64 1 }
; CHECK-LABEL: test13
; CHECK-DAG: select
; CHECK-DAG: load volatile
; CHECK: store volatile {{.*}}, !tbaa !0
; CHECK-NOT: load
; CHECK-NOT: store
[SimplifyCFG] Tail-merge calls with sideeffects This was deliberately disabled during my rewrite of SinkIfThenToEnd to keep behaviour at least vaguely consistent with the previous version and keep it as close to NFC as I could. There's no real reason not to merge sideeffect calls though, so let's do it! Small fixup along the way to ensure we don't create indirect calls. Should fix PR28964. llvm-svn: 280215
2016-08-31 10:46:16 +00:00
; The call should be commoned.
define i32 @test13a(i1 zeroext %flag, i32 %w, i32 %x, i32 %y) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%sv1 = call i32 @bar(i32 %x)
br label %if.end
if.else:
%sv2 = call i32 @bar(i32 %y)
br label %if.end
if.end:
%p = phi i32 [ %sv1, %if.then ], [ %sv2, %if.else ]
ret i32 1
}
declare i32 @bar(i32)
; CHECK-LABEL: test13a
; CHECK: %[[x:.*]] = select i1 %flag
; CHECK: call i32 @bar(i32 %[[x]])
[SimplifyCFG] Change the algorithm in SinkThenElseCodeToEnd r279460 rewrote this function to be able to handle more than two incoming edges and took pains to ensure this didn't regress anything. This time we change the logic for determining if an instruction should be sunk. Previously we used a single pass greedy algorithm - sink instructions until one requires more than one PHI node or we run out of instructions to sink. This had the problem that sinking instructions that had non-identical but trivially the same operands needed extra logic so we sunk them aggressively. For example: %a = load i32* %b %d = load i32* %b %c = gep i32* %a, i32 0 %e = gep i32* %d, i32 1 Sinking %c and %e would naively require two PHI merges as %a != %d. But the loads are obviously equivalent (and maybe can't be hoisted because there is no common predecessor). This is why we implemented the fairly complex function areValuesTriviallySame(), to look through trivial differences like this. However it's just not clever enough. Instead, throw areValuesTriviallySame away, use pointer equality to check equivalence of operands and switch to a two-stage algorithm. In the "scan" stage, we look at every sinkable instruction in isolation from end of block to front. If it's sinkable, we keep track of all operands that required PHI merging. In the "sink" stage, we iteratively sink the last non-terminator in the source blocks. But when calculating how many PHIs are actually required to be inserted (to work out if we should stop or not) we remove any values that have already been sunk from the set of PHI-merges required, which allows us to be more aggressive. This turns an algorithm with potentially recursive lookahead (looking through GEPs, casts, loads and any other instruction potentially not CSE'd) to two linear scans. llvm-svn: 280351
2016-09-01 10:44:35 +00:00
; The load should be commoned.
define i32 @test14(i1 zeroext %flag, i32 %w, i32 %x, i32 %y, %struct.anon* %s) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%dummy = add i32 %x, 1
%gepa = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 1
%sv1 = load i32, i32* %gepa
%cmp1 = icmp eq i32 %sv1, 56
br label %if.end
if.else:
%dummy2 = add i32 %x, 4
%gepb = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 1
%sv2 = load i32, i32* %gepb
%cmp2 = icmp eq i32 %sv2, 57
br label %if.end
if.end:
%p = phi i1 [ %cmp1, %if.then ], [ %cmp2, %if.else ]
ret i32 1
}
; CHECK-LABEL: test14
; CHECK: getelementptr
; CHECK: load
; CHECK-NOT: load
; The load should be commoned.
define i32 @test15(i1 zeroext %flag, i32 %w, i32 %x, i32 %y, %struct.anon* %s) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%dummy = add i32 %x, 1
%gepa = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 0
%sv1 = load i32, i32* %gepa
%ext1 = zext i32 %sv1 to i64
%cmp1 = icmp eq i64 %ext1, 56
br label %if.end
if.else:
%dummy2 = add i32 %x, 4
%gepb = getelementptr inbounds %struct.anon, %struct.anon* %s, i32 0, i32 1
%sv2 = load i32, i32* %gepb
%ext2 = zext i32 %sv2 to i64
%cmp2 = icmp eq i64 %ext2, 57
br label %if.end
if.end:
%p = phi i1 [ %cmp1, %if.then ], [ %cmp2, %if.else ]
ret i32 1
}
; CHECK-LABEL: test15
; CHECK: getelementptr
; CHECK: load
; CHECK-NOT: load
define zeroext i1 @test_crash(i1 zeroext %flag, i32* %i4, i32* %m, i32* %n) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%tmp1 = load i32, i32* %i4
%tmp2 = add i32 %tmp1, -1
store i32 %tmp2, i32* %i4
br label %if.end
if.else:
%tmp3 = load i32, i32* %m
%tmp4 = load i32, i32* %n
%tmp5 = add i32 %tmp3, %tmp4
store i32 %tmp5, i32* %i4
br label %if.end
if.end:
ret i1 true
}
; CHECK-LABEL: test_crash
; No checks for test_crash - just ensure it doesn't crash!
[SimplifyCFG] Handle tail-sinking of more than 2 incoming branches This was a real restriction in the original version of SinkIfThenCodeToEnd. Now it's been rewritten, the restriction can be lifted. As part of this, we handle a very common and useful case where one of the incoming branches is actually conditional. Consider: if (a) x(1); else if (b) x(2); This produces the following CFG: [if] / \ [x(1)] [if] | | \ | | \ | [x(2)] | \ | / [ end ] [end] has two unconditional predecessor arcs and one conditional. The conditional refers to the implicit empty 'else' arc. This same pattern can also be caused by an empty default block in a switch. We can't sink the call to x() down to end because no call to x() happens on the third incoming arc (assume that x() has sideeffects for the sake of argument; if something is safe to speculate we could indeed sink nevertheless but this cannot happen in the general case and causes many extra selects). We are now able to detect this case and split off the unconditional arcs to a common successor: [if] / \ [x(1)] [if] | | \ | | \ | [x(2)] | \ / | [sink.split] | \ / [ end ] Now we can sink the call to x() into %sink.split. This can cause significant code simplification in many testcases. llvm-svn: 280364
2016-09-01 12:58:13 +00:00
define zeroext i1 @test16(i1 zeroext %flag, i1 zeroext %flag2, i32 %blksA, i32 %blksB, i32 %nblks) {
entry:
br i1 %flag, label %if.then, label %if.else
if.then:
%cmp = icmp uge i32 %blksA, %nblks
%frombool1 = zext i1 %cmp to i8
br label %if.end
if.else:
br i1 %flag2, label %if.then2, label %if.end
if.then2:
%add = add i32 %nblks, %blksB
%cmp2 = icmp ule i32 %add, %blksA
%frombool3 = zext i1 %cmp2 to i8
br label %if.end
if.end:
%obeys.0 = phi i8 [ %frombool1, %if.then ], [ %frombool3, %if.then2 ], [ 0, %if.else ]
%tobool4 = icmp ne i8 %obeys.0, 0
ret i1 %tobool4
}
; CHECK-LABEL: test16
; CHECK: zext
; CHECK-NOT: zext
define zeroext i1 @test17(i32 %flag, i32 %blksA, i32 %blksB, i32 %nblks) {
entry:
switch i32 %flag, label %if.end [
i32 0, label %if.then
i32 1, label %if.then2
]
if.then:
%cmp = icmp uge i32 %blksA, %nblks
%frombool1 = zext i1 %cmp to i8
br label %if.end
if.then2:
%add = add i32 %nblks, %blksB
%cmp2 = icmp ule i32 %add, %blksA
%frombool3 = zext i1 %cmp2 to i8
br label %if.end
if.end:
%obeys.0 = phi i8 [ %frombool1, %if.then ], [ %frombool3, %if.then2 ], [ 0, %entry ]
%tobool4 = icmp ne i8 %obeys.0, 0
ret i1 %tobool4
}
; CHECK-LABEL: test17
; CHECK: if.then:
; CHECK-NEXT: icmp uge
; CHECK-NEXT: br label %[[x:.*]]
; CHECK: if.then2:
; CHECK-NEXT: add
; CHECK-NEXT: icmp ule
; CHECK-NEXT: br label %[[x]]
; CHECK: [[x]]:
; CHECK-NEXT: %[[y:.*]] = phi i1 [ %cmp
; CHECK-NEXT: %[[z:.*]] = zext i1 %[[y]]
; CHECK-NEXT: br label %if.end
; CHECK: if.end:
; CHECK-NEXT: phi i8
; CHECK-DAG: [ %[[z]], %[[x]] ]
; CHECK-DAG: [ 0, %entry ]
define zeroext i1 @test18(i32 %flag, i32 %blksA, i32 %blksB, i32 %nblks) {
entry:
switch i32 %flag, label %if.then3 [
i32 0, label %if.then
i32 1, label %if.then2
]
if.then:
%cmp = icmp uge i32 %blksA, %nblks
%frombool1 = zext i1 %cmp to i8
br label %if.end
if.then2:
%add = add i32 %nblks, %blksB
%cmp2 = icmp ule i32 %add, %blksA
%frombool3 = zext i1 %cmp2 to i8
br label %if.end
if.then3:
%add2 = add i32 %nblks, %blksA
%cmp3 = icmp ule i32 %add2, %blksA
%frombool4 = zext i1 %cmp3 to i8
br label %if.end
if.end:
%obeys.0 = phi i8 [ %frombool1, %if.then ], [ %frombool3, %if.then2 ], [ %frombool4, %if.then3 ]
%tobool4 = icmp ne i8 %obeys.0, 0
ret i1 %tobool4
}
; CHECK-LABEL: test18
; CHECK: if.end:
; CHECK-NEXT: %[[x:.*]] = phi i1
; CHECK-DAG: [ %cmp, %if.then ]
; CHECK-DAG: [ %cmp2, %if.then2 ]
; CHECK-DAG: [ %cmp3, %if.then3 ]
; CHECK-NEXT: zext i1 %[[x]] to i8
[SimplifyCFG] Properly CSE metadata in SinkThenElseCodeToEnd This was missing, meaning the metadata in sunk instructions was potentially bogus and could cause miscompiles. llvm-svn: 280072
2016-08-30 10:56:08 +00:00
; CHECK: !0 = !{!1, !1, i64 0}
; CHECK: !1 = !{!"float", !2}
[SimplifyCFG] Tail-merge calls with sideeffects This was deliberately disabled during my rewrite of SinkIfThenToEnd to keep behaviour at least vaguely consistent with the previous version and keep it as close to NFC as I could. There's no real reason not to merge sideeffect calls though, so let's do it! Small fixup along the way to ensure we don't create indirect calls. Should fix PR28964. llvm-svn: 280215
2016-08-31 10:46:16 +00:00
; CHECK: !2 = !{!"an example type tree"}
Reference in New Issue Copy Permalink