6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-13 20:32:21 +00:00
Code Issues Projects Releases Wiki Activity
f710fb14ee
llvm-6502/test/Transforms/SROA/phi-and-select.ll
Chandler Carruth 77c1270033 Refactor the PartitionUse structure to actually use the Use* instead of 
a pair of instructions, one for the used pointer and the second for the
user. This simplifies the representation and also makes it more dense.

This was noticed because of the miscompile in PR13926. In that case, we
were running up against a fundamental "bad idea" in the speculation of
PHI and select instructions: the speculation and rewriting are
interleaved, which requires phi speculation to also perform load
rewriting! This is bad, and causes us to miss opportunities to do (for
example) vector rewriting only exposed after PHI speculation, etc etc.
It also, in the old system, required us to insert *new* load uses into
the current partition's use list, which would then be ignored during
rewriting because we had already extracted an end iterator for the use
list. The appending behavior (and much of the other oddities) stem from
the strange de-duplication strategy in the PartitionUse builder.
Amusingly, all this went without notice for so long because it could
only be triggered by having *different* GEPs into the same partition of
the same alloca, where both different GEPs were operands of a single
PHI, and where the GEP which was not encountered first also had multiple
uses within that same PHI node... Hence the insane steps required to
reproduce.

So, step one in fixing this fundamental bad idea is to make the
PartitionUse actually contain a Use*, and to make the builder do proper
deduplication instead of funky de-duplication. This is enough to remove
the appending behavior, and fix the miscompile in PR13926, but there is
more work to be done here. Subsequent commits will lift the speculation
into its own visitor. It'll be a useful step toward potentially
extracting all of the speculation logic into a generic utility
transform.

The existing PHI test case for repeated operands has been made more
extreme to catch even these issues. This test case, run through the old
pass, will exactly reproduce the miscompile from PR13926. ;] We were so
close here!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@164925 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-01 01:49:22 +00:00

393 lines
9.2 KiB
LLVM
Raw Blame History

; RUN: opt < %s -sroa -S | FileCheck %s
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"
define i32 @test1() {
; CHECK: @test1
entry:
%a = alloca [2 x i32]
; CHECK-NOT: alloca
%a0 = getelementptr [2 x i32]* %a, i64 0, i32 0
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 0, i32* %a0
store i32 1, i32* %a1
%v0 = load i32* %a0
%v1 = load i32* %a1
; CHECK-NOT: store
; CHECK-NOT: load
%cond = icmp sle i32 %v0, %v1
br i1 %cond, label %then, label %exit
then:
br label %exit
exit:
%phi = phi i32* [ %a1, %then ], [ %a0, %entry ]
; CHECK: phi i32 [ 1, %{{.*}} ], [ 0, %{{.*}} ]
%result = load i32* %phi
ret i32 %result
}
define i32 @test2() {
; CHECK: @test2
entry:
%a = alloca [2 x i32]
; CHECK-NOT: alloca
%a0 = getelementptr [2 x i32]* %a, i64 0, i32 0
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 0, i32* %a0
store i32 1, i32* %a1
%v0 = load i32* %a0
%v1 = load i32* %a1
; CHECK-NOT: store
; CHECK-NOT: load
%cond = icmp sle i32 %v0, %v1
%select = select i1 %cond, i32* %a1, i32* %a0
; CHECK: select i1 %{{.*}}, i32 1, i32 0
%result = load i32* %select
ret i32 %result
}
define i32 @test3(i32 %x) {
; CHECK: @test3
entry:
%a = alloca [2 x i32]
; CHECK-NOT: alloca
; Note that we build redundant GEPs here to ensure that having different GEPs
; into the same alloca partation continues to work with PHI speculation. This
; was the underlying cause of PR13926.
%a0 = getelementptr [2 x i32]* %a, i64 0, i32 0
%a0b = getelementptr [2 x i32]* %a, i64 0, i32 0
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
%a1b = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 0, i32* %a0
store i32 1, i32* %a1
; CHECK-NOT: store
switch i32 %x, label %bb0 [ i32 1, label %bb1
i32 2, label %bb2
i32 3, label %bb3
i32 4, label %bb4
i32 5, label %bb5
i32 6, label %bb6
i32 7, label %bb7 ]
bb0:
br label %exit
bb1:
br label %exit
bb2:
br label %exit
bb3:
br label %exit
bb4:
br label %exit
bb5:
br label %exit
bb6:
br label %exit
bb7:
br label %exit
exit:
%phi = phi i32* [ %a1, %bb0 ], [ %a0, %bb1 ], [ %a0, %bb2 ], [ %a1, %bb3 ],
[ %a1b, %bb4 ], [ %a0b, %bb5 ], [ %a0b, %bb6 ], [ %a1b, %bb7 ]
; CHECK: phi i32 [ 1, %{{.*}} ], [ 0, %{{.*}} ], [ 0, %{{.*}} ], [ 1, %{{.*}} ], [ 1, %{{.*}} ], [ 0, %{{.*}} ], [ 0, %{{.*}} ], [ 1, %{{.*}} ]
%result = load i32* %phi
ret i32 %result
}
define i32 @test4() {
; CHECK: @test4
entry:
%a = alloca [2 x i32]
; CHECK-NOT: alloca
%a0 = getelementptr [2 x i32]* %a, i64 0, i32 0
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 0, i32* %a0
store i32 1, i32* %a1
%v0 = load i32* %a0
%v1 = load i32* %a1
; CHECK-NOT: store
; CHECK-NOT: load
%cond = icmp sle i32 %v0, %v1
%select = select i1 %cond, i32* %a0, i32* %a0
; CHECK-NOT: select
%result = load i32* %select
ret i32 %result
; CHECK: ret i32 0
}
define i32 @test5(i32* %b) {
; CHECK: @test5
entry:
%a = alloca [2 x i32]
; CHECK-NOT: alloca
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 1, i32* %a1
; CHECK-NOT: store
%select = select i1 true, i32* %a1, i32* %b
; CHECK-NOT: select
%result = load i32* %select
; CHECK-NOT: load
ret i32 %result
; CHECK: ret i32 1
}
declare void @f(i32*, i32*)
define i32 @test6(i32* %b) {
; CHECK: @test6
entry:
%a = alloca [2 x i32]
%c = alloca i32
; CHECK-NOT: alloca
%a1 = getelementptr [2 x i32]* %a, i64 0, i32 1
store i32 1, i32* %a1
%select = select i1 true, i32* %a1, i32* %b
%select2 = select i1 false, i32* %a1, i32* %b
%select3 = select i1 false, i32* %c, i32* %b
; CHECK: %[[select2:.*]] = select i1 false, i32* undef, i32* %b
; CHECK: %[[select3:.*]] = select i1 false, i32* undef, i32* %b
; Note, this would potentially escape the alloca pointer except for the
; constant folding of the select.
call void @f(i32* %select2, i32* %select3)
; CHECK: call void @f(i32* %[[select2]], i32* %[[select3]])
%result = load i32* %select
; CHECK-NOT: load
%dead = load i32* %c
ret i32 %result
; CHECK: ret i32 1
}
define i32 @test7() {
; CHECK: @test7
; CHECK-NOT: alloca
entry:
%X = alloca i32
br i1 undef, label %good, label %bad
good:
%Y1 = getelementptr i32* %X, i64 0
store i32 0, i32* %Y1
br label %exit
bad:
%Y2 = getelementptr i32* %X, i64 1
store i32 0, i32* %Y2
br label %exit
exit:
%P = phi i32* [ %Y1, %good ], [ %Y2, %bad ]
; CHECK: %[[phi:.*]] = phi i32 [ 0, %good ],
%Z2 = load i32* %P
ret i32 %Z2
; CHECK: ret i32 %[[phi]]
}
define i32 @test8(i32 %b, i32* %ptr) {
; Ensure that we rewrite allocas to the used type when that use is hidden by
; a PHI that can be speculated.
; CHECK: @test8
; CHECK-NOT: alloca
; CHECK-NOT: load
; CHECK: %[[value:.*]] = load i32* %ptr
; CHECK-NOT: load
; CHECK: %[[result:.*]] = phi i32 [ undef, %else ], [ %[[value]], %then ]
; CHECK-NEXT: ret i32 %[[result]]
entry:
%f = alloca float
%test = icmp ne i32 %b, 0
br i1 %test, label %then, label %else
then:
br label %exit
else:
%bitcast = bitcast float* %f to i32*
br label %exit
exit:
%phi = phi i32* [ %bitcast, %else ], [ %ptr, %then ]
%loaded = load i32* %phi, align 4
ret i32 %loaded
}
define i32 @test9(i32 %b, i32* %ptr) {
; Same as @test8 but for a select rather than a PHI node.
; CHECK: @test9
; CHECK-NOT: alloca
; CHECK-NOT: load
; CHECK: %[[value:.*]] = load i32* %ptr
; CHECK-NOT: load
; CHECK: %[[result:.*]] = select i1 %{{.*}}, i32 undef, i32 %[[value]]
; CHECK-NEXT: ret i32 %[[result]]
entry:
%f = alloca float
store i32 0, i32* %ptr
%test = icmp ne i32 %b, 0
%bitcast = bitcast float* %f to i32*
%select = select i1 %test, i32* %bitcast, i32* %ptr
%loaded = load i32* %select, align 4
ret i32 %loaded
}
define i32 @test10(i32 %b, i32* %ptr) {
; Don't try to promote allocas which are not elligible for it even after
; rewriting due to the necessity of inserting bitcasts when speculating a PHI
; node.
; CHECK: @test10
; CHECK: %[[alloca:.*]] = alloca
; CHECK: %[[argvalue:.*]] = load i32* %ptr
; CHECK: %[[cast:.*]] = bitcast double* %[[alloca]] to i32*
; CHECK: %[[allocavalue:.*]] = load i32* %[[cast]]
; CHECK: %[[result:.*]] = phi i32 [ %[[allocavalue]], %else ], [ %[[argvalue]], %then ]
; CHECK-NEXT: ret i32 %[[result]]
entry:
%f = alloca double
store double 0.0, double* %f
%test = icmp ne i32 %b, 0
br i1 %test, label %then, label %else
then:
br label %exit
else:
%bitcast = bitcast double* %f to i32*
br label %exit
exit:
%phi = phi i32* [ %bitcast, %else ], [ %ptr, %then ]
%loaded = load i32* %phi, align 4
ret i32 %loaded
}
define i32 @test11(i32 %b, i32* %ptr) {
; Same as @test10 but for a select rather than a PHI node.
; CHECK: @test11
; CHECK: %[[alloca:.*]] = alloca
; CHECK: %[[cast:.*]] = bitcast double* %[[alloca]] to i32*
; CHECK: %[[allocavalue:.*]] = load i32* %[[cast]]
; CHECK: %[[argvalue:.*]] = load i32* %ptr
; CHECK: %[[result:.*]] = select i1 %{{.*}}, i32 %[[allocavalue]], i32 %[[argvalue]]
; CHECK-NEXT: ret i32 %[[result]]
entry:
%f = alloca double
store double 0.0, double* %f
store i32 0, i32* %ptr
%test = icmp ne i32 %b, 0
%bitcast = bitcast double* %f to i32*
%select = select i1 %test, i32* %bitcast, i32* %ptr
%loaded = load i32* %select, align 4
ret i32 %loaded
}
define i32 @test12(i32 %x, i32* %p) {
; Ensure we don't crash or fail to nuke dead selects of allocas if no load is
; never found.
; CHECK: @test12
; CHECK-NOT: alloca
; CHECK-NOT: select
; CHECK: ret i32 %x
entry:
%a = alloca i32
store i32 %x, i32* %a
%dead = select i1 undef, i32* %a, i32* %p
%load = load i32* %a
ret i32 %load
}
define i32 @test13(i32 %x, i32* %p) {
; Ensure we don't crash or fail to nuke dead phis of allocas if no load is ever
; found.
; CHECK: @test13
; CHECK-NOT: alloca
; CHECK-NOT: phi
; CHECK: ret i32 %x
entry:
%a = alloca i32
store i32 %x, i32* %a
br label %loop
loop:
%phi = phi i32* [ %p, %entry ], [ %a, %loop ]
br i1 undef, label %loop, label %exit
exit:
%load = load i32* %a
ret i32 %load
}
define i32 @PR13905() {
; Check a pattern where we have a chain of dead phi nodes to ensure they are
; deleted and promotion can proceed.
; CHECK: @PR13905
; CHECK-NOT: alloca i32
; CHECK: ret i32 undef
entry:
%h = alloca i32
store i32 0, i32* %h
br i1 undef, label %loop1, label %exit
loop1:
%phi1 = phi i32* [ null, %entry ], [ %h, %loop1 ], [ %h, %loop2 ]
br i1 undef, label %loop1, label %loop2
loop2:
br i1 undef, label %loop1, label %exit
exit:
%phi2 = phi i32* [ %phi1, %loop2 ], [ null, %entry ]
ret i32 undef
}
define i32 @PR13906() {
; Another pattern which can lead to crashes due to failing to clear out dead
; PHI nodes or select nodes. This triggers subtly differently from the above
; cases because the PHI node is (recursively) alive, but the select is dead.
; CHECK: @PR13906
; CHECK-NOT: alloca
entry:
%c = alloca i32
store i32 0, i32* %c
br label %for.cond
for.cond:
%d.0 = phi i32* [ undef, %entry ], [ %c, %if.then ], [ %d.0, %for.cond ]
br i1 undef, label %if.then, label %for.cond
if.then:
%tmpcast.d.0 = select i1 undef, i32* %c, i32* %d.0
br label %for.cond
}
Reference in New Issue View Git Blame Copy Permalink