bf789b1957
For the longest time we used `AAValueSimplify` and
`genericValueTraversal` to determine "potential values". This was
problematic for many reasons:
- We recomputed the result a lot as there was no caching for the 9
locations calling `genericValueTraversal`.
- We added the idea of "intra" vs. "inter" procedural simplification
only as an afterthought. `genericValueTraversal` did offer an option
but `AAValueSimplify` did not. Thus, we might end up with "too much"
simplification in certain situations and then gave up on it.
- Because `genericValueTraversal` was not a real `AA` we ended up with
problems like the infinite recursion bug (#54981) as well as code
duplication.
This patch introduces `AAPotentialValues` and replaces the
`AAValueSimplify` uses with it. `genericValueTraversal` is folded into
`AAPotentialValues` as are the instruction simplifications performed in
`AAValueSimplify` before. We further distinguish "intra" and "inter"
procedural simplification now.
`AAValueSimplify` was not deleted as we haven't ported the
re-materialization of instructions yet. There are other differences over
the former handling, e.g., we may not fold trivially foldable
instructions right now, e.g., `add i32 1, 1` is not folded to `i32 2`
but if an operand would be simplified to `i32 1` we would fold it still.
We are also even more aware of function/SCC boundaries in CGSCC passes,
which is good even if some tests look like they regress.
Fixes: https://github.com/llvm/llvm-project/issues/54981
Note: A previous version was flawed and consequently reverted in
6555558a80.
159 lines
7.7 KiB
LLVM
159 lines
7.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes --check-globals
|
|
; call site specific analysis is enabled
|
|
|
|
; RUN: opt -attributor -enable-new-pm=0 -attributor-enable-call-site-specific-deduction=true -attributor-manifest-internal -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=2 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_NPM,NOT_CGSCC_OPM,NOT_TUNIT_NPM,IS__TUNIT____,IS________OPM,IS__TUNIT_OPM
|
|
|
|
; RUN: opt -aa-pipeline=basic-aa -passes=attributor -attributor-enable-call-site-specific-deduction=true -attributor-manifest-internal -attributor-max-iterations-verify -attributor-annotate-decl-cs -attributor-max-iterations=2 -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_CGSCC_OPM,NOT_CGSCC_NPM,NOT_TUNIT_OPM,IS__TUNIT____,IS________NPM,IS__TUNIT_NPM
|
|
|
|
; RUN: opt -attributor-cgscc -attributor-enable-call-site-specific-deduction=true -enable-new-pm=0 -attributor-manifest-internal -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_NPM,IS__CGSCC____,IS________OPM,IS__CGSCC_OPM
|
|
|
|
; RUN: opt -aa-pipeline=basic-aa -passes=attributor-cgscc -attributor-enable-call-site-specific-deduction=true -attributor-manifest-internal -attributor-annotate-decl-cs -S < %s | FileCheck %s --check-prefixes=CHECK,NOT_TUNIT_NPM,NOT_TUNIT_OPM,NOT_CGSCC_OPM,IS__CGSCC____,IS________NPM,IS__CGSCC_NPM
|
|
|
|
define i32 @test_range(i32 %unknown) {
|
|
; CHECK-LABEL: define {{[^@]+}}@test_range
|
|
; CHECK-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[UNKNOWN]], 100
|
|
; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 100, i32 0
|
|
; CHECK-NEXT: ret i32 [[TMP2]]
|
|
;
|
|
%1 = icmp sgt i32 %unknown, 100
|
|
%2 = select i1 %1, i32 100, i32 0
|
|
ret i32 %2
|
|
}
|
|
|
|
define i32 @test1(i32 %unknown, i32 %b) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test1
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]], i32 [[B:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test_range(i32 [[UNKNOWN]])
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = sub nsw i32 [[TMP1]], [[B]]
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP2]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test1
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]], i32 [[B:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test_range(i32 [[UNKNOWN]])
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = sub nsw i32 [[TMP1]], [[B]]
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP2]]
|
|
;
|
|
%1 = call i32 @test_range(i32 %unknown)
|
|
%2 = sub nsw i32 %1, %b
|
|
ret i32 %2
|
|
}
|
|
|
|
define i32 @test2(i32 %unknown, i32 %b) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test2
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]], i32 [[B:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test_range(i32 [[UNKNOWN]])
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = add nsw i32 [[TMP1]], [[B]]
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP2]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test2
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]], i32 [[B:%.*]]) #[[ATTR1]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test_range(i32 [[UNKNOWN]])
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = add nsw i32 [[TMP1]], [[B]]
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP2]]
|
|
;
|
|
%1 = call i32 @test_range(i32 %unknown)
|
|
%2 = add nsw i32 %1, %b
|
|
ret i32 %2
|
|
}
|
|
|
|
; Positive checks
|
|
|
|
; FIXME: AAValueSimplify preserves the context but simplifies to a value in the other function, I think.
|
|
; Either way, as we settle on the new AAValueSimplifyReturned scheme that replaces AAReturnedValues
|
|
; we need to look into this again. For the purpose of making some progress we take this regression
|
|
; for now, call site contexts are not on by default anyway (yet).
|
|
define i32 @test1_pcheck(i32 %unknown) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test1_pcheck
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test1(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = icmp sle i32 [[TMP1]], 90
|
|
; IS__TUNIT____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test1_pcheck
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR1]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test1(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = icmp sle i32 [[TMP1]], 90
|
|
; IS__CGSCC____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
%1 = call i32 @test1(i32 %unknown, i32 20)
|
|
%2 = icmp sle i32 %1, 90
|
|
%3 = zext i1 %2 to i32
|
|
ret i32 %3
|
|
}
|
|
|
|
define i32 @test2_pcheck(i32 %unknown) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test2_pcheck
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test2(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = icmp sge i32 [[TMP1]], 20
|
|
; IS__TUNIT____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test2_pcheck
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR1]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test2(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = icmp sge i32 [[TMP1]], 20
|
|
; IS__CGSCC____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
%1 = call i32 @test2(i32 %unknown, i32 20)
|
|
%2 = icmp sge i32 %1, 20
|
|
%3 = zext i1 %2 to i32
|
|
ret i32 %3
|
|
}
|
|
|
|
; Negative checks
|
|
|
|
define i32 @test1_ncheck(i32 %unknown) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test1_ncheck
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test1(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = icmp sle i32 [[TMP1]], 10
|
|
; IS__TUNIT____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test1_ncheck
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR1]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test1(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = icmp sle i32 [[TMP1]], 10
|
|
; IS__CGSCC____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
%1 = call i32 @test1(i32 %unknown, i32 20)
|
|
%2 = icmp sle i32 %1, 10
|
|
%3 = zext i1 %2 to i32
|
|
ret i32 %3
|
|
}
|
|
|
|
define i32 @test2_ncheck(i32 %unknown) {
|
|
; IS__TUNIT____-LABEL: define {{[^@]+}}@test2_ncheck
|
|
; IS__TUNIT____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR0]] {
|
|
; IS__TUNIT____-NEXT: [[TMP1:%.*]] = call i32 @test2(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__TUNIT____-NEXT: [[TMP2:%.*]] = icmp sge i32 [[TMP1]], 30
|
|
; IS__TUNIT____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__TUNIT____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
; IS__CGSCC____-LABEL: define {{[^@]+}}@test2_ncheck
|
|
; IS__CGSCC____-SAME: (i32 [[UNKNOWN:%.*]]) #[[ATTR1]] {
|
|
; IS__CGSCC____-NEXT: [[TMP1:%.*]] = call i32 @test2(i32 [[UNKNOWN]], i32 noundef 20)
|
|
; IS__CGSCC____-NEXT: [[TMP2:%.*]] = icmp sge i32 [[TMP1]], 30
|
|
; IS__CGSCC____-NEXT: [[TMP3:%.*]] = zext i1 [[TMP2]] to i32
|
|
; IS__CGSCC____-NEXT: ret i32 [[TMP3]]
|
|
;
|
|
%1 = call i32 @test2(i32 %unknown, i32 20)
|
|
%2 = icmp sge i32 %1, 30
|
|
%3 = zext i1 %2 to i32
|
|
ret i32 %3
|
|
}
|
|
;.
|
|
; IS__TUNIT____: attributes #[[ATTR0]] = { nofree norecurse nosync nounwind readnone willreturn }
|
|
; IS__TUNIT____: attributes #[[ATTR1:[0-9]+]] = { nofree nosync nounwind readnone willreturn }
|
|
;.
|
|
; IS__CGSCC____: attributes #[[ATTR0]] = { nofree norecurse nosync nounwind readnone willreturn }
|
|
; IS__CGSCC____: attributes #[[ATTR1]] = { nofree nosync nounwind readnone willreturn }
|
|
; IS__CGSCC____: attributes #[[ATTR2:[0-9]+]] = { readnone willreturn }
|
|
;.
|