RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-16 08:29:43 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Make use @llvm.assume for loop guards in ScalarEvolution

Browse Source 
This adds a basic (but important) use of @llvm.assume calls in ScalarEvolution.
When SE is attempting to validate a condition guarding a loop (such as whether
or not the loop count can be zero), this check should also include dominating
assumptions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217348 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hal Finkel 2014-09-07 21:37:59 +00:00
parent 1c0c67a007
commit 5f36b46bf0
2 changed files with 107 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
lib/Analysis/ScalarEvolution.cpp
View File

@ -6313,13 +6313,22 @@ ScalarEvolution::isLoopBackedgeGuardedByCond(const Loop *L,
BranchInst *LoopContinuePredicate =
dyn_cast<BranchInst>(Latch->getTerminator());
if (!LoopContinuePredicate ||
LoopContinuePredicate->isUnconditional())
return false;
return isImpliedCond(Pred, LHS, RHS,
if (LoopContinuePredicate && LoopContinuePredicate->isConditional() &&
isImpliedCond(Pred, LHS, RHS,
LoopContinuePredicate->getCondition(),
LoopContinuePredicate->getSuccessor(0) != L->getHeader());
LoopContinuePredicate->getSuccessor(0) != L->getHeader()))
return true;
// Check conditions due to any @llvm.assume intrinsics.
for (auto &CI : AT->assumptions(F)) {
if (!DT->dominates(CI, Latch->getTerminator()))
continue;
if (isImpliedCond(Pred, LHS, RHS, CI->getArgOperand(0), false))
return true;
}
return false;
}
/// isLoopEntryGuardedByCond - Test whether entry to the loop is protected
@ -6353,6 +6362,15 @@ ScalarEvolution::isLoopEntryGuardedByCond(const Loop *L,
return true;
}
// Check conditions due to any @llvm.assume intrinsics.
for (auto &CI : AT->assumptions(F)) {
if (!DT->dominates(CI, L->getHeader()))
continue;
if (isImpliedCond(Pred, LHS, RHS, CI->getArgOperand(0), false))
return true;
}
return false;
}

83
test/Analysis/ScalarEvolution/nsw-offset-assume.ll Normal file
View File

@ -0,0 +1,83 @@
; RUN: opt < %s -S -analyze -scalar-evolution | FileCheck %s
; ScalarEvolution should be able to fold away the sign-extensions
; on this loop with a primary induction variable incremented with
; a nsw add of 2 (this test is derived from the nsw-offset.ll test, but uses an
; assume instead of a preheader conditional branch to guard the loop).
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
define void @foo(i32 %no, double* nocapture %d, double* nocapture %q) nounwind {
entry:
%n = and i32 %no, 4294967294
%0 = icmp sgt i32 %n, 0 ; <i1> [#uses=1]
tail call void @llvm.assume(i1 %0)
br label %bb.nph
bb.nph: ; preds = %entry
br label %bb
bb: ; preds = %bb.nph, %bb1
%i.01 = phi i32 [ %16, %bb1 ], [ 0, %bb.nph ] ; <i32> [#uses=5]
; CHECK: %1 = sext i32 %i.01 to i64
; CHECK: --> {0,+,2}<nuw><nsw><%bb>
%1 = sext i32 %i.01 to i64 ; <i64> [#uses=1]
; CHECK: %2 = getelementptr inbounds double* %d, i64 %1
; CHECK: --> {%d,+,16}<nsw><%bb>
%2 = getelementptr inbounds double* %d, i64 %1 ; <double*> [#uses=1]
%3 = load double* %2, align 8 ; <double> [#uses=1]
%4 = sext i32 %i.01 to i64 ; <i64> [#uses=1]
%5 = getelementptr inbounds double* %q, i64 %4 ; <double*> [#uses=1]
%6 = load double* %5, align 8 ; <double> [#uses=1]
%7 = or i32 %i.01, 1 ; <i32> [#uses=1]
; CHECK: %8 = sext i32 %7 to i64
; CHECK: --> {1,+,2}<nuw><nsw><%bb>
%8 = sext i32 %7 to i64 ; <i64> [#uses=1]
; CHECK: %9 = getelementptr inbounds double* %q, i64 %8
; CHECK: {(8 + %q),+,16}<nsw><%bb>
%9 = getelementptr inbounds double* %q, i64 %8 ; <double*> [#uses=1]
; Artificially repeat the above three instructions, this time using
; add nsw instead of or.
%t7 = add nsw i32 %i.01, 1 ; <i32> [#uses=1]
; CHECK: %t8 = sext i32 %t7 to i64
; CHECK: --> {1,+,2}<nuw><nsw><%bb>
%t8 = sext i32 %t7 to i64 ; <i64> [#uses=1]
; CHECK: %t9 = getelementptr inbounds double* %q, i64 %t8
; CHECK: {(8 + %q),+,16}<nsw><%bb>
%t9 = getelementptr inbounds double* %q, i64 %t8 ; <double*> [#uses=1]
%10 = load double* %9, align 8 ; <double> [#uses=1]
%11 = fadd double %6, %10 ; <double> [#uses=1]
%12 = fadd double %11, 3.200000e+00 ; <double> [#uses=1]
%13 = fmul double %3, %12 ; <double> [#uses=1]
%14 = sext i32 %i.01 to i64 ; <i64> [#uses=1]
%15 = getelementptr inbounds double* %d, i64 %14 ; <double*> [#uses=1]
store double %13, double* %15, align 8
%16 = add nsw i32 %i.01, 2 ; <i32> [#uses=2]
br label %bb1
bb1: ; preds = %bb
%17 = icmp slt i32 %16, %n ; <i1> [#uses=1]
br i1 %17, label %bb, label %bb1.return_crit_edge
bb1.return_crit_edge: ; preds = %bb1
br label %return
return: ; preds = %bb1.return_crit_edge, %entry
ret void
}
declare void @llvm.assume(i1) nounwind
; Note: Without the preheader assume, there is an 'smax' in the
; backedge-taken count expression:
; CHECK: Loop %bb: backedge-taken count is ((-1 + (2 * (%no /u 2))) /u 2)
; CHECK: Loop %bb: max backedge-taken count is 1073741822