HomePhabricator

[LV] Fix crash when computing max VF too early

Authored by c-rhodes on Jan 16 2021, 8:08 AM.

Description

[LV] Fix crash when computing max VF too early

D90687 introduced a crash:

llvm::LoopVectorizationCostModel::computeMaxVF(llvm::ElementCount, unsigned int):
  Assertion `WideningDecisions.empty() && Uniforms.empty() && Scalars.empty() &&
  "No decisions should have been taken at this point"' failed.

when compiling the following C code:

typedef struct {
char a;
} b;

b *c;
int d, e;

int f() {
  int g = 0;
  for (; d; d++) {
    e = 0;
    for (; e < c[d].a; e++)
      g++;
  }
  return g;
}

with:

clang -Os -target hexagon -mhvx -fvectorize -mv67 testcase.c -S -o -

This occurred since prior to D90687 computeFeasibleMaxVF would only be
called in computeMaxVF when a scalar epilogue was allowed, but now it's
always called. This causes the assert above since computeFeasibleMaxVF
collects all viable VFs larger than the default MaxVF, and for each VF
calculates the register usage which results in analysis being done the
assert above guards against. This can occur in computeFeasibleMaxVF if
TTI.shouldMaximizeVectorBandwidth and this target hook is implemented in
the hexagon backend to always return true.

Reported by @iajbar.

Reviewed By: fhahn

Differential Revision: https://reviews.llvm.org/D94869

Details

Committed
c-rhodesFeb 1 2021, 4:14 AM
Reviewer
fhahn
Differential Revision
D94869: [LV] Fix crash when computing max VF too early
Parents
rG3b8a1d581e6e: NFC: Migrate SpeculativeExecution to work on InstructionCost
Branches
Unknown
Tags
Unknown