[LV] Forced vectorization with runtime checks and OptForSize

When vectorisation is forced with a pragma, we optimise for min size, and we
need to emit runtime memory checks, then allow this code growth and don't run
in an assert like we currently do.

This is the result of D65197 and D66803, and was a use-case not really
considered before. If this now happens, we emit an optimisation remark warning
about the code-size expansion, which can be avoided by not forcing
vectorisation or possibly source-code modifications.

Differential Revision: https://reviews.llvm.org/D67764

llvm-svn: 372694

Author: Sjoerd Meijer

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -2730,8 +2730,19 @@ void InnerLoopVectorizer::emitMemRuntimeChecks(Loop *L, BasicBlock *Bypass) {
   if (!MemRuntimeCheck)
     return;
 
-  assert(!BB->getParent()->hasOptSize() &&
-         "Cannot emit memory checks when optimizing for size");
+  if (BB->getParent()->hasOptSize()) {
+    assert(Cost->Hints->getForce() == LoopVectorizeHints::FK_Enabled &&
+           "Cannot emit memory checks when optimizing for size, unless forced "
+           "to vectorize.");
+    ORE->emit([&]() {
+      return OptimizationRemarkAnalysis(DEBUG_TYPE, "VectorizationCodeSize",
+                                        L->getStartLoc(), L->getHeader())
+             << "Code-size may be reduced by not forcing "
+                "vectorization, or by source-code modifications "
+                "eliminating the need for runtime checks "
+                "(e.g., adding 'restrict').";
+    });
+  }
 
   // Create a new block containing the memory check.
   BB->setName("vector.memcheck");

llvm/test/Transforms/LoopVectorize/runtime-check.ll

@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -disable-basicaa -S -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s -check-prefix=FORCED_OPTSIZE
 
 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-n8:16:32:64-S128"
 
@@ -159,6 +160,32 @@ loopexit:
 
 ; CHECK: !9 = !DILocation(line: 101, column: 1, scope: !{{.*}})
 
+define dso_local void @forced_optsize(i64* noalias nocapture readonly %x_p, i64* noalias nocapture readonly %y_p, i64* noalias nocapture %z_p) minsize optsize {
+;
+; FORCED_OPTSIZE: remark: <unknown>:0:0: Code-size may be reduced by not forcing vectorization, or by source-code modifications eliminating the need for runtime checks (e.g., adding 'restrict').
+; FORCED_OPTSIZE-LABEL: @forced_optsize(
+; FORCED_OPTSIZE:       vector.body:
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i64, i64* %x_p, i64 %indvars.iv
+  %0 = load i64, i64* %arrayidx, align 8
+  %arrayidx2 = getelementptr inbounds i64, i64* %y_p, i64 %indvars.iv
+  %1 = load i64, i64* %arrayidx2, align 8
+  %add = add nsw i64 %1, %0
+  %arrayidx4 = getelementptr inbounds i64, i64* %z_p, i64 %indvars.iv
+  store i64 %add, i64* %arrayidx4, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 128
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body, !llvm.loop !12
+}
+
 !llvm.module.flags = !{!0, !1}
 !llvm.dbg.cu = !{!9}
 !0 = !{i32 2, !"Dwarf Version", i32 4}
@@ -177,3 +204,6 @@ loopexit:
                              splitDebugFilename: "abc.debug", emissionKind: 2)
 !10 = !DIFile(filename: "path/to/file", directory: "/path/to/dir")
 !11 = !{i32 2, !"Debug Info Version", i32 3}
+!12 = distinct !{!12, !13, !14}
+!13 = !{!"llvm.loop.vectorize.width", i32 2}
+!14 = !{!"llvm.loop.vectorize.enable", i1 true}