Add support for llvm.vectorizer metadata

- llvm.loop.parallel metadata has been renamed to llvm.loop to be more generic
  by making the root of additional loop metadata.
  - Loop::isAnnotatedParallel now looks for llvm.loop and associated
    llvm.mem.parallel_loop_access
  - document llvm.loop and update llvm.mem.parallel_loop_access
- add support for llvm.vectorizer.width and llvm.vectorizer.unroll
  - document llvm.vectorizer.* metadata
  - add utility class LoopVectorizerHints for getting/setting loop metadata
  - use llvm.vectorizer.width=1 to indicate already vectorized instead of
    already_vectorized
- update existing tests that used llvm.loop.parallel and
  llvm.vectorizer.already_vectorized

Reviewed by: Nadav Rotem


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182802 91177308-0d34-0410-b5e6-96231b3b80d8

6 files changed, 86 insertions, 10 deletions

diff --git a/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll b/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
index 47a5e7aee4..30579cebb1 100644
--- a/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
+++ b/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
@@ -21,7 +21,7 @@ for.end.us:                                       ; preds = %for.body3.us
   %indvars.iv.next34 = add i64 %indvars.iv33, 1
   %lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
   %exitcond36 = icmp eq i32 %lftr.wideiv35, %m
-  br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop.parallel !5
+  br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop !5
 
 for.body3.us:                                     ; preds = %for.body3.us, %for.body3.lr.ph.us
   %indvars.iv29 = phi i64 [ 0, %for.body3.lr.ph.us ], [ %indvars.iv.next30, %for.body3.us ]
@@ -35,7 +35,7 @@ for.body3.us:                                     ; preds = %for.body3.us, %for.
   %indvars.iv.next30 = add i64 %indvars.iv29, 1
   %lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
   %exitcond32 = icmp eq i32 %lftr.wideiv31, %m
-  br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop.parallel !4
+  br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop !4
 
 for.body3.lr.ph.us:                               ; preds = %for.end.us, %entry
   %indvars.iv33 = phi i64 [ %indvars.iv.next34, %for.end.us ], [ 0, %entry ]
diff --git a/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll b/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
index f904a8e0b1..2c47fcb4d3 100644
--- a/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
+++ b/test/Transforms/LoopVectorize/X86/parallel-loops-after-reg2mem.ll
@@ -35,7 +35,7 @@ for.body:                                         ; preds = %for.body.for.body_c
   %indvars.iv.next.reload = load i64* %indvars.iv.next.reg2mem
   %lftr.wideiv = trunc i64 %indvars.iv.next.reload to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
-  br i1 %exitcond, label %for.end, label %for.body.for.body_crit_edge, !llvm.loop.parallel !3
+  br i1 %exitcond, label %for.end, label %for.body.for.body_crit_edge, !llvm.loop !3
 
 for.body.for.body_crit_edge:                      ; preds = %for.body
   %indvars.iv.next.reload2 = load i64* %indvars.iv.next.reg2mem
diff --git a/test/Transforms/LoopVectorize/X86/parallel-loops.ll b/test/Transforms/LoopVectorize/X86/parallel-loops.ll
index 3f1a071e69..681a815d32 100644
--- a/test/Transforms/LoopVectorize/X86/parallel-loops.ll
+++ b/test/Transforms/LoopVectorize/X86/parallel-loops.ll
@@ -65,7 +65,7 @@ for.body:                                         ; preds = %for.body, %entry
   store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
-  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop.parallel !3
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3
 
 for.end:                                          ; preds = %for.body
   ret void
@@ -98,7 +98,7 @@ for.body:                                         ; preds = %for.body, %entry
   store i32 %2, i32* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !6
   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
   %exitcond = icmp eq i32 %lftr.wideiv, 512
-  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop.parallel !6
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !6
 
 for.end:                                          ; preds = %for.body
   ret void
diff --git a/test/Transforms/LoopVectorize/metadata-unroll.ll b/test/Transforms/LoopVectorize/metadata-unroll.ll
new file mode 100644
index 0000000000..0112feeca0
--- /dev/null
+++ b/test/Transforms/LoopVectorize/metadata-unroll.ll
@@ -0,0 +1,41 @@
+; RUN: opt < %s  -loop-vectorize -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+
+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"
+target triple = "x86_64-apple-macosx10.8.0"
+
+@a = common global [2048 x i32] zeroinitializer, align 16
+
+; This is the loop.
+;  for (i=0; i<n; i++){
+;    a[i] += i;
+;  }
+;CHECK: @inc
+;CHECK: load <4 x i32>
+;CHECK: load <4 x i32>
+;CHECK: add nsw <4 x i32>
+;CHECK: add nsw <4 x i32>
+;CHECK: store <4 x i32>
+;CHECK: store <4 x i32>
+;CHECK: ret void
+define void @inc(i32 %n) nounwind uwtable noinline ssp {
+  %1 = icmp sgt i32 %n, 0
+  br i1 %1, label %.lr.ph, label %._crit_edge
+
+.lr.ph:                                           ; preds = %0, %.lr.ph
+  %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
+  %2 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
+  %3 = load i32* %2, align 4
+  %4 = trunc i64 %indvars.iv to i32
+  %5 = add nsw i32 %3, %4
+  store i32 %5, i32* %2, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %._crit_edge, label %.lr.ph, !llvm.loop !0
+
+._crit_edge:                                      ; preds = %.lr.ph, %0
+  ret void
+}
+
+!0 = metadata !{metadata !0, metadata !1}
+!1 = metadata !{metadata !"llvm.vectorizer.unroll", i32 2}
diff --git a/test/Transforms/LoopVectorize/metadata-width.ll b/test/Transforms/LoopVectorize/metadata-width.ll
new file mode 100644
index 0000000000..b06d442416
--- /dev/null
+++ b/test/Transforms/LoopVectorize/metadata-width.ll
@@ -0,0 +1,31 @@
+; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -dce -instcombine -S | FileCheck %s
+
+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"
+target triple = "x86_64-unknown-linux-gnu"
+
+; CHECK: @test1
+; CHECK: store <8 x i32>
+; CHECK: ret void
+define void @test1(i32* nocapture %a, i32 %n) #0 {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = trunc i64 %indvars.iv to i32
+  store i32 %0, i32* %arrayidx, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-frame-pointer-elim-non-leaf"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!0 = metadata !{metadata !0, metadata !1}
+!1 = metadata !{metadata !"llvm.vectorizer.width", i32 8}
diff --git a/test/Transforms/LoopVectorize/vectorize-once.ll b/test/Transforms/LoopVectorize/vectorize-once.ll
index f289ded25d..2b8f3fd31f 100644
--- a/test/Transforms/LoopVectorize/vectorize-once.ll
+++ b/test/Transforms/LoopVectorize/vectorize-once.ll
@@ -11,7 +11,7 @@ target triple = "x86_64-apple-macosx10.8.0"
 ; This test checks that we add metadata to vectorized loops
 ; CHECK: _Z4foo1Pii
 ; CHECK: <4 x i32>
-; CHECK: llvm.vectorizer.already_vectorized
+; CHECK: llvm.loop
 ; CHECK: ret
 
 ; This test comes from the loop:
@@ -40,10 +40,10 @@ _ZSt10accumulateIPiiET0_T_S2_S1_.exit:            ; preds = %for.body.i, %entry
   ret i32 %__init.addr.0.lcssa.i
 }
 
-; This test checks that we don't vectorize loops that are marked with the "already vectorized" metadata.
+; This test checks that we don't vectorize loops that are marked with the "width" == 1 metadata.
 ; CHECK: _Z4foo2Pii
 ; CHECK-NOT: <4 x i32>
-; CHECK: llvm.vectorizer.already_vectorized
+; CHECK: llvm.loop
 ; CHECK: ret
 define i32 @_Z4foo2Pii(i32* %A, i32 %n) #0 {
 entry:
@@ -59,7 +59,7 @@ for.body.i:                                       ; preds = %entry, %for.body.i
   %add.i = add nsw i32 %0, %__init.addr.05.i
   %incdec.ptr.i = getelementptr inbounds i32* %__first.addr.04.i, i64 1
   %cmp.i = icmp eq i32* %incdec.ptr.i, %add.ptr
-  br i1 %cmp.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i, !llvm.vectorizer.already_vectorized !3
+  br i1 %cmp.i, label %_ZSt10accumulateIPiiET0_T_S2_S1_.exit, label %for.body.i, !llvm.loop !0
 
 _ZSt10accumulateIPiiET0_T_S2_S1_.exit:            ; preds = %for.body.i, %entry
   %__init.addr.0.lcssa.i = phi i32 [ 0, %entry ], [ %add.i, %for.body.i ]
@@ -68,5 +68,9 @@ _ZSt10accumulateIPiiET0_T_S2_S1_.exit:            ; preds = %for.body.i, %entry
 
 attributes #0 = { nounwind readonly ssp uwtable "fp-contract-model"="standard" "no-frame-pointer-elim" "no-frame-pointer-elim-non-leaf" "realign-stack" "relocation-model"="pic" "ssp-buffers-size"="8" }
 
-!3 = metadata !{}
+; CHECK: !0 = metadata !{metadata !0, metadata !1}
+; CHECK: !1 = metadata !{metadata !"llvm.vectorizer.width", i32 1}
+; CHECK: !2 = metadata !{metadata !2, metadata !1}
 
+!0 = metadata !{metadata !0, metadata !1}
+!1 = metadata !{metadata !"llvm.vectorizer.width", i32 1}