Add a flag vectorizer-maximize-bandwidth in loop vectorizer to enable using larger vectorization factor.

To be able to maximize the bandwidth during vectorization, this patch provides a new flag vectorizer-maximize-bandwidth. When it is turned on, the vectorizer will determine the vectorization factor (VF) using the smallest instead of widest type in the loop. To avoid increasing register pressure too much, estimates of the register usage for different VFs are calculated so that we only choose a VF when its register usage doesn't exceed the number of available registers.

This is the second attempt to submit this patch. The first attempt got a test failure on ARM. This patch is updated to try to fix the failure (more specifically, by handling the case when VF=1).

Differential revision: http://reviews.llvm.org/D8943

llvm-svn: 251850

2 files changed, 50 insertions, 4 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll b/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
new file mode 100644
index 00000000000..e6dc39c2afa
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
@@ -0,0 +1,46 @@
+; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -mcpu=corei7-avx -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@a = global [1000 x i8] zeroinitializer, align 16
+@b = global [1000 x i8] zeroinitializer, align 16
+@c = global [1000 x i8] zeroinitializer, align 16
+@u = global [1000 x i32] zeroinitializer, align 16
+@v = global [1000 x i32] zeroinitializer, align 16
+@w = global [1000 x i32] zeroinitializer, align 16
+
+; Tests that the vectorization factor is determined by the smallest instead of
+; widest type in the loop for maximum bandwidth when
+; -vectorizer-maximize-bandwidth is indicated.
+;
+; CHECK-label: foo
+; CHECK: LV: Selecting VF: 16.
+define void @foo() {
+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 [1000 x i8], [1000 x i8]* @b, i64 0, i64 %indvars.iv
+  %0 = load i8, i8* %arrayidx, align 1
+  %arrayidx2 = getelementptr inbounds [1000 x i8], [1000 x i8]* @c, i64 0, i64 %indvars.iv
+  %1 = load i8, i8* %arrayidx2, align 1
+  %add = add i8 %1, %0
+  %arrayidx6 = getelementptr inbounds [1000 x i8], [1000 x i8]* @a, i64 0, i64 %indvars.iv
+  store i8 %add, i8* %arrayidx6, align 1
+  %arrayidx8 = getelementptr inbounds [1000 x i32], [1000 x i32]* @v, i64 0, i64 %indvars.iv
+  %2 = load i32, i32* %arrayidx8, align 4
+  %arrayidx10 = getelementptr inbounds [1000 x i32], [1000 x i32]* @w, i64 0, i64 %indvars.iv
+  %3 = load i32, i32* %arrayidx10, align 4
+  %add11 = add nsw i32 %3, %2
+  %arrayidx13 = getelementptr inbounds [1000 x i32], [1000 x i32]* @u, i64 0, i64 %indvars.iv
+  store i32 %add11, i32* %arrayidx13, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1000
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll b/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
index 6cd3c9c3bc0..cca829b9457 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vector_ptr_load_store.ll
@@ -17,7 +17,7 @@ target triple = "x86_64-apple-macosx10.8.0"
 ; widest vector count.
 ;
 ; CHECK: test_consecutive_store
-; CHECK: The Widest type: 64 bits
+; CHECK: The Smallest and Widest types: 64 / 64 bits.
 define void @test_consecutive_store(%0**, %0**, %0** nocapture) nounwind ssp uwtable align 2 {
   %4 = load %0*, %0** %2, align 8
   %5 = icmp eq %0** %0, %1
@@ -51,7 +51,7 @@ define void @test_consecutive_store(%0**, %0**, %0** nocapture) nounwind ssp uwt
 ;       p[i][y] = (int*) (1 + q[i]);
 ;     }
 ; CHECK: test_nonconsecutive_store
-; CHECK: The Widest type: 16 bits
+; CHECK: The Smallest and Widest types: 16 / 16 bits.
 define void @test_nonconsecutive_store() nounwind ssp uwtable {
   br label %1
 
@@ -93,7 +93,7 @@ define void @test_nonconsecutive_store() nounwind ssp uwtable {
 ;; Now we check the same rules for loads. We should take consecutive loads of
 ;; pointer types into account.
 ; CHECK: test_consecutive_ptr_load
-; CHECK: The Widest type: 64 bits
+; CHECK: The Smallest and Widest types: 8 / 64 bits.
 define i8 @test_consecutive_ptr_load() nounwind readonly ssp uwtable {
   br label %1
 
@@ -117,7 +117,7 @@ define i8 @test_consecutive_ptr_load() nounwind readonly ssp uwtable {
 
 ;; However, we should not take unconsecutive loads of pointers into account.
 ; CHECK: test_nonconsecutive_ptr_load
-; CHECK: The Widest type: 16 bits
+; CHECK: LV: The Smallest and Widest types: 16 / 16 bits.
 define void @test_nonconsecutive_ptr_load() nounwind ssp uwtable {
   br label %1