diff options
| author | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2017-04-12 12:41:37 +0000 |
|---|---|---|
| committer | Jonas Paulsson <paulsson@linux.vnet.ibm.com> | 2017-04-12 12:41:37 +0000 |
| commit | da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04 (patch) | |
| tree | 5ead03687c900acdb6bf62c7c34fa34f62b03480 /llvm/test/Transforms/LoopVectorize | |
| parent | 12194e9bec6f5c4dc887659983764e6cfb708205 (diff) | |
| download | bcm5719-llvm-da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04.tar.gz bcm5719-llvm-da74ed42dadbbf62644fb8fe0ff1e7885c7b2a04.zip | |
[LoopVectorizer, TTI] New method supportsEfficientVectorElementLoadStore()
Since SystemZ supports vector element load/store instructions, there is no
need for extracts/inserts if a vector load/store gets scalarized.
This patch lets Target specify that it supports such instructions by means of
a new TTI hook that defaults to false.
The use for this is in the LoopVectorizer getScalarizationOverhead() method,
which will with this patch produce a smaller sum for a vector load/store on
SystemZ.
New test: test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll
Review: Adam Nemet
https://reviews.llvm.org/D30680
llvm-svn: 300056
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll b/llvm/test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll new file mode 100644 index 00000000000..e7096c29b99 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/SystemZ/load-store-scalarization-cost.ll @@ -0,0 +1,33 @@ +; REQUIRES: asserts +; RUN: opt -mtriple=s390x-unknown-linux -mcpu=z13 -loop-vectorize \ +; RUN: -force-vector-width=4 -debug-only=loop-vectorize \ +; RUN: -disable-output -enable-interleaved-mem-accesses=false < %s 2>&1 | \ +; RUN: FileCheck %s +; +; Check that a scalarized load/store does not get a cost for insterts/ +; extracts, since z13 supports element load/store. + +define void @fun(i32* %data, i64 %n) { +entry: + br label %for.body + +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds i32, i32* %data, i64 %i + %tmp1 = load i32, i32* %tmp0, align 4 + %tmp2 = add i32 %tmp1, 1 + store i32 %tmp2, i32* %tmp0, align 4 + %i.next = add nuw nsw i64 %i, 2 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void + +; CHECK: LV: Found an estimated cost of 4 for VF 4 For instruction: %tmp1 = load i32, i32* %tmp0, align 4 +; CHECK: LV: Found an estimated cost of 4 for VF 4 For instruction: store i32 %tmp2, i32* %tmp0, align 4 + +; CHECK: LV: Scalarizing: %tmp1 = load i32, i32* %tmp0, align 4 +; CHECK: LV: Scalarizing: store i32 %tmp2, i32* %tmp0, align 4 +} + |
