llvm/test/Transforms/LoopVectorize/X86, branch release_33http://llvm.orghttps://git.amat.us/llvm/atom/test/Transforms/LoopVectorize/X86?h=release_332013-04-30T17:52:57ZTBAA: remove !tbaa from testing cases if not used.2013-04-30T17:52:57ZManman Renmren@apple.com2013-04-30T17:52:57Zurn:sha1:2dc50d306752c8672d1543feb88517705cdb25e7
This will make it easier to turn on struct-path aware TBAA since the metadata
format will change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180796 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorize: Scalarize padded types2013-04-24T16:16:01ZArnold Schwaighoferaschwaighofer@apple.com2013-04-24T16:16:01Zurn:sha1:a4b8b4ccc9ecd6863606c7cdde6ec1b38734708a
This patch disables memory-instruction vectorization for types that need padding
bytes, e.g., x86_fp80 has 10 bytes store size with 6 bytes padding in darwin on
x86_64. Because the load/store vectorization is performed by the bit casting to
a packed vector, which has incompatible memory layout due to the lack of padding
bytes, the present vectorizer produces inconsistent result for memory
instructions of those types.
This patch checks an equality of the AllocSize of a scalar type and allocated
size for each vector element, to ensure that there is no padding bytes and the
array can be read/written using vector operations.
Patch by Daisuke Takahashi!
Fixes PR15758.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180196 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorizer: Bail out if we don't have datalayout we need it2013-04-24T16:15:58ZArnold Schwaighoferaschwaighofer@apple.com2013-04-24T16:15:58Zurn:sha1:b03ad17536097a0f172428c939e80ce7657e201b
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180195 91177308-0d34-0410-b5e6-96231b3b80d8
Call the potentially costly isAnnotatedParallel() only once. 2013-04-23T16:44:43ZPekka Jaaskelainenpekka.jaaskelainen@tut.fi2013-04-23T16:44:43Zurn:sha1:2e59a125fce4235beeb4e72cafbcbe62854ed77c
Made the uniform write test's checks a bit stricter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180119 91177308-0d34-0410-b5e6-96231b3b80d8
Refuse to (even try to) vectorize loops which have uniform writes,2013-04-23T08:08:51ZPekka Jaaskelainenpekka.jaaskelainen@tut.fi2013-04-23T08:08:51Zurn:sha1:a8958769ea5583d58ae51931d8b1271c23fd20ea
even if erroneously annotated with the parallel loop metadata.
Fixes Bug 15794:
"Loop Vectorizer: Crashes with the use of llvm.loop.parallel metadata"
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180081 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorizer: Pass OperandValueKind information to the cost model2013-04-04T23:26:27ZArnold Schwaighoferaschwaighofer@apple.com2013-04-04T23:26:27Zurn:sha1:ac2cc0170f7d13e7c2e87f7728c99a6d07876f5c
Pass down the fact that an operand is going to be a vector of constants.
This should bring the performance of MultiSource/Benchmarks/PAQ8p/paq8p on x86
back. It had degraded to scalar performance due to my pervious shift cost change
that made all shifts expensive on x86.
radar://13576547
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178809 91177308-0d34-0410-b5e6-96231b3b80d8
X86TTI: Add accurate costs for itofp operations, based on the actual instruction counts.2013-04-01T10:23:49ZBenjamin Kramerbenny.kra@googlemail.com2013-04-01T10:23:49Zurn:sha1:13497b3aa7589fc4f9e924f850a7e5151e9ddd2f
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178459 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorizer: Insert some white space to make test case more readable2013-03-14T21:31:09ZArnold Schwaighoferaschwaighofer@apple.com2013-03-14T21:31:09Zurn:sha1:c184a5f4cad9415ee93ff6d24da2ed676573b61c
Also remove some unneeded function attributes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177114 91177308-0d34-0410-b5e6-96231b3b80d8
Add missing asserts flag to test - it uses debug flags2013-03-14T19:01:58ZArnold Schwaighoferaschwaighofer@apple.com2013-03-14T19:01:58Zurn:sha1:e2188d9c43d9e81407d2c7b7ef887e27f028a8ff
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177102 91177308-0d34-0410-b5e6-96231b3b80d8
LoopVectorize: Invert case when we use a vector cmp value to query select cost2013-03-14T18:54:36ZArnold Schwaighoferaschwaighofer@apple.com2013-03-14T18:54:36Zurn:sha1:d517da33b712b5d8d687ee5e5974056a4787ec4f
We generate a select with a vectorized condition argument when the condition is
NOT loop invariant. Not the other way around.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177098 91177308-0d34-0410-b5e6-96231b3b80d8