[PATCH] D57779: [SLP] Add support for throttling.

[Dinar Temirbulatov via Phabricator via llvm-commits]

dtemirbulatov marked 3 inline comments as done.
dtemirbulatov added inline comments.


================
Comment at: test/Transforms/SLPVectorizer/X86/bswap.ll:25
 ; SSE-NEXT:    [[BSWAP1:%.*]] = call i64 @llvm.bswap.i64(i64 [[LD1]])
-; SSE-NEXT:    store i64 [[BSWAP0]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @dst64, i32 0, i64 0), align 8
-; SSE-NEXT:    store i64 [[BSWAP1]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @dst64, i32 0, i64 1), align 8
+; SSE-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> undef, i64 [[BSWAP0]], i32 0
+; SSE-NEXT:    [[TMP2:%.*]] = insertelement <2 x i64> [[TMP1]], i64 [[BSWAP1]], i32 1
----------------
ABataev wrote:
> Still look like too optimistic.
hmm, it might be missed spill-cost recalculation.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57779/new/

https://reviews.llvm.org/D57779