Jim Apple has posted comments on this change. Change subject: IMPALA-2809: Improve ByteSwap with builtin function or SSE or AVX2. ......................................................................
Patch Set 5: (2 comments) http://gerrit.cloudera.org:8080/#/c/3081/5/be/src/util/bit-util.inline.h File be/src/util/bit-util.inline.h: Line 139: __attribute__((target("sse4.2"))) I just realized that I'm not sure if we can use __attribute__((target... and Intel intrinsics. See sse-util.h for the reason why: #ifndef IR_COMPILE /// When compiling to native code (i.e. not IR), we cannot use the -msse4.2 compiler /// flag. Otherwise, the compiler will emit SSE 4.2 instructions outside of the runtime /// SSE 4.2 checks and Impala will crash on CPUs that don't support SSE 4.2 /// (IMPALA-1399/1646). The compiler intrinsics cannot be used without -msse4.2, so we /// define our own implementations of the intrinsics instead. Line 174: static const FuncPointer SIMDFuncTable[2] = {ByteSwapSSE_Unit, ByteSwapAVX2_Unit}; > Hi Jim. If you don't mind, I just want to make sure that you suggest to mak Sorry, I meant an actual template parameter. -- To view, visit http://gerrit.cloudera.org:8080/3081 To unsubscribe, visit http://gerrit.cloudera.org:8080/settings Gerrit-MessageType: comment Gerrit-Change-Id: I392ed5a8d5683f30f161282c228c1aedd7b648c1 Gerrit-PatchSet: 5 Gerrit-Project: Impala Gerrit-Branch: cdh5-trunk Gerrit-Owner: Youwei Wang <[email protected]> Gerrit-Reviewer: Alex Behm <[email protected]> Gerrit-Reviewer: Jim Apple <[email protected]> Gerrit-Reviewer: Marcel Kornacker <[email protected]> Gerrit-Reviewer: Mostafa Mokhtar <[email protected]> Gerrit-Reviewer: Tim Armstrong <[email protected]> Gerrit-Reviewer: Youwei Wang <[email protected]> Gerrit-HasComments: Yes
