[Haskell-cafe] llvm is generating invalid instructions (problem with autovectorization?)
mainland at apeiron.net
Thu May 22 01:05:49 UTC 2014
Perhaps your installed version of binutils does not support the sarxq
You can ask GHC to pass flags to llc and friends:
On 05/21/2014 06:50 PM, Mike Izbicki wrote:
> I have some code* that is causing llvm to throw a fit. In particular,
> I get (compiling with GHC 7.8 and llvm 3.4):
> Error: no such instruction: `sarxq %rax,%rbx,%r14'
> Similar errors get repeated several thousand times, and it's always a
> sarxq instruction. Now, my code doesn't use any of the simd primops,
> so the sarxq must be coming from llvm's autovectorization. Is it
> possible that somehow GHC's output bytecode could be responsible, or
> is the problem more likely with llvm proper? Is there any way I can
> force GHC to pass flags to llvm so I can experiment with different
> Another clue that the cause might be in llvm's autovectorization is
> that when I compile with llvm 3.0 (which does not support
> autovectorization), there are no error messages.
> * I suspect my code is far too complicated for it to shed any light on
> this question, but it's available at:
> If need be, I can create a minimal sample of code that causes the
> error, but I don't want to go through the trouble if it's not needed.
More information about the Haskell-Cafe