Lists

Terms and Conditions
Lists hosted on this site
Email the Postmaster
Tips for posting to public mailing lists

codegen bug with SSE autovectorization

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

codegen bug with SSE autovectorization

Subject: codegen bug with SSE autovectorization
From: "Elron Yellin" <email@hidden>
Date: Thu, 15 Jun 2006 10:57:15 -0400

There is a codegen bug in Apple's gcc with SSE autovectorization.
Should the compiler ever decide to vectorize a loop with logical shift
operations, it will generate the wrong shift constant.  The problem is
that the SSE2 logical shift instruction takes a single 128 bit shift
value, but Apple's gcc is treating the shift operand as a vector of N
shift values.  So for the case of a double word shift, instead of
shifting by, eg, 0x12 it shifts by 0x00000012000000120000001200000012,
and the result is of course always zero.

Apparently this bug does not exist in the FSF gcc.

(radar 4583078)

Elron
_______________________________________________
Do not post admin requests to the list. They will be ignored.
Xcode-users mailing list      (email@hidden)
Help/Unsubscribe/Update your Subscription:
This email sent to email@hidden


Follow-Ups:

Re: codegen bug with SSE autovectorization
From: Devang Patel <email@hidden>


Prev by Date:
Reporting distributed build bugs

Next by Date:
Re: Reporting distributed build bugs

Previous by thread:
Re: Reporting distributed build bugs

Next by thread:
Re: codegen bug with SSE autovectorization

Index(es):

Date
Thread