Mercurial > hg > truffle
diff src/share/vm/graal/graalCompilerToGPU.cpp @ 12653:1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
* Change dynamic loading of CUDA driver API functions to load 32-bit or 64-bit versions of depending on the the host architecture.
* Add ability to generate PTX kernels to be launched both on 32-bit and 64-bit hosts.
* Use Unified Virtual Memory APIs to perform array argument marshalling.
* PTX array storage test runs on the device and returns correct results.
* More integer test failures on GPU fixed.
author | S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com> |
---|---|
date | Fri, 01 Nov 2013 18:34:03 -0400 |
parents | 4dba97fb1a6f |
children | f1a55428a8d7 |
line wrap: on
line diff
--- a/src/share/vm/graal/graalCompilerToGPU.cpp Fri Nov 01 13:07:22 2013 +0100 +++ b/src/share/vm/graal/graalCompilerToGPU.cpp Fri Nov 01 18:34:03 2013 -0400 @@ -99,16 +99,19 @@ if (TraceGPUInteraction) { switch (ptxka.get_ret_type()) { case T_INT: - tty->print_cr("GPU execution returned %d", result.get_jint()); + tty->print_cr("GPU execution returned (int) %d", result.get_jint()); + break; + case T_LONG: + tty->print_cr("GPU execution returned (long) %ld", result.get_jlong()); break; case T_FLOAT: - tty->print_cr("GPU execution returned %f", result.get_jfloat()); + tty->print_cr("GPU execution returned (float) %f", result.get_jfloat()); break; case T_DOUBLE: - tty->print_cr("GPU execution returned %f", result.get_jdouble()); + tty->print_cr("GPU execution returned (double) %f", result.get_jdouble()); break; default: - tty->print_cr("GPU returned unhandled"); + tty->print_cr("**** Value returned by GPU not yet handled"); break; } }