annotate src/gpu/ptx/vm/ptxKernelArguments.cpp @ 11670:891fa65ef9ec

Merge.
author Thomas Wuerthinger <thomas.wuerthinger@oracle.com>
date Mon, 16 Sep 2013 19:56:54 +0200
parents 91e5f927af63
children d8659ad83fcc
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
11485
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
1 /*
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
2 * Copyright (c) 2013, Oracle and/or its affiliates. All rights reserved.
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
4 *
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
5 * This code is free software; you can redistribute it and/or modify it
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
6 * under the terms of the GNU General Public License version 2 only, as
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
7 * published by the Free Software Foundation.
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
8 *
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
9 * This code is distributed in the hope that it will be useful, but WITHOUT
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
11 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
12 * version 2 for more details (a copy is included in the LICENSE file that
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
13 * accompanied this code).
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
14 *
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
15 * You should have received a copy of the GNU General Public License version
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
16 * 2 along with this work; if not, write to the Free Software Foundation,
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
18 *
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
20 * or visit www.oracle.com if you need additional information or have any
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
21 * questions.
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
22 *
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
23 */
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
24
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
25 #include "precompiled.hpp"
11596
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
26 #include "ptxKernelArguments.hpp"
11485
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
27 #include "runtime/javaCalls.hpp"
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
28
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
29 gpu::Ptx::cuda_cu_memalloc_func_t gpu::Ptx::_cuda_cu_memalloc;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
30 gpu::Ptx::cuda_cu_memcpy_htod_func_t gpu::Ptx::_cuda_cu_memcpy_htod;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
31
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
32 // Get next java argument
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
33 oop PTXKernelArguments::next_arg(BasicType expectedType) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
34 assert(_index < _args->length(), "out of bounds");
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
35 oop arg=((objArrayOop) (_args))->obj_at(_index++);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
36 assert(expectedType == T_OBJECT || java_lang_boxing_object::is_instance(arg, expectedType), "arg type mismatch");
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
37 return arg;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
38 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
39
11596
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
40 void PTXKernelArguments::do_int() {
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
41 // If the parameter is a return value,
11485
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
42 if (is_return_type()) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
43 // Allocate device memory for T_INT return value pointer on device. Size in bytes
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
44 int status = gpu::Ptx::_cuda_cu_memalloc(&_return_value_ptr, T_INT_BYTE_SIZE);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
45 if (status != GRAAL_CUDA_SUCCESS) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
46 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
47 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
48 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
49 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
50 // Push _return_value_ptr to _kernelBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
51 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _return_value_ptr;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
52 _bufferOffset += sizeof(_return_value_ptr);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
53 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
54 else {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
55 // Get the next java argument and its value which should be a T_INT
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
56 oop arg = next_arg(T_INT);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
57 // Copy the java argument value to kernelArgBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
58 jvalue intval;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
59 if (java_lang_boxing_object::get_value(arg, &intval) != T_INT) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
60 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_INT");
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
61 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
62 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
63 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
64 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = intval.i;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
65 _bufferOffset += sizeof(intval.i);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
66 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
67 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
68 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
69
11596
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
70 void PTXKernelArguments::do_long() {
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
71 // If the parameter is a return value,
11485
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
72 if (is_return_type()) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
73 // Allocate device memory for T_LONG return value pointer on device. Size in bytes
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
74 int status = gpu::Ptx::_cuda_cu_memalloc(&_return_value_ptr, T_LONG_BYTE_SIZE);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
75 if (status != GRAAL_CUDA_SUCCESS) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
76 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
77 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
78 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
79 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
80 // Push _return_value_ptr to _kernelBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
81 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _return_value_ptr;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
82 _bufferOffset += sizeof(_return_value_ptr);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
83 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
84 else {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
85 // Get the next java argument and its value which should be a T_LONG
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
86 oop arg = next_arg(T_LONG);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
87 // Copy the java argument value to kernelArgBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
88 jvalue val;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
89 if (java_lang_boxing_object::get_value(arg, &val) != T_LONG) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
90 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_LONG");
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
91 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
92 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
93 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
94 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = val.j;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
95 _bufferOffset += sizeof(val.j);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
96 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
97 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
98 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
99
11596
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
100 void PTXKernelArguments::do_byte() {
91e5f927af63 Initial implementation of PTXRuntime (RegisterConfig, PTX description etc); guarded with new flag UseGPU. Specify -XX:+UseGPU to exercise this new implementation.
bharadwaj
parents: 11485
diff changeset
101 // If the parameter is a return value,
11485
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
102 if (is_return_type()) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
103 // Allocate device memory for T_BYTE return value pointer on device. Size in bytes
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
104 int status = gpu::Ptx::_cuda_cu_memalloc(&_return_value_ptr, T_BYTE_SIZE);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
105 if (status != GRAAL_CUDA_SUCCESS) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
106 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
107 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
108 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
109 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
110 // Push _return_value_ptr to _kernelBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
111 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _return_value_ptr;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
112 _bufferOffset += sizeof(_return_value_ptr);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
113 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
114 else {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
115 // Get the next java argument and its value which should be a T_BYTE
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
116 oop arg = next_arg(T_BYTE);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
117 // Copy the java argument value to kernelArgBuffer
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
118 jvalue val;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
119 if (java_lang_boxing_object::get_value(arg, &val) != T_BYTE) {
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
120 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_BYTE");
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
121 _success = false;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
122 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
123 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
124 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = val.b;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
125 _bufferOffset += sizeof(val.b);
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
126 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
127 return;
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
128 }
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
129
49bb1bc983c6 Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff changeset
130 // TODO implement other do_*