Mercurial > hg > truffle
annotate src/gpu/ptx/vm/ptxKernelArguments.cpp @ 13705:ac5b0f31f7a2
Truffle API-change: FrameDescriptors are now stored in the RootNode in a final field instead of the CallTarget.
author | Christian Humer <christian.humer@gmail.com> |
---|---|
date | Fri, 17 Jan 2014 17:06:08 +0100 |
parents | 1a7e7011a341 |
children |
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"); |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
35 oop arg = ((objArrayOop) (_args))->obj_at(_index++); |
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
36 assert(expectedType == T_OBJECT || |
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
37 java_lang_boxing_object::is_instance(arg, expectedType), "arg type mismatch"); |
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
|
38 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
|
39 } |
49bb1bc983c6
Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff
changeset
|
40 |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
41 /* |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
42 * Pad kernel argument buffer to naturally align for given size. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
43 */ |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
44 void PTXKernelArguments::pad_kernel_argument_buffer(size_t dataSz) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
45 while ((_bufferOffset % dataSz) != 0) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
46 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = (char) 0; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
47 _bufferOffset += sizeof(char); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
48 } |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
49 return; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
50 } |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
51 void PTXKernelArguments::do_int() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
52 // If the parameter is a return value, |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
53 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
54 // Allocate device memory for T_INT return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
55 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_INT_BYTE_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
56 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
57 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
58 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
59 return; |
11894
c7abc8411011
Fixed BasicPTXTest and IntegerPTXTest
Morris Meyer <morris.meyer@oracle.com>
parents:
11821
diff
changeset
|
60 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
61 |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
62 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
63 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
64 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
65 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
66 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
67 _bufferOffset += sizeof(_dev_return_value); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
68 } else { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
69 // Get the next java argument and its value which should be a T_INT |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
70 oop arg = next_arg(T_INT); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
71 // Copy the java argument value to kernelArgBuffer |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
72 jvalue intval; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
73 if (java_lang_boxing_object::get_value(arg, &intval) != T_INT) { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
74 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_INT"); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
75 _success = false; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
76 return; |
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
|
77 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
78 |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
79 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
80 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
81 pad_kernel_argument_buffer(sizeof(intval.i)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
82 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
83 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = intval.i; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
84 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
85 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
86 _bufferOffset += sizeof(intval.i); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
87 } |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
88 return; |
11894
c7abc8411011
Fixed BasicPTXTest and IntegerPTXTest
Morris Meyer <morris.meyer@oracle.com>
parents:
11821
diff
changeset
|
89 } |
c7abc8411011
Fixed BasicPTXTest and IntegerPTXTest
Morris Meyer <morris.meyer@oracle.com>
parents:
11821
diff
changeset
|
90 |
c7abc8411011
Fixed BasicPTXTest and IntegerPTXTest
Morris Meyer <morris.meyer@oracle.com>
parents:
11821
diff
changeset
|
91 void PTXKernelArguments::do_float() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
92 // If the parameter is a return value, |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
93 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
94 // Allocate device memory for T_FLOAT return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
95 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_FLOAT_BYTE_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
96 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
97 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
98 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
99 return; |
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
|
100 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
101 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
102 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
103 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
104 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
105 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
106 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
107 _bufferOffset += sizeof(_dev_return_value); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
108 } else { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
109 // Get the next java argument and its value which should be a T_FLOAT |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
110 oop arg = next_arg(T_FLOAT); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
111 // Copy the java argument value to kernelArgBuffer |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
112 jvalue floatval; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
113 if (java_lang_boxing_object::get_value(arg, &floatval) != T_FLOAT) { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
114 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_FLOAT"); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
115 _success = false; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
116 return; |
11894
c7abc8411011
Fixed BasicPTXTest and IntegerPTXTest
Morris Meyer <morris.meyer@oracle.com>
parents:
11821
diff
changeset
|
117 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
118 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
119 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
120 pad_kernel_argument_buffer(sizeof(floatval.f)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
121 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = (gpu::Ptx::CUdeviceptr) floatval.f; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
122 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
123 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
124 _bufferOffset += sizeof(floatval.f); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
125 } |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
126 return; |
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
|
127 } |
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 |
11902
67a1e27a8dbb
PTX initial float and double
Morris Meyer <morris.meyer@oracle.com>
parents:
11901
diff
changeset
|
129 void PTXKernelArguments::do_double() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
130 // If the parameter is a return value, |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
131 jvalue doubleval; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
132 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
133 // Allocate device memory for T_DOUBLE return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
134 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_DOUBLE_BYTE_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
135 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
136 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
137 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
138 return; |
11902
67a1e27a8dbb
PTX initial float and double
Morris Meyer <morris.meyer@oracle.com>
parents:
11901
diff
changeset
|
139 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
140 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
141 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
142 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
143 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
144 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
145 // Advance _bufferOffset. |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
146 _bufferOffset += sizeof(doubleval.d); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
147 } else { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
148 // Get the next java argument and its value which should be a T_INT |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
149 oop arg = next_arg(T_FLOAT); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
150 // Copy the java argument value to kernelArgBuffer |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
151 if (java_lang_boxing_object::get_value(arg, &doubleval) != T_DOUBLE) { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
152 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_INT"); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
153 _success = false; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
154 return; |
11902
67a1e27a8dbb
PTX initial float and double
Morris Meyer <morris.meyer@oracle.com>
parents:
11901
diff
changeset
|
155 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
156 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
157 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
158 pad_kernel_argument_buffer(sizeof(doubleval.d)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
159 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = (gpu::Ptx::CUdeviceptr) doubleval.d; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
160 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
161 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
162 _bufferOffset += sizeof(doubleval.d); |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
163 // For a 64-bit host, since size of double is 8, there is no need |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
164 // to pad the kernel argument buffer to ensure 8-byte alignment of |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
165 // the next potential argument to be pushed. |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
166 } |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
167 return; |
11902
67a1e27a8dbb
PTX initial float and double
Morris Meyer <morris.meyer@oracle.com>
parents:
11901
diff
changeset
|
168 } |
67a1e27a8dbb
PTX initial float and double
Morris Meyer <morris.meyer@oracle.com>
parents:
11901
diff
changeset
|
169 |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
170 void PTXKernelArguments::do_long() { |
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
|
171 // 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
|
172 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
173 // Allocate device memory for T_LONG return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
174 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_LONG_BYTE_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
175 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
176 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
177 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
178 return; |
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
|
179 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
180 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
181 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
182 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
183 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
184 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
185 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
186 _bufferOffset += sizeof(_dev_return_value); |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
187 } else { |
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
|
188 // 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
|
189 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
|
190 // 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
|
191 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
|
192 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
|
193 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
|
194 _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
|
195 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
|
196 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
197 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
198 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
199 pad_kernel_argument_buffer(sizeof(val.j)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
200 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = val.j; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
201 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
202 // Advance _bufferOffset |
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
|
203 _bufferOffset += sizeof(val.j); |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
204 // For a 64-bit host, since size of long is 8, there is no need |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
205 // to pad the kernel argument buffer to ensure 8-byte alignment of |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
206 // the next potential argument to be pushed. |
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
|
207 } |
49bb1bc983c6
Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff
changeset
|
208 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
|
209 } |
49bb1bc983c6
Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff
changeset
|
210 |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
211 void PTXKernelArguments::do_byte() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
212 // If the parameter is a return value, |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
213 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
214 // Allocate device memory for T_BYTE return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
215 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_BYTE_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
216 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
217 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
218 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
219 return; |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
220 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
221 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
222 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
223 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
224 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
225 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
226 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
227 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
228 _bufferOffset += sizeof(_dev_return_value); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
229 } else { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
230 // Get the next java argument and its value which should be a T_BYTE |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
231 oop arg = next_arg(T_BYTE); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
232 // Copy the java argument value to kernelArgBuffer |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
233 jvalue val; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
234 if (java_lang_boxing_object::get_value(arg, &val) != T_BYTE) { |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
235 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_BYTE"); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
236 _success = false; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
237 return; |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
238 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
239 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
240 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
241 pad_kernel_argument_buffer(sizeof(val.b)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
242 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = val.b; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
243 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
244 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
245 _bufferOffset += sizeof(val.b); |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
246 // For a 64-bit host, since size of T_BYTE is 8, there is no need |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
247 // to pad the kernel argument buffer to ensure 8-byte alignment of |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
248 // the next potential argument to be pushed. |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
249 } |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
250 return; |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
251 } |
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
252 |
11901
61767ccd4600
PTX boolean return value, emitIntegerTestMove, warnings
Morris Meyer <morris.meyer@oracle.com>
parents:
11894
diff
changeset
|
253 void PTXKernelArguments::do_bool() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
254 // If the parameter is a return value, |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
255 if (is_return_type()) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
256 // Allocate device memory for T_BYTE return value pointer on device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
257 int status = gpu::Ptx::_cuda_cu_memalloc(&_dev_return_value, T_BOOLEAN_SIZE); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
258 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
259 tty->print_cr("[CUDA] *** Error (%d) Failed to allocate memory for return value pointer on device", status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
260 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
261 return; |
11901
61767ccd4600
PTX boolean return value, emitIntegerTestMove, warnings
Morris Meyer <morris.meyer@oracle.com>
parents:
11894
diff
changeset
|
262 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
263 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
264 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
265 pad_kernel_argument_buffer(sizeof(_dev_return_value)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
266 // Push _dev_return_value to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
267 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = _dev_return_value; |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
268 _bufferOffset += sizeof(_dev_return_value); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
269 } else { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
270 // Get the next java argument and its value which should be a T_BOOLEAN |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
271 oop arg = next_arg(T_BOOLEAN); |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
272 // Copy the java argument value to kernelArgBuffer |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
273 jvalue val; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
274 if (java_lang_boxing_object::get_value(arg, &val) != T_BOOLEAN) { |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
275 tty->print_cr("[CUDA] *** Error: Unexpected argument type; expecting T_BOOLEAN"); |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
276 _success = false; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
277 return; |
11901
61767ccd4600
PTX boolean return value, emitIntegerTestMove, warnings
Morris Meyer <morris.meyer@oracle.com>
parents:
11894
diff
changeset
|
278 } |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
279 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
280 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
281 pad_kernel_argument_buffer(sizeof(val.z)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
282 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = val.z; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
283 |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
284 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
285 _bufferOffset += sizeof(val.z); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
286 } |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
287 return; |
11901
61767ccd4600
PTX boolean return value, emitIntegerTestMove, warnings
Morris Meyer <morris.meyer@oracle.com>
parents:
11894
diff
changeset
|
288 } |
61767ccd4600
PTX boolean return value, emitIntegerTestMove, warnings
Morris Meyer <morris.meyer@oracle.com>
parents:
11894
diff
changeset
|
289 |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
290 void PTXKernelArguments::do_array(int begin, int end) { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
291 // Get the next java argument and its value which should be a T_ARRAY |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
292 oop arg = next_arg(T_OBJECT); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
293 assert(arg->is_array(), "argument value not an array"); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
294 // Size of array argument |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
295 int argSize = arg->size() * HeapWordSize; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
296 // Device pointer to array argument. |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
297 gpu::Ptx::CUdeviceptr arrayArgOnDev; |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
298 int status; |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
299 |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
300 // Register host memory for use by the device. Size in bytes |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
301 status = gpu::Ptx::_cuda_cu_mem_host_register(arg, argSize, GRAAL_CU_MEMHOSTREGISTER_DEVICEMAP); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
302 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
303 tty->print_cr("[CUDA] *** Error (%d) Failed to register host memory for array argument on device", |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
304 status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
305 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
306 return; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
307 } |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
308 // Get device pointer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
309 status = gpu::Ptx::_cuda_cu_mem_host_get_device_pointer(&arrayArgOnDev, arg, 0); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
310 if (status != GRAAL_CUDA_SUCCESS) { |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
311 tty->print_cr("[CUDA] *** Error (%d) Failed to get device pointer of mapped pinned memory of array argument.", |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
312 status); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
313 _success = false; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
314 return; |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
315 } |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
316 |
12653
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
317 // Kernel arguments are expected to be naturally aligned. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
318 // Insert padding into kernel argument buffer, if needed. |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
319 pad_kernel_argument_buffer(sizeof(arrayArgOnDev)); |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
320 // Push device array argument to _kernelBuffer |
1a7e7011a341
* PTX kernel argument buffer now has naturally aligned arguments as required by PTX JIT compiler.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12545
diff
changeset
|
321 *((gpu::Ptx::CUdeviceptr*) &_kernelArgBuffer[_bufferOffset]) = arrayArgOnDev; |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
322 |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
323 // Advance _bufferOffset |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
324 _bufferOffset += sizeof(arrayArgOnDev); |
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
325 return; |
11821
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
326 } |
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
327 |
d8659ad83fcc
PTX single-threaded array store, Warp annotation
Morris Meyer <morris.meyer@oracle.com>
parents:
11596
diff
changeset
|
328 void PTXKernelArguments::do_void() { |
12519
f020e149c1b6
PTX codegen enhancements; fixes to PTX test regressions.
S.Bharadwaj Yadavalli <bharadwaj.yadavalli@oracle.com>
parents:
12360
diff
changeset
|
329 return; |
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
|
330 } |
49bb1bc983c6
Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff
changeset
|
331 |
49bb1bc983c6
Implement several missing PTX codegen features; return value capture and method args passing of java method executed on GPU.
bharadwaj
parents:
diff
changeset
|
332 // TODO implement other do_* |