Homec4science
Diffusion lammps (efficient_neuronet) Browse

lammps/lib/gpu/device.ptx
6b1774dc2052efficient_neuronet

Last Change
Raw File

device.ptx
View Options

.version 2.3
.target sm_20
.address_size 64
// compiled with /usr/local/cuda/open64/lib//be
// nvopencc 4.0 built on 2011-05-12
//-----------------------------------------------------------
// Compiling /tmp/tmpxft_00009a81_00000000-9_lal_device.cpp3.i (/home/sjplimp/ccBI#.zwVkZj)
//-----------------------------------------------------------
//-----------------------------------------------------------
// Options:
//-----------------------------------------------------------
// Target:ptx, ISA:sm_20, Endian:little, Pointer Size:64
// -O3 (Optimization level)
// -g0 (Debug level)
// -m2 (Report advisories)
//-----------------------------------------------------------
.file 1 "<command-line>"
.file 2 "/tmp/tmpxft_00009a81_00000000-8_lal_device.cudafe2.gpu"
.file 3 "/usr/lib/gcc/x86_64-redhat-linux/4.4.5/include/stddef.h"
.file 4 "/usr/local/cuda/include/crt/device_runtime.h"
.file 5 "/usr/local/cuda/include/host_defines.h"
.file 6 "/usr/local/cuda/include/builtin_types.h"
.file 7 "/usr/local/cuda/include/device_types.h"
.file 8 "/usr/local/cuda/include/driver_types.h"
.file 9 "/usr/local/cuda/include/surface_types.h"
.file 10 "/usr/local/cuda/include/texture_types.h"
.file 11 "/usr/local/cuda/include/vector_types.h"
.file 12 "/usr/local/cuda/include/device_launch_parameters.h"
.file 13 "/usr/local/cuda/include/crt/storage_class.h"
.file 14 "/usr/include/bits/types.h"
.file 15 "/usr/include/time.h"
.file 16 "lal_device.cu"
.file 17 "/usr/local/cuda/include/common_functions.h"
.file 18 "/usr/local/cuda/include/math_functions.h"
.file 19 "/usr/local/cuda/include/math_constants.h"
.file 20 "/usr/local/cuda/include/device_functions.h"
.file 21 "/usr/local/cuda/include/sm_11_atomic_functions.h"
.file 22 "/usr/local/cuda/include/sm_12_atomic_functions.h"
.file 23 "/usr/local/cuda/include/sm_13_double_functions.h"
.file 24 "/usr/local/cuda/include/sm_20_atomic_functions.h"
.file 25 "/usr/local/cuda/include/sm_20_intrinsics.h"
.file 26 "/usr/local/cuda/include/surface_functions.h"
.file 27 "/usr/local/cuda/include/texture_fetch_functions.h"
.file 28 "/usr/local/cuda/include/math_functions_dbl_ptx3.h"
.entry kernel_zero (
.param .u64 __cudaparm_kernel_zero_mem,
.param .s32 __cudaparm_kernel_zero_numel)
{
.reg .u32 %r<9>;
.reg .u64 %rd<6>;
.reg .pred %p<3>;
.loc 16 20 0
$LDWbegin_kernel_zero:
cvt.s32.u32 %r1, %ctaid.x;
cvt.s32.u32 %r2, %ntid.x;
mul24.lo.s32 %r3, %r1, %r2;
mov.u32 %r4, %tid.x;
add.u32 %r5, %r3, %r4;
ld.param.s32 %r6, [__cudaparm_kernel_zero_numel];
setp.le.s32 %p1, %r6, %r5;
@%p1 bra $Lt_0_1026;
.loc 16 24 0
mov.s32 %r7, 0;
ld.param.u64 %rd1, [__cudaparm_kernel_zero_mem];
cvt.s64.s32 %rd2, %r5;
mul.wide.s32 %rd3, %r5, 4;
add.u64 %rd4, %rd1, %rd3;
st.global.s32 [%rd4+0], %r7;
$Lt_0_1026:
.loc 16 25 0
exit;
$LDWend_kernel_zero:
} // kernel_zero
.entry kernel_info (
.param .u64 __cudaparm_kernel_info_info)
{
.reg .u32 %r<16>;
.reg .u64 %rd<3>;
.loc 16 27 0
$LDWbegin_kernel_info:
.loc 16 28 0
ld.param.u64 %rd1, [__cudaparm_kernel_info_info];
mov.s32 %r1, 200;
st.global.s32 [%rd1+0], %r1;
.loc 16 29 0
mov.s32 %r2, 32;
st.global.s32 [%rd1+4], %r2;
.loc 16 30 0
mov.s32 %r3, 32;
st.global.s32 [%rd1+8], %r3;
.loc 16 31 0
mov.s32 %r4, 4;
st.global.s32 [%rd1+12], %r4;
.loc 16 32 0
mov.s32 %r5, 8;
st.global.s32 [%rd1+16], %r5;
.loc 16 33 0
mov.s32 %r6, 64;
st.global.s32 [%rd1+20], %r6;
.loc 16 34 0
mov.s32 %r7, 128;
st.global.s32 [%rd1+24], %r7;
.loc 16 35 0
mov.s32 %r8, 11;
st.global.s32 [%rd1+28], %r8;
.loc 16 36 0
mov.s32 %r9, 8;
st.global.s32 [%rd1+32], %r9;
.loc 16 37 0
mov.s32 %r10, 128;
st.global.s32 [%rd1+36], %r10;
.loc 16 38 0
mov.s32 %r11, 128;
st.global.s32 [%rd1+40], %r11;
.loc 16 39 0
mov.s32 %r12, 128;
st.global.s32 [%rd1+44], %r12;
.loc 16 40 0
mov.s32 %r13, 128;
st.global.s32 [%rd1+48], %r13;
.loc 16 41 0
mov.s32 %r14, 8;
st.global.s32 [%rd1+52], %r14;
.loc 16 42 0
exit;
$LDWend_kernel_info:
} // kernel_info
c4science · Help