Error Building ptx file

rafael.o.scatena · August 20, 2024, 7:02pm

Hello,
I get an error building the .ptx file for my module. I don`t know what it is…

Thank you, Rafael Scatena

MeshStructs.cuh file:

#ifndef MESHSTRUCTS_CUH
#define MESHSTRUCTS_CUH

#include <cmath> 
#include <cstdint> 
#include "MeshStructs.cuh"

static const int N = static_cast<int>(3131877);


struct Point {	double  x;	double  y;	double  z;};

Code around line 15:

      #include <math.h>
      #include <stdio.h>
      #include "MeshStructs.cuh"
      #include <cuda_runtime.h>
      #include <device_launch_parameters.h>
      #include "CudaTriangleBox.cuh"  



__host__ __device__ inline Point Cudacross(const Point& a, const Point& b) {
    Point c;    c.x = a.y * b.z - a.z * b.y;    c.y = a.z * b.x - a.x * b.z;    c.z = a.x * b.y - a.y * b.x;
    return c;}

__host__ __device__ inline double Cudadot(const double  a[3], const double b[3]) {
    return a[0] * b[0] + a[1] * b[1] + a[2] * b[2];}


__device__  inline int planeBoxOverlap(const Point& normal_in, const Point& vert_in, double maxbox[3])	
        {   double normal[3] = {normal_in.x, normal_in.y, normal_in.z};
            double vert[3] = {vert_in.x, vert_in.y, vert_in.z};
            double vmin[3],vmax[3];

            
            vmin[0] = (normal[0] > 0.0) ? -maxbox[0] : maxbox[0];
            vmax[0] = (normal[0] > 0.0) ? maxbox[0] : -maxbox[0];

            vmin[1] = (normal[1] > 0.0) ? -maxbox[1] : maxbox[1];
            vmax[1] = (normal[1] > 0.0) ? maxbox[1] : -maxbox[1];

            vmin[2] = (normal[2] > 0.0) ? -maxbox[2] : maxbox[2];
            vmax[2] = (normal[2] > 0.0) ? maxbox[2] : -maxbox[2];


          

            if(Cudadot(normal,vmin)>0.0) return 0;	

            if(Cudadot(normal,vmax)>=0.0) return 1;	return 0;}

Error Message:

 60%] Building CUDA object CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o
Descarregando processo filho 0x64e689edf490 PID 3514033 
/usr/bin/nvcc -forward-unknown-to-host-compiler -DENABLE_OFFSCREEN_RENDERING=ON -DFMT_LOCALE -DITK_FFTIMAGEFILTERINIT_FACTORY_REGISTER_MANAGER -DITK_IMAGEIO_FACTORY_REGISTER_MANAGER -DITK_MESHIO_FACTORY_REGISTER_MANAGER -DITK_TRANSFORMIO_FACTORY_REGISTER_MANAGER -DMPICH_SKIP_MPICXX -DMPI_NO_CPPBIND -DOMPI_SKIP_MPICXX -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE -D_LARGEFILE64_SOURCE -D_LARGEFILE_SOURCE -D_MPICC_H -D_POSIX_C_SOURCE=200809L -Dkiss_fft_scalar=double -DvtkIOExport_AUTOINIT_INCLUDE="\"/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH/CMakeFiles/vtkModuleAutoInit_9159d64c3f87c6ec39d323a6f8382482.h\"" -DvtkRenderingContext2D_AUTOINIT_INCLUDE="\"/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH/CMakeFiles/vtkModuleAutoInit_9159d64c3f87c6ec39d323a6f8382482.h\"" -DvtkRenderingCore_AUTOINIT_INCLUDE="\"/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH/CMakeFiles/vtkModuleAutoInit_9159d64c3f87c6ec39d323a6f8382482.h\"" -DvtkRenderingOpenGL2_AUTOINIT_INCLUDE="\"/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH/CMakeFiles/vtkModuleAutoInit_9159d64c3f87c6ec39d323a6f8382482.h\"" -DvtkRenderingVolume_AUTOINIT_INCLUDE="\"/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH/CMakeFiles/vtkModuleAutoInit_9159d64c3f87c6ec39d323a6f8382482.h\"" --options-file CMakeFiles/PRISMAMESH.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 "--generate-code=arch=compute_80,code=[compute_80,sm_80]" -w -MD -MT CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o -MF CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o.d -x cu -rdc=true -c "/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/CudaTriangleBox.cu" -o CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o
Filho ativo 0x64e689edf490 (CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o) PID 3514035 
ptxas /tmp/tmpxft_00359eb4_00000000-6_CudaTriangleBox.ptx, line 15; fatal   : Parsing error near '(': syntax error
ptxas fatal   : Ptx assembly aborted due to errors
Descarregando processo filho 0x64e689edf490 PID 3514035 
make[2]: *** [CMakeFiles/PRISMAMESH.dir/build.make:136: CMakeFiles/PRISMAMESH.dir/CudaTriangleBox.cu.o] Erro 255
Removendo o processo filho 0x64e689edf490 PID 3514035 da cadeia.
make[2]: Saindo do diretório '/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH'
Descarregando processo filho 0x5c5483e26720 PID 3513707 
make[1]: *** [CMakeFiles/Makefile2:114: CMakeFiles/PRISMAMESH.dir/all] Erro 2
Removendo o processo filho 0x5c5483e26720 PID 3513707 da cadeia.
make[1]: Saindo do diretório '/home/3484681/Área de Trabalho/PRISMAMESH/PRISMAMESH/PRISMAMESH'
Descarregando processo filho 0x5c7aa6c1d350 PID 3513679 
make: *** [Makefile:94: all] Erro 2
Removendo o processo filho 0x5c7aa6c1d350 PID 3513679 da cadeia.

Robert_Crovella · August 20, 2024, 9:43pm

The reported line 15 is of a PTX file. You haven’t shown anything from that file. rather than supplying the PTX file, I suggest providing a complete example.

rafael.o.scatena · August 20, 2024, 11:45pm

That is the .ptx file:

	//
	// Generated by NVIDIA NVVM Compiler
	//
	// Compiler Build ID: CL-32267302
	// Cuda compilation tools, release 12.0, V12.0.140
	// Based on NVVM 7.0.1
	//
	
	.version 8.0
	.target sm_52
	.address_size 64
	
		// .globl	_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi
	
	.visible .entry  (.param .b32 func_retval0) _Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi(
		.param .u64 _Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_0,
		.param .u64 _Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_1,
		.param .u64 _Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_2,
		.param .u32 _Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_3
	)
	{
		.reg .pred 	%p<51>;
		.reg .b32 	%r<23>;
		.reg .f64 	%fd<170>;
		.reg .b64 	%rd<31>;
	
	
		ld.param.u64 	%rd6, [_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_0];
		ld.param.u64 	%rd7, [_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_1];
		ld.param.u64 	%rd5, [_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_2];
		ld.param.u32 	%r4, [_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_3];
		cvta.to.global.u64 	%rd1, %rd7;
		cvta.to.global.u64 	%rd8, %rd6;
		add.s64 	%rd2, %rd8, 8;
		ld.global.f64 	%fd1, [%rd8+32];
		ld.global.f64 	%fd2, [%rd8+40];
		ld.global.f64 	%fd3, [%rd8+48];
		mov.u32 	%r5, %ntid.x;
		mov.u32 	%r6, %ctaid.x;
		mov.u32 	%r7, %tid.x;
		mad.lo.s32 	%r1, %r6, %r5, %r7;
		setp.ge.s32 	%p1, %r1, %r4;
		@%p1 bra 	$L__BB0_29;
	
		ld.global.f64 	%fd34, [%rd2];
		ld.global.f64 	%fd35, [%rd2+8];
		ld.global.f64 	%fd36, [%rd2+16];
		cvt.s64.s32 	%rd3, %r1;
		mul.wide.s32 	%rd9, %r1, 24;
		add.s64 	%rd10, %rd1, %rd9;
		ld.global.f64 	%fd37, [%rd10];
		sub.f64 	%fd4, %fd37, %fd34;
		ld.global.f64 	%fd38, [%rd10+8];
		sub.f64 	%fd5, %fd38, %fd35;
		ld.global.f64 	%fd39, [%rd10+16];
		sub.f64 	%fd6, %fd39, %fd36;
		ld.global.f64 	%fd40, [%rd10+75165048];
		sub.f64 	%fd7, %fd40, %fd34;
		ld.global.f64 	%fd41, [%rd10+75165056];
		sub.f64 	%fd8, %fd41, %fd35;
		ld.global.f64 	%fd42, [%rd10+75165064];
		sub.f64 	%fd9, %fd42, %fd36;
		sub.f64 	%fd10, %fd40, %fd37;
		sub.f64 	%fd11, %fd41, %fd37;
		sub.f64 	%fd12, %fd42, %fd37;
		sub.f64 	%fd13, %fd40, %fd40;
		sub.f64 	%fd14, %fd41, %fd40;
		sub.f64 	%fd15, %fd42, %fd40;
		sub.f64 	%fd16, %fd37, %fd40;
		sub.f64 	%fd17, %fd38, %fd40;
		sub.f64 	%fd18, %fd39, %fd40;
		abs.f64 	%fd20, %fd11;
		abs.f64 	%fd21, %fd12;
		mul.f64 	%fd43, %fd5, %fd12;
		mul.f64 	%fd44, %fd6, %fd11;
		sub.f64 	%fd45, %fd43, %fd44;
		mul.f64 	%fd46, %fd8, %fd12;
		mul.f64 	%fd47, %fd9, %fd11;
		sub.f64 	%fd48, %fd46, %fd47;
		setp.lt.f64 	%p2, %fd45, %fd48;
		selp.f64 	%fd49, %fd45, %fd48, %p2;
		selp.f64 	%fd50, %fd48, %fd45, %p2;
		mul.f64 	%fd51, %fd2, %fd21;
		fma.rn.f64 	%fd52, %fd3, %fd20, %fd51;
		setp.gt.f64 	%p3, %fd49, %fd52;
		neg.f64 	%fd53, %fd52;
		setp.lt.f64 	%p4, %fd50, %fd53;
		or.pred  	%p5, %p3, %p4;
		cvta.to.global.u64 	%rd11, %rd5;
		mul.wide.s32 	%rd12, %r1, 8;
		add.s64 	%rd4, %rd11, %rd12;
		@%p5 bra 	$L__BB0_28;
		bra.uni 	$L__BB0_2;
	
	$L__BB0_28:
		mov.u64 	%rd28, -1;
		st.global.u64 	[%rd4], %rd28;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_2:
		abs.f64 	%fd167, %fd10;
		mul.f64 	%fd54, %fd4, %fd12;
		mul.f64 	%fd55, %fd6, %fd10;
		sub.f64 	%fd56, %fd55, %fd54;
		mul.f64 	%fd57, %fd9, %fd10;
		mul.f64 	%fd58, %fd7, %fd12;
		sub.f64 	%fd59, %fd57, %fd58;
		setp.lt.f64 	%p6, %fd56, %fd59;
		selp.f64 	%fd60, %fd56, %fd59, %p6;
		selp.f64 	%fd61, %fd59, %fd56, %p6;
		mul.f64 	%fd62, %fd1, %fd21;
		fma.rn.f64 	%fd63, %fd3, %fd167, %fd62;
		setp.gt.f64 	%p7, %fd60, %fd63;
		neg.f64 	%fd64, %fd63;
		setp.lt.f64 	%p8, %fd61, %fd64;
		or.pred  	%p9, %p7, %p8;
		@%p9 bra 	$L__BB0_27;
		bra.uni 	$L__BB0_3;
	
	$L__BB0_27:
		mov.u64 	%rd27, -1;
		st.global.u64 	[%rd4], %rd27;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_3:
		abs.f64 	%fd169, %fd11;
		abs.f64 	%fd168, %fd10;
		mul.f64 	%fd65, %fd7, %fd11;
		mul.f64 	%fd66, %fd8, %fd10;
		sub.f64 	%fd67, %fd65, %fd66;
		mul.f64 	%fd68, %fd1, %fd169;
		fma.rn.f64 	%fd69, %fd2, %fd168, %fd68;
		setp.gt.f64 	%p10, %fd67, %fd69;
		neg.f64 	%fd70, %fd69;
		setp.lt.f64 	%p11, %fd67, %fd70;
		or.pred  	%p12, %p10, %p11;
		@%p12 bra 	$L__BB0_26;
		bra.uni 	$L__BB0_4;
	
	$L__BB0_26:
		mov.u64 	%rd26, -1;
		st.global.u64 	[%rd4], %rd26;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_4:
		abs.f64 	%fd22, %fd13;
		mul.f64 	%fd71, %fd6, %fd14;
		mul.f64 	%fd72, %fd5, %fd15;
		sub.f64 	%fd73, %fd72, %fd71;
		mul.f64 	%fd74, %fd9, %fd14;
		mul.f64 	%fd75, %fd8, %fd15;
		sub.f64 	%fd76, %fd75, %fd74;
		setp.lt.f64 	%p13, %fd73, %fd76;
		selp.f64 	%fd77, %fd73, %fd76, %p13;
		selp.f64 	%fd78, %fd76, %fd73, %p13;
		abs.f64 	%fd23, %fd15;
		mul.f64 	%fd79, %fd2, %fd23;
		abs.f64 	%fd24, %fd14;
		fma.rn.f64 	%fd80, %fd3, %fd24, %fd79;
		setp.gt.f64 	%p14, %fd77, %fd80;
		neg.f64 	%fd81, %fd80;
		setp.lt.f64 	%p15, %fd78, %fd81;
		or.pred  	%p16, %p14, %p15;
		@%p16 bra 	$L__BB0_25;
		bra.uni 	$L__BB0_5;
	
	$L__BB0_25:
		mov.u64 	%rd25, -1;
		st.global.u64 	[%rd4], %rd25;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_5:
		mul.f64 	%fd82, %fd4, %fd15;
		mul.f64 	%fd83, %fd6, %fd13;
		sub.f64 	%fd84, %fd83, %fd82;
		mul.f64 	%fd85, %fd9, %fd13;
		mul.f64 	%fd86, %fd7, %fd15;
		sub.f64 	%fd87, %fd85, %fd86;
		setp.lt.f64 	%p17, %fd84, %fd87;
		selp.f64 	%fd88, %fd84, %fd87, %p17;
		selp.f64 	%fd89, %fd87, %fd84, %p17;
		mul.f64 	%fd90, %fd1, %fd23;
		fma.rn.f64 	%fd91, %fd3, %fd22, %fd90;
		setp.gt.f64 	%p18, %fd88, %fd91;
		neg.f64 	%fd92, %fd91;
		setp.lt.f64 	%p19, %fd89, %fd92;
		or.pred  	%p20, %p18, %p19;
		@%p20 bra 	$L__BB0_24;
		bra.uni 	$L__BB0_6;
	
	$L__BB0_24:
		mov.u64 	%rd24, -1;
		st.global.u64 	[%rd4], %rd24;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_6:
		mul.f64 	%fd93, %fd4, %fd14;
		mul.f64 	%fd94, %fd5, %fd13;
		sub.f64 	%fd95, %fd93, %fd94;
		mul.f64 	%fd96, %fd8, %fd13;
		mul.f64 	%fd97, %fd7, %fd14;
		sub.f64 	%fd98, %fd97, %fd96;
		setp.lt.f64 	%p21, %fd95, %fd98;
		selp.f64 	%fd99, %fd95, %fd98, %p21;
		selp.f64 	%fd100, %fd98, %fd95, %p21;
		mul.f64 	%fd101, %fd1, %fd24;
		fma.rn.f64 	%fd102, %fd2, %fd22, %fd101;
		setp.gt.f64 	%p22, %fd99, %fd102;
		neg.f64 	%fd103, %fd102;
		setp.lt.f64 	%p23, %fd100, %fd103;
		or.pred  	%p24, %p22, %p23;
		@%p24 bra 	$L__BB0_23;
		bra.uni 	$L__BB0_7;
	
	$L__BB0_23:
		mov.u64 	%rd23, -1;
		st.global.u64 	[%rd4], %rd23;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_7:
		abs.f64 	%fd25, %fd16;
		mul.f64 	%fd104, %fd6, %fd17;
		mul.f64 	%fd105, %fd5, %fd18;
		sub.f64 	%fd106, %fd105, %fd104;
		mul.f64 	%fd107, %fd9, %fd17;
		mul.f64 	%fd108, %fd8, %fd18;
		sub.f64 	%fd109, %fd108, %fd107;
		setp.lt.f64 	%p25, %fd106, %fd109;
		selp.f64 	%fd110, %fd106, %fd109, %p25;
		selp.f64 	%fd111, %fd109, %fd106, %p25;
		abs.f64 	%fd26, %fd18;
		mul.f64 	%fd112, %fd2, %fd26;
		abs.f64 	%fd27, %fd17;
		fma.rn.f64 	%fd113, %fd3, %fd27, %fd112;
		setp.gt.f64 	%p26, %fd110, %fd113;
		neg.f64 	%fd114, %fd113;
		setp.lt.f64 	%p27, %fd111, %fd114;
		or.pred  	%p28, %p26, %p27;
		@%p28 bra 	$L__BB0_22;
		bra.uni 	$L__BB0_8;
	
	$L__BB0_22:
		mov.u64 	%rd22, -1;
		st.global.u64 	[%rd4], %rd22;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_8:
		mul.f64 	%fd115, %fd4, %fd18;
		mul.f64 	%fd116, %fd6, %fd16;
		sub.f64 	%fd117, %fd116, %fd115;
		mul.f64 	%fd118, %fd9, %fd16;
		mul.f64 	%fd119, %fd7, %fd18;
		sub.f64 	%fd120, %fd118, %fd119;
		setp.lt.f64 	%p29, %fd117, %fd120;
		selp.f64 	%fd121, %fd117, %fd120, %p29;
		selp.f64 	%fd122, %fd120, %fd117, %p29;
		mul.f64 	%fd123, %fd1, %fd26;
		fma.rn.f64 	%fd124, %fd3, %fd25, %fd123;
		setp.gt.f64 	%p30, %fd121, %fd124;
		neg.f64 	%fd125, %fd124;
		setp.lt.f64 	%p31, %fd122, %fd125;
		or.pred  	%p32, %p30, %p31;
		@%p32 bra 	$L__BB0_21;
		bra.uni 	$L__BB0_9;
	
	$L__BB0_21:
		mov.u64 	%rd21, -1;
		st.global.u64 	[%rd4], %rd21;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_9:
		mul.f64 	%fd126, %fd4, %fd17;
		mul.f64 	%fd127, %fd5, %fd16;
		sub.f64 	%fd128, %fd126, %fd127;
		mul.f64 	%fd129, %fd8, %fd16;
		mul.f64 	%fd130, %fd7, %fd17;
		sub.f64 	%fd131, %fd130, %fd129;
		setp.lt.f64 	%p33, %fd131, %fd128;
		selp.f64 	%fd132, %fd131, %fd128, %p33;
		selp.f64 	%fd133, %fd128, %fd131, %p33;
		mul.f64 	%fd134, %fd1, %fd27;
		fma.rn.f64 	%fd135, %fd2, %fd25, %fd134;
		setp.gt.f64 	%p34, %fd132, %fd135;
		neg.f64 	%fd136, %fd135;
		setp.lt.f64 	%p35, %fd133, %fd136;
		or.pred  	%p36, %p34, %p35;
		@%p36 bra 	$L__BB0_20;
		bra.uni 	$L__BB0_10;
	
	$L__BB0_20:
		mov.u64 	%rd20, -1;
		st.global.u64 	[%rd4], %rd20;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_10:
		min.f64 	%fd137, %fd4, %fd7;
		setp.gt.f64 	%p37, %fd137, %fd1;
		max.f64 	%fd138, %fd4, %fd7;
		setp.lt.f64 	%p38, %fd138, %fd1;
		or.pred  	%p39, %p37, %p38;
		@%p39 bra 	$L__BB0_19;
		bra.uni 	$L__BB0_11;
	
	$L__BB0_19:
		mov.u64 	%rd19, -1;
		st.global.u64 	[%rd4], %rd19;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_11:
		min.f64 	%fd139, %fd5, %fd8;
		setp.gt.f64 	%p40, %fd139, %fd2;
		max.f64 	%fd140, %fd5, %fd8;
		setp.lt.f64 	%p41, %fd140, %fd2;
		or.pred  	%p42, %p40, %p41;
		@%p42 bra 	$L__BB0_18;
		bra.uni 	$L__BB0_12;
	
	$L__BB0_18:
		mov.u64 	%rd18, -1;
		st.global.u64 	[%rd4], %rd18;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_12:
		min.f64 	%fd141, %fd6, %fd9;
		setp.gt.f64 	%p43, %fd141, %fd3;
		max.f64 	%fd142, %fd6, %fd9;
		setp.lt.f64 	%p44, %fd142, %fd3;
		or.pred  	%p45, %p43, %p44;
		@%p45 bra 	$L__BB0_17;
		bra.uni 	$L__BB0_13;
	
	$L__BB0_17:
		mov.u64 	%rd17, -1;
		st.global.u64 	[%rd4], %rd17;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_13:
		mul.f64 	%fd143, %fd11, %fd15;
		mul.f64 	%fd144, %fd12, %fd14;
		sub.f64 	%fd28, %fd143, %fd144;
		mul.f64 	%fd145, %fd10, %fd15;
		mul.f64 	%fd146, %fd12, %fd13;
		sub.f64 	%fd29, %fd146, %fd145;
		mul.f64 	%fd147, %fd11, %fd13;
		mul.f64 	%fd148, %fd10, %fd14;
		sub.f64 	%fd30, %fd148, %fd147;
		setp.gt.f64 	%p46, %fd28, 0d0000000000000000;
		neg.f64 	%fd149, %fd1;
		selp.f64 	%fd150, %fd1, %fd149, %p46;
		selp.f64 	%fd151, %fd149, %fd1, %p46;
		sub.f64 	%fd152, %fd151, %fd4;
		sub.f64 	%fd31, %fd150, %fd4;
		setp.gt.f64 	%p47, %fd29, 0d0000000000000000;
		neg.f64 	%fd153, %fd2;
		selp.f64 	%fd154, %fd2, %fd153, %p47;
		selp.f64 	%fd155, %fd153, %fd2, %p47;
		sub.f64 	%fd156, %fd155, %fd5;
		sub.f64 	%fd32, %fd154, %fd5;
		setp.gt.f64 	%p48, %fd30, 0d0000000000000000;
		neg.f64 	%fd157, %fd3;
		selp.f64 	%fd158, %fd3, %fd157, %p48;
		selp.f64 	%fd159, %fd157, %fd3, %p48;
		sub.f64 	%fd160, %fd159, %fd6;
		sub.f64 	%fd33, %fd158, %fd6;
		mul.f64 	%fd161, %fd28, %fd152;
		fma.rn.f64 	%fd162, %fd29, %fd156, %fd161;
		fma.rn.f64 	%fd163, %fd30, %fd160, %fd162;
		setp.gt.f64 	%p49, %fd163, 0d0000000000000000;
		@%p49 bra 	$L__BB0_16;
	
		mul.f64 	%fd164, %fd28, %fd31;
		fma.rn.f64 	%fd165, %fd29, %fd32, %fd164;
		fma.rn.f64 	%fd166, %fd30, %fd33, %fd165;
		setp.ltu.f64 	%p50, %fd166, 0d0000000000000000;
		@%p50 bra 	$L__BB0_16;
		bra.uni 	$L__BB0_15;
	
	$L__BB0_16:
		mov.u64 	%rd16, -1;
		st.global.u64 	[%rd4], %rd16;
		mov.u32 	%r22, 0;
		bra.uni 	$L__BB0_29;
	
	$L__BB0_15:
		ld.param.u64 	%rd30, [_Z13triBoxOverlapRK10OctreeNodeRK9TrianglesR12TriangleListi_param_1];
		cvta.to.global.u64 	%rd29, %rd30;
		shl.b64 	%rd13, %rd3, 3;
		add.s64 	%rd14, %rd29, %rd13;
		ld.global.u64 	%rd15, [%rd14+250550160];
		st.global.u64 	[%rd4], %rd15;
		mov.u32 	%r22, 1;
	
	$L__BB0_29:
		st.param.b32 	[func_retval0+0], %r22;
		ret;
	
	}

Topic		Replies	Views
Matlab 2007b and CUDA Can't compile CUDA example with Matlab CUDA Programming and Performance	19	20100	June 25, 2009
Weird error when compiling CUDA Programming and Performance	3	1305	August 2, 2011
CUDA 9.2 (9.2.148) Update1, nvcc compiler bug CUDA Programming and Performance	10	1125	August 18, 2018
compilation error with cuda 8 & VS 2015 attached full verbosed output CUDA Setup and Installation	0	737	February 10, 2019
Problem with square_me.c Example from Accelerating MATLAB with CUDA Using MEX Files CUDA Programming and Performance	0	2791	September 2, 2009
Simple surface compilation problem on CUDA CUDA Programming and Performance	6	59585	May 25, 2012
Build Error MSB3721 When calling object method within kernel, using compiler directives CUDA Programming and Performance	9	5724	November 18, 2015
Cuda compilation error: class template has already been defined and invalid records warnings CUDA Programming and Performance	5	3097	July 7, 2018
How to fix Error MSB3721 CUDA Setup and Installation	15	35010	November 26, 2023
Working: nvmex,vista64,VS2008 express,cuda 2.2 CUDA Programming and Performance	15	21194	October 12, 2011

Error Building ptx file

Related topics