GNU gdb (GDB) 7.7 Copyright (C) 2014 Free Software Foundation, Inc. License GPLv3+: GNU GPL version 3 or later This is free software: you are free to change and redistribute it. There is NO WARRANTY, to the extent permitted by law. Type "show copying" and "show warranty" for details. This GDB was configured as "x86_64-unknown-linux-gnu". Type "show configuration" for configuration details. For bug reporting instructions, please see: . Find the GDB manual and other documentation resources online at: . For help, type "help". Type "apropos word" to search for commands related to "word"... Reading symbols from ./opencv_test_ocl...(no debugging symbols found)...done. (gdb) b compute_memory_postalloc_chunk Function "compute_memory_postalloc_chunk" not defined. Make breakpoint pending on future shared library load? (y or [n]) Breakpoint 1 (compute_memory_postalloc_chunk) pending. (gdb) run --gtest_filter='Arithm/Absdiff.Mat/20' Starting program: /home/noxbru/Workplace/Mesa/opencv/build/bin/opencv_test_ocl --gtest_filter='Arithm/Absdiff.Mat/20' warning: Could not load shared library symbols for linux-vdso.so.1. Do you need "set solib-search-path" or "set sysroot"? [Thread debugging using libthread_db enabled] Using host libthread_db library "/usr/lib/libthread_db.so.1". warning: File "/usr/lib/libstdc++.so.6.0.19-gdb.py" auto-loading has been declined by your `auto-load safe-path' set to "$debugdir:$datadir/auto-load". To enable execution of this file add add-auto-load-safe-path /usr/lib/libstdc++.so.6.0.19-gdb.py line to your configuration file "/home/noxbru/.gdbinit". To completely disable this security protection add set auto-load safe-path / line to your configuration file "/home/noxbru/.gdbinit". For more information about this security protection see the "Auto-loading safe path" section in the GDB manual. E.g., run from the shell: info "(gdb)Auto-loading safe path" OpenCV version: 2.4.8 OpenCV VCS version: 2.4.8-142-gbb4199b Build type: release CPU features: sse sse2 sse3 [New Thread 0x7fffe3093700 (LWP 962)] [New Thread 0x7fffdf2b9700 (LWP 963)] * compute_memory_pool_new() OpenCL Platforms: Default GPU : AMD CEDAR : OpenCL 1.1 MESA 10.2.0-devel Current OpenCL device: Platform = Default Type = GPU Name = AMD CEDAR Version = OpenCL 1.1 MESA 10.2.0-devel Compute units = 1 Max work group size = 256 Local memory size = 32 kB Max memory allocation size = 48 MB Double support = No Unified memory = Yes Note: Google Test filter = Arithm/Absdiff.Mat/20 [==========] Running 1 test from 1 test case. [----------] Global test environment set-up. [----------] 1 test from Arithm/Absdiff [ RUN ] Arithm/Absdiff.Mat/20 *** r600_compute_global_buffer_create width = 6144 array_size = 0 * compute_memory_alloc() size_in_dw = 1536 (6144 bytes) + Adding item 0xe8afc0 id = 0 size = 1536 (6144 bytes) * r600_compute_global_transfer_map() level = 0, usage = 2, box(x = 0, y = 0, z = 0 width = 1890, height = 1, depth = 1) Buffer id = 0 offset = 0 (box.x) * compute_memory_finalize_pending() + list: offset = -1 id = 0 size = 1536 (6144 bytes) * compute_memory_grow_pool() new_size_in_dw = 2560 (10240 bytes) * compute_memory_pool_init() initial_size_in_dw = 16384 * compute_memory_prealloc_chunk() size_in_dw = 1536 + Found space for Item 0xe8afc0 id = 0 start_in_dw = 0 (0 bytes) size_in_dw = 1536 (6144 bytes) *** r600_compute_global_buffer_create width = 133952 array_size = 0 * compute_memory_alloc() size_in_dw = 33488 (133952 bytes) + Adding item 0xe90670 id = 1 size = 33488 (133952 bytes) *** evergreen_create_compute_state *** evergreen_bind_compute_state *** evergreen_set_compute_resources: start = 0 count = 0 *** evergreen_set_global_binding first = 0 n = 2 * compute_memory_finalize_pending() + list: offset = 0 id = 0 size = 1536 (6144 bytes) + list: offset = -1 id = 1 size = 33488 (133952 bytes) * compute_memory_grow_pool() new_size_in_dw = 36048 (144192 bytes) Aligned size = 36864 (147456 bytes) * compute_memory_shadow() device_to_host = 1 * compute_memory_transfer() device_to_host = 1, offset_in_chunk = 0, size = 65536 * compute_memory_shadow() device_to_host = 0 * compute_memory_transfer() device_to_host = 0, offset_in_chunk = 0, size = 147456 * compute_memory_prealloc_chunk() size_in_dw = 33488 + Found space for Item 0xe90670 id = 1 start_in_dw = 2048 (8192 bytes) size_in_dw = 33488 (133952 bytes) Breakpoint 1, compute_memory_postalloc_chunk (pool=pool@entry=0xe67040, start_in_dw=start_in_dw@entry=2048) at compute_memory_pool.c:128 128 { (gdb) c Continuing. * compute_memory_postalloc_chunck() start_in_dw = 2048 bind rat: 0 *** evergreen_launch_grid: pc = 0 ; ModuleID = 'radeon' target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64" target triple = "r600--" ; Function Attrs: nounwind define void @convertC3C4(<4 x i16> addrspace(1)* noalias nocapture readonly %src, <4 x i16> addrspace(1)* nocapture %dst, i32 %cols, i32 %rows, i32 %dstStep_in_piexl, i32 %pixel_end) #0 { %x.i.i = tail call i32 @llvm.r600.read.tgid.x() #1 %x.i8.i = tail call i32 @llvm.r600.read.local.size.x() #1 %1 = mul i32 %x.i8.i, %x.i.i %x.i1.i = tail call i32 @llvm.r600.read.tidig.x() #1 %2 = add i32 %x.i1.i, %1 %3 = shl i32 %2, 8 %4 = ashr exact i32 %3, 8 %5 = mul nsw i32 %4, 3 %6 = insertelement <3 x i32> undef, i32 %5, i32 0 %7 = add nsw i32 %5, 1 %8 = insertelement <3 x i32> %6, i32 %7, i32 1 %9 = add nsw i32 %5, 2 %10 = insertelement <3 x i32> %8, i32 %9, i32 2 %11 = insertelement <3 x i32> undef, i32 %pixel_end, i32 0 %12 = shufflevector <3 x i32> %11, <3 x i32> undef, <3 x i32> zeroinitializer %13 = icmp slt <3 x i32> %12, %10 %14 = icmp slt <3 x i32> %10, zeroinitializer %15 = select <3 x i1> %14, <3 x i32> zeroinitializer, <3 x i32> %10 %16 = select <3 x i1> %13, <3 x i32> %12, <3 x i32> %15 %17 = extractelement <3 x i32> %16, i32 0 %18 = getelementptr inbounds <4 x i16> addrspace(1)* %src, i32 %17 %19 = load <4 x i16> addrspace(1)* %18, align 8, !tbaa !4 %20 = extractelement <3 x i32> %16, i32 1 %21 = getelementptr inbounds <4 x i16> addrspace(1)* %src, i32 %20 %22 = load <4 x i16> addrspace(1)* %21, align 8, !tbaa !4 %23 = extractelement <3 x i32> %16, i32 2 %24 = getelementptr inbounds <4 x i16> addrspace(1)* %src, i32 %23 %25 = load <4 x i16> addrspace(1)* %24, align 8, !tbaa !4 %26 = extractelement <4 x i16> %19, i32 0 %27 = insertelement <4 x i16> undef, i16 %26, i32 0 %28 = extractelement <4 x i16> %19, i32 1 %29 = insertelement <4 x i16> %27, i16 %28, i32 1 %30 = extractelement <4 x i16> %19, i32 2 %31 = insertelement <4 x i16> %29, i16 %30, i32 2 %32 = insertelement <4 x i16> %31, i16 0, i32 3 %33 = extractelement <4 x i16> %19, i32 3 %34 = insertelement <4 x i16> undef, i16 %33, i32 0 %35 = extractelement <4 x i16> %22, i32 0 %36 = insertelement <4 x i16> %34, i16 %35, i32 1 %37 = extractelement <4 x i16> %22, i32 1 %38 = insertelement <4 x i16> %36, i16 %37, i32 2 %39 = insertelement <4 x i16> %38, i16 0, i32 3 %40 = extractelement <4 x i16> %22, i32 2 %41 = insertelement <4 x i16> undef, i16 %40, i32 0 %42 = extractelement <4 x i16> %22, i32 3 %43 = insertelement <4 x i16> %41, i16 %42, i32 1 %44 = extractelement <4 x i16> %25, i32 0 %45 = insertelement <4 x i16> %43, i16 %44, i32 2 %46 = insertelement <4 x i16> %45, i16 0, i32 3 %47 = shl i32 %2, 2 %48 = sdiv i32 %47, %cols %49 = insertelement <4 x i32> undef, i32 %48, i32 0 %50 = shufflevector <4 x i32> %49, <4 x i32> undef, <4 x i32> zeroinitializer %51 = srem i32 %47, %cols %52 = insertelement <4 x i32> undef, i32 %51, i32 0 %53 = shufflevector <4 x i32> %52, <4 x i32> undef, <4 x i32> zeroinitializer %54 = add <4 x i32> %53, %55 = insertelement <4 x i32> undef, i32 %cols, i32 0 %56 = shufflevector <4 x i32> %55, <4 x i32> undef, <4 x i32> zeroinitializer %57 = icmp sge <4 x i32> %54, %56 %58 = add <4 x i32> %50, %59 = select <4 x i1> %57, <4 x i32> %58, <4 x i32> %50 %60 = sub <4 x i32> %54, %56 %61 = select <4 x i1> %57, <4 x i32> %60, <4 x i32> %54 %62 = icmp sge <4 x i32> %61, %56 %63 = add <4 x i32> %59, %64 = select <4 x i1> %62, <4 x i32> %63, <4 x i32> %59 %65 = sub <4 x i32> %61, %56 %66 = select <4 x i1> %62, <4 x i32> %65, <4 x i32> %61 %67 = icmp sge <4 x i32> %66, %56 %68 = add <4 x i32> %64, %69 = select <4 x i1> %67, <4 x i32> %68, <4 x i32> %64 %70 = sub <4 x i32> %66, %56 %71 = select <4 x i1> %67, <4 x i32> %70, <4 x i32> %66 %72 = insertelement <4 x i32> undef, i32 %dstStep_in_piexl, i32 0 %73 = shufflevector <4 x i32> %72, <4 x i32> undef, <4 x i32> zeroinitializer %74 = shl <4 x i32> %69, %75 = ashr <4 x i32> %74, %76 = shl <4 x i32> %73, %77 = ashr <4 x i32> %76, %78 = mul <4 x i32> %75, %77 %79 = add <4 x i32> %78, %71 %80 = extractelement <4 x i32> %71, i32 3 %81 = icmp slt i32 %80, %cols %82 = extractelement <4 x i32> %69, i32 3 %83 = icmp slt i32 %82, %rows %or.cond = and i1 %81, %83 br i1 %or.cond, label %84, label %100 ;