IntelPython · roxx30198 · Dec 12, 2023
diff --git a/docs/source/user_guide/debugging/debugging_environment.rst b/docs/source/user_guide/debugging/debugging_environment.rst
@@ -9,7 +9,6 @@ Configure debugging environment
 
         export ONEAPI_ROOT=/path/to/oneapi
         source $ONEAPI_ROOT/debugger/latest/env/vars.sh
-        source $ONEAPI_ROOT/compiler/latest/env/vars.sh
 
 2) Create and activate conda environment with the installed numba-dpex:
 

diff --git a/numba_dpex/examples/debug/commands/docs/backtrace b/numba_dpex/examples/debug/commands/docs/backtrace
@@ -1,18 +1,17 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_dpex_func.py:22
+(gdb) break simple_dpex_func.py:12
 (gdb) run simple_dpex_func.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::func_sum () at simple_dpex_func.py:22
-22          result = a_in_func + b_in_func
+Thread 13 "python" hit Breakpoint 2, __main__::func_sum_242dpex_fn[abi:v2][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](float, float) (
+    a_in_func=5, b_in_func=5) at simple_dpex_func.py:12
+12          result = a_in_func + b_in_func  # breakpoint location
 (gdb) backtrace
-#0  __main__::func_sum () at simple_dpex_func.py:22
-#1  __main__::kernel_sum () at simple_dpex_func.py:29
+#0  __main__::func_sum_242dpex_fn[abi:v2][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](float, float) (a_in_func=5, b_in_func=5)
+    at simple_dpex_func.py:12
 (gdb) continue
 ...
-[Switching to Thread 1.1073742080 lane 0]
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::func_sum () at simple_dpex_func.py:22
-22          result = a_in_func + b_in_func
-(gdb) continue
+Thread 15 "python" hit Breakpoint 2, __main__::func_sum_242dpex_fn[abi:v2][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](float, float) (
+    a_in_func=6, b_in_func=6) at simple_dpex_func.py:12
+12          result = a_in_func + b_in_func  # breakpoint location
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/backtrace_kernel b/numba_dpex/examples/debug/commands/docs/backtrace_kernel
@@ -1,17 +1,13 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_dpex_func.py:28
+(gdb) break simple_dpex_func.py:18
 (gdb) run simple_dpex_func.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::kernel_sum () at simple_dpex_func.py:28
-28          i = dpex.get_global_id(0)
+Thread 9 "python" hit Breakpoint 1, __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=...,
+    c_in_kernel=...) at simple_dpex_func.py:18
+18          i = ndpx.get_global_id(0)
 (gdb) backtrace
-#0  __main__::kernel_sum () at simple_dpex_func.py:28
-(gdb) continue
+#0  __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<
+float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=..., c_in_kernel=...) at simple_dpex_func.py:18
 ...
-[Switching to Thread 1.1073742080 lane 0]
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::kernel_sum () at simple_dpex_func.py:28
-28          i = dpex.get_global_id(0)
-(gdb) continue
-...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/break_conditional b/numba_dpex/examples/debug/commands/docs/break_conditional
@@ -1,12 +1,11 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_sum.py:23 if i == 1
+(gdb) break simple_sum.py:14 if i == 1
 (gdb) run simple_sum.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lane 1, __main__::data_parallel_sum () at simple_sum.py:23
-23          c[i] = a[i] + b[i]
+Thread 11 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...) at simple_sum.py:14
+14          c[i] = a[i] + b[i]  # Condition breakpoint location
 (gdb) print i
 $1 = 1
-(gdb) continue
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/break_file_func b/numba_dpex/examples/debug/commands/docs/break_file_func
@@ -1,4 +1,4 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
 (gdb) break simple_sum.py:data_parallel_sum
 (gdb) run simple_sum.py
@@ -8,6 +8,4 @@ Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::data_parallel_sum
 (gdb) continue
 Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::data_parallel_sum () at simple_sum.py:20
 20          @dpex.kernel(debug=True)
-(gdb) continue
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/break_func b/numba_dpex/examples/debug/commands/docs/break_func
@@ -1,4 +1,4 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
 (gdb) break data_parallel_sum
 (gdb) run simple_sum.py
@@ -8,6 +8,5 @@ Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::data_parallel_sum
 (gdb) continue
 Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::data_parallel_sum () at simple_sum.py:20
 20          @dpex.kernel(debug=True)
-(gdb) continue
+
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/break_line_number b/numba_dpex/examples/debug/commands/docs/break_line_number
@@ -1,13 +1,15 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_sum.py:20
+(gdb) break simple_sum.py:11
 (gdb) run simple_sum.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::data_parallel_sum () at simple_sum.py:20
-20          @dpex.kernel(debug=True)
-(gdb) continue
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::data_parallel_sum () at simple_sum.py:20
-20          @dpex.kernel(debug=True)
+Thread 12 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...) at simple_sum.py:13
+13          i = ndpx.get_global_id(0)
 (gdb) continue
+[Switching to thread 15 (Thread 0x7fff55cc0640 (LWP 44013))]
+
+Thread 15 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...) at simple_sum.py:13
+13          i = ndpx.get_global_id(0)
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/break_nested_func b/numba_dpex/examples/debug/commands/docs/break_nested_func
@@ -1,4 +1,4 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
 (gdb) break simple_dpex_func.py:func_sum
 (gdb) run simple_dpex_func.py
@@ -8,6 +8,5 @@ Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::func_sum () at sim
 (gdb) continue
 Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::func_sum () at simple_dpex_func.py:22
 22          result = a_in_func + b_in_func
-(gdb) continue
+
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/info_func b/numba_dpex/examples/debug/commands/docs/info_func
@@ -1,17 +1,26 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_sum.py:22
+(gdb) break simple_sum.py:12
 (gdb) run simple_sum.py
 (gdb) info functions data_parallel_sum
 ...
 All functions matching regular expression "data_parallel_sum":
+
 File simple_sum.py:
-20:         void __main__::data_parallel_sum(Array<float, 1, C, mutable, aligned>, Array<float, 1, C, mutable, aligned>, Array<float, 1, C, mutable, aligned>);
+12:     i8 **__main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<float, 1, C, opencl_cpu>,
+DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>);
 (gdb) continue
+[Switching to thread 12 (Thread 0x7fff564c2640 (LWP 44543))]
+
+Thread 12 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](
+    DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...) at simple_sum.py:13
+13          i = ndpx.get_global_id(0)
 (gdb) info functions __main__
 ...
 All functions matching regular expression "__main__":
-20:         void __main__::data_parallel_sum(Array<float, 1, C, mutable, aligned>, Array<float, 1, C, mutable, aligned>, Array<float, 1, C, mutable, aligned>);
-(gdb) continue
+
+File simple_sum.py:
+12:     i8 **__main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](
+    DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>);
+
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/local_variables_0 b/numba_dpex/examples/debug/commands/docs/local_variables_0
@@ -1,81 +1,60 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break sum_local_vars.py:22
+(gdb) break sum_local_vars.py:13
 (gdb) run sum_local_vars.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::data_parallel_sum () at sum_local_vars.py:22
-22          i = dpex.get_global_id(0)
+Thread 11 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](
+    DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...)
+    at sum_local_vars.py:13
+13          i = ndpx.get_global_id(0)
 (gdb) info locals
-a = '\000' <repeats 55 times>
-b = '\000' <repeats 55 times>
-c = '\000' <repeats 55 times>
+__ocl_dbg_gid0 = 2
+__ocl_dbg_gid1 = 0
+__ocl_dbg_gid2 = 0
 i = 0
 l1 = 0
 l2 = 0
-__ocl_dbg_gid0 = 0
-__ocl_dbg_gid1 = 0
-__ocl_dbg_gid2 = 0
-__ocl_dbg_lid0 = 0
-__ocl_dbg_lid1 = 0
-__ocl_dbg_lid2 = 0
-__ocl_dbg_grid0 = 0
-__ocl_dbg_grid1 = 0
-__ocl_dbg_grid2 = 0
 (gdb) next
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::data_parallel_sum () at sum_local_vars.py:22
-22          i = dpex.get_global_id(0)
+[Switching to thread 1 (Thread 0x7ffff7c71740 (LWP 45181))]
+
+Thread 1 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](
+    DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...)
+    at sum_local_vars.py:13
+13          i = ndpx.get_global_id(0)
 (gdb) next
 23          l1 = a[i] + 2.5
 (gdb) next
 24          l2 = b[i] * 0.3
 (gdb) info locals
-a = '\000' <repeats 55 times>
-b = '\000' <repeats 16 times>, "\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000\000\000\240\016XUU\000\000\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000"
-c = '\000' <repeats 16 times>, "\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000\000\000@\256WUU\000\000\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000"
-i = 8
-l1 = 2.5931931659579277
-l2 = 0
-__ocl_dbg_gid0 = 0
+__ocl_dbg_gid0 = 3
 __ocl_dbg_gid1 = 0
 __ocl_dbg_gid2 = 0
-__ocl_dbg_lid0 = 42949672970
-__ocl_dbg_lid1 = 0
-__ocl_dbg_lid2 = 93825037590528
-__ocl_dbg_grid0 = 4612811918334230528
-__ocl_dbg_grid1 = 0
-__ocl_dbg_grid2 = 0
-(gdb) next
-25          c[i] = l1 + l2
-(gdb) info locals
-a = '\000' <repeats 55 times>
-b = '\000' <repeats 55 times>
-c = '\000' <repeats 16 times>, "\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000\000\000@\256WUU\000\000\n\000\000\000\000\000\000\000\004\000\000\000\000\000\000"
-i = 8
-l1 = 2.5931931659579277
-l2 = 0.22954882979393004
-__ocl_dbg_gid0 = 0
-__ocl_dbg_gid1 = 8
-__ocl_dbg_gid2 = 8
-__ocl_dbg_lid0 = 93825034429928
-__ocl_dbg_lid1 = 0
-__ocl_dbg_lid2 = 93825034429936
-__ocl_dbg_grid0 = 4599075939470750515
-__ocl_dbg_grid1 = 0
-__ocl_dbg_grid2 = 0
+i = 3
+l1 = 3.4331700205802917
+l2 = 0
 (gdb) print a
-$1 = '\000' <repeats 55 times>
+$1 = {meminfo = 0x0, parent = 0x0, nitems = 0, itemsize = 0, data = 0x0, sycl_queue = 0x0, shape = {0}, strides = {0}}
 (gdb) print l1
-$3 = 2.5931931659579277
+$2 = 2.5931931659579277
 (gdb) print l2
-$4 = 0.22954882979393004
+$4 = 0
 (gdb) ptype a
-type = byte [56]
+type = struct DpnpNdArray(dtype=float32, ndim=1, layout=C, address_space=1, usm_type=device, device=opencl:cpu:0, sycl_queue=DpctlSyclQueue on opencl:cpu:0)
+({float addrspace(1)*, i8* addrspace(1)*, i64, i64, float addrspace(1)*, i8* addrspace(1)*, [1 x i64], [1 x i64]}) {
+    float *meminfo;
+    i8 **parent;
+    int64 nitems;
+    int64 itemsize;
+    float *data;
+    i8 **sycl_queue;
+    i64 shape[1];
+    i64 strides[1];
+}
 (gdb) whatis a
-type = byte [56]
+type = DpnpNdArray(dtype=float32, ndim=1, layout=C, address_space=1, usm_type=device, device=opencl:cpu:0, sycl_queue=DpctlSyclQueue on opencl:cpu:0)
+({float addrspace(1)*, i8* addrspace(1)*, i64, i64, float addrspace(1)*, i8* addrspace(1)*, [1 x i64], [1 x i64]})
 (gdb) ptype l1
-type = double
+type = float64
 (gdb) whatis l1
-type = double
-(gdb) continue
+type = float64
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/local_variables_1 b/numba_dpex/examples/debug/commands/docs/local_variables_1
@@ -1,23 +1,19 @@
 $ NUMBA_OPT=1 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break sum_local_vars.py:22
+(gdb) break sum_local_vars.py:13
 (gdb) run sum_local_vars.py
 ...
-Thread 2.1 hit Breakpoint 1, with SIMD lanes [0-7], __main__::data_parallel_sum () at sum_local_vars.py:22
-22           i = dpex.get_global_id(0)
+[Switching to thread 11 (Thread 0x7fff568c3640 (LWP 7679))]
+
+Thread 11 "python" hit Breakpoint 1, __main__::data_parallel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a=..., b=..., c=...)
+    at sum_local_vars.py:13
+13          i = ndpx.get_global_id(0)
 (gdb) info locals
-__ocl_dbg_gid0 = 8
+__ocl_dbg_gid0 = 3
 __ocl_dbg_gid1 = 0
 __ocl_dbg_gid2 = 0
-__ocl_dbg_lid0 = 8
-__ocl_dbg_lid1 = 0
-__ocl_dbg_lid2 = 0
-__ocl_dbg_grid0 = 0
-__ocl_dbg_grid1 = 0
-__ocl_dbg_grid2 = 0
 i = 0
 l1 = 0
 l2 = 0
-(gdb) continue
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/next b/numba_dpex/examples/debug/commands/docs/next
@@ -1,14 +1,20 @@
-$ NUMBA_OPT=0 gdb-oneapi -q python
+$ NUMBA_OPT=0 NUMBA_DPEX_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_dpex_func.py:29
+(gdb) break simple_dpex_func.py:19
 (gdb) run simple_dpex_func.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::kernel_sum () at simple_dpex_func.py:29
-29          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
-(gdb) next
-[Switching to Thread 1.1073742080 lane 0]
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::kernel_sum () at simple_dpex_func.py:29
-29          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
+[Switching to thread 11 (Thread 0x7fff56cc4640 (LWP 8028))]
+
+Thread 11 "python" hit Breakpoint 1, __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray
+<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=...,
+    c_in_kernel=...) at simple_dpex_func.py:19
+19          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
 (gdb) next
+[Switching to thread 13 (Thread 0x7fff564c2640 (LWP 8030))]
+
+Thread 13 "python" hit Breakpoint 1, __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray
+<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=...,
+    c_in_kernel=...) at simple_dpex_func.py:19
+19          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
+
 ...
-Done...
diff --git a/numba_dpex/examples/debug/commands/docs/sheduler_locking b/numba_dpex/examples/debug/commands/docs/sheduler_locking
@@ -1,21 +1,27 @@
 $ NUMBA_OPT=0 gdb-oneapi -q python
 (gdb) set breakpoint pending on
-(gdb) break simple_dpex_func.py:29
+(gdb) break simple_dpex_func.py:19
 (gdb) run simple_dpex_func.py
 ...
-Thread 2.2 hit Breakpoint 1, with SIMD lanes [0-7], __main__::kernel_sum () at simple_dpex_func.py:29
-29          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
+[Switching to thread 13 (Thread 0x7fff564c2640 (LWP 8030))]
+
+Thread 13 "python" hit Breakpoint 1, __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](DpnpNdArray<
+float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=...,
+    c_in_kernel=...) at simple_dpex_func.py:19
+19          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
 (gdb) set scheduler-locking step
 (gdb) step
-__main__::func_sum () at dpex_func.py:22
-22          result = a_in_func + b_in_func
+__main__::func_sum_242dpex_fn[abi:v2][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA](float, float) (a_in_func=4, b_in_func=4)
+    at simple_dpex_func.py:12
+12          result = a_in_func + b_in_func  # breakpoint location
 (gdb) step
 23          return result
 (gdb) continue
 ...
-[Switching to Thread 1.1073742080 lane 0]
-Thread 2.3 hit Breakpoint 1, with SIMD lanes [0-1], __main__::kernel_sum () at simple_dpex_func.py:29
-29          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
-(gdb) continue
+[Switching to thread 15 (Thread 0x7fff55cc0640 (LWP 8032))]
+
+Thread 15 "python" hit Breakpoint 1, __main__::kernel_sum_241dpex_fn[abi:v1][abi:c8tJTC_2fWgMemLSg1AEMDLWKQhCFpAEkANV7BEpoA]
+(DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>, DpnpNdArray<float, 1, C, opencl_cpu>) (a_in_kernel=..., b_in_kernel=...,
+    c_in_kernel=...) at simple_dpex_func.py:19
+19          c_in_kernel[i] = func_sum(a_in_kernel[i], b_in_kernel[i])
 ...
-Done...