mwarusz

 Info: volumerhs_orig! details:
│ - 171 registers, max 256 threads
│ - 0 bytes local memory,
│   1.113 KiB shared memory,
└   0 bytes constant memory
Trial(7.074 ms)
┌ Info: volumerhs_ijk! details:
│ - 136 registers, max 384 threads
│ - 0 bytes local memory,
│   1.113 KiB shared memory,

mwarusz

+---------+-------------------------+-------------------+----------------+----------+
|   FT    | split_explicit_implicit | penalty on linear | remainer_model |  result  |
+---------+-------------------------+-------------------+----------------+----------+
| Float32 | false                   | yes               | -              | stable   |
| Float32 | true                    | yes               | fully discrete | unstable |
| Float64 | true                    | yes               | fully discrete | stable   |
| Float64 | false                   | no                | -              | unstable |
| Float64 | true                    | no                | fully discrete | unstable |
| Float64 | true                    | no                | single flux    | stable   |

mwarusz

diff --git a/src/mapreduce.jl b/src/mapreduce.jl
index 14bcfe1..ad2da8c 100644
--- a/src/mapreduce.jl
+++ b/src/mapreduce.jl
@@ -132,14 +132,15 @@ function partial_mapreduce_grid(f, op, neutral, Rreduce, Rother, shuffle, R, As.
 end
 
 ## COV_EXCL_STOP
-
-NVTX.@range function GPUArrays.mapreducedim!(f, op, R::CuArray{T}, As::AbstractArray...; init=nothing) where T

mwarusz

Invocations                               Metric Name                        Metric Description         Min         Max         Avg
Device "Tesla V100-SXM2-16GB (0)"
    Kernel: ptxcall___gpu_transpose_kernel_naive__426_1
         10                      l2_tex_read_hit_rate               L2 Hit Rate (Texture Reads)      90.44%      90.50%      90.48%
         10                           global_hit_rate         Global Hit Rate in unified l1/tex       0.54%       0.55%       0.54%
    Kernel: ptxcall_transpose_cuda__5
         10                      l2_tex_read_hit_rate               L2 Hit Rate (Texture Reads)      50.11%      50.12%      50.12%
         10                           global_hit_rate         Global Hit Rate in unified l1/tex      77.75%      77.75%      77.75%
    Kernel: ptxcall___gpu_transpose_kernel_naive_ldg__429_2
         10                      l2_tex_read_hit_rate               L2 Hit Rate (Texture Reads)      90.53%      90.56%      90.54%

mwarusz

==4461== Profiling application: julia kernel_transpose.jl
==4461== Profiling result:
==4461== Metric result:
Invocations                               Metric Name                        Metric Description         Min         Max         Avg
Device "GeForce MX150 (0)"
    Kernel: ptxcall___gpu_transpose_kernel_naive__426_1
         10                      l2_tex_read_hit_rate               L2 Hit Rate (Texture Reads)       0.08%       0.10%       0.09%
         10                           global_hit_rate         Global Hit Rate in unified l1/tex       0.00%       0.00%       0.00%
    Kernel: ptxcall_transpose_cuda__5
         10                      l2_tex_read_hit_rate               L2 Hit Rate (Texture Reads)      87.50%      87.50%      87.50%

mwarusz

using KernelAbstractions
using GPUifyLoops
using CUDAnative, CuArrays, CUDAdrv

@kernel function transpose_kernel_naive!(b, a)
  I = @index(Global, Cartesian)
  i, j = Tuple(I)
  @inbounds b[i, j] = a[j, i]
end

mwarusz

─────────────────────────────────────────────────────────────────────────────
                                      Time                   Allocations
                              ──────────────────────   ───────────────────────
       Tot / % measured:            573s / 100%             242GiB / 100%

 Section              ncalls     time   %tot     avg     alloc   %tot      avg
 ─────────────────────────────────────────────────────────────────────────────
 dostep!                 100     572s   100%   5.72s    242GiB  100%   2.42GiB
   facerhs!              500     241s  42.2%   483ms    124GiB  51.1%   253MiB

mwarusz

==64089== Profiling application: julia --project=../../../env/gpu isentropicvortex.jl
==64089== Profiling result:
   Start  Duration            Grid Size      Block Size     Regs*    SSMem*    DSMem*           Device   Context    Stream  Name
      ms        ms                                                       KB         B
1.15e+05  1.838327         (125000 1 1)       (125 1 1)        40  0.000000         0  Tesla V100-SXM2         1         7  ptxcall_knl_nodal_update_aux__6 [136]
1.22e+05  5.682147         (125000 1 1)         (5 5 5)       150  14.89844         0  Tesla V100-SXM2         1         7  ptxcall_volumerhs__7 [147]
1.25e+05  9.771470         (125000 1 1)        (25 1 1)       106  0.000000         0  Tesla V100-SXM2         1         7  ptxcall_facerhs__8 [158]
1.25e+05  3.028208         (305176 1 1)       (256 1 1)        16  0.000000         0  Tesla V100-SXM2         1         7  ptxcall_update__9 [169]
1.25e+05  1.840918         (125000 1 1)       (125 1 1)        40  0.000000         0

mwarusz

diff --git a/Project.toml b/Project.toml
index 104d043..d15c4ad 100644
--- a/Project.toml
+++ b/Project.toml
@@ -5,6 +5,7 @@ version = "0.2.8"
 
 [deps]
 Cassette = "7057c7e9-c182-5462-911a-8362d720325c"
+Cthulhu = "f68482b8-f384-11e8-15f7-abe071a5a75f"
 Requires = "ae029012-a4dd-5104-9daa-d747884805df"

mwarusz

//
// Generated by LLVM NVPTX Back-End
//

.version 6.0
.target sm_61
.address_size 64

.extern .func  (.param .b32 func_retval0) vprintf
(