Artem-B

// ABI compatibility shims for  CUDA-11.7.
// Patch affected libraries with:
// objcopy \
// --redefine-sym cudaCreateTextureObject=cudaCreateTextureObject_v115 \
// --redefine-sym cudaGetTextureObjectTextureDesc=cudaGetTextureObjectTextureDesc_v115 \
// --redefine-sym cublasGetVersion_v2=cublasGetVersion_v2_v115 \
// --redefine-sym cublasLtGetVersion=cublasLtGetVersion_v115 \
// libnvinfer_static.a libcudnn_static.a
//

Artem-B

#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <math.h>

#include "cuda_runtime.h"
#include "helper_cuda.h" // from cuda_samples

// Copy of texture descriptor from CUDA-11.7, so we can build the sample 
// in a way that simulates compilation with an older CUDA version.

Artem-B

Now and then video/sound stutters for about a second or two. I do have Hyper-V enabled and do use WSL2 (and docker, configured to use it), but in my case the issue does seem to happen when none of WSL2 VMs are running, so it's possible that it may be more of a Hyper-V issue than WSL2 itself.

I've managed to capture it with ETW trace. As far as I can tell, during this time, everything stalls for about 50ms, then resumes for 10ms and this cycle continues.

Absolutely no events get captured during the quiet periods. Here's one example:

Artem-B

; Reproducer for a bad performance regression triggered by switch to the new PM.
; `barney` ended up with the local variables not being optimized away and that
; had rather dramatic effect on some GPU code. See
; https://bugs.llvm.org/show_bug.cgi?id=52037 for the gory details.
;
; NOTE that opt -O3 produces different IR.
;
; RUN: opt -mtriple=nvptx64-nvidia-cuda -passes='default<O3>' -S %s -o - \
; RUN:  | llc -mtriple=nvptx64-nvidia-cuda -mcpu=sm_70 -O3  -o - \
; RUN:  | FileCheck %s

Artem-B

;*** IR Dump After Combine redundant instructions *** (function: _ZN8cuforces12forcesDeviceI13forces_paramsIL10KernelType3EL14SPHFormulation1EL20DensityDiffusionType3EL12BoundaryType4E12FullViscSpecIL12RheologyType0EL15TurbulenceModel1EL26ComputationalViscosityType0EL12ViscousModel0EL15AverageOperator0ELm517ELb0EELm517EL12ParticleType1ELSD_0EL7RunMode1ELb0ELb0ELb0ELb0E5emptyI18xsph_forces_paramsESF_I20volume_forces_paramsESF_I21grenier_forces_paramsESF_I25sa_boundary_forces_paramsESF_I28dummy_boundary_forces_paramsESF_I25water_depth_forces_paramsESF_I18keps_forces_paramsESF_I14tau_tex_paramsESF_I22eulerVel_forces_paramsESF_I29internal_energy_forces_paramsESF_I28effective_visc_forces_paramsEELS2_3ELS3_1ELS4_3ELS5_4ESC_Lm517ELSD_1ELSD_0EEEvT_)
; ModuleID = 'reduced.ll.ll'
source_filename = "<stdin>"
target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
target triple = "nvptx64-nvidia-cuda"

%struct.char3 = type { i8, i8, i8 }
%"class.cuneibs::neiblist_iterator_core" = type <{ i32*, i16*, %struct.float

Artem-B

;*** IR Dump After Straight line strength reduction (slsr) *** (function: _ZN8cuforces12forcesDeviceI13forces_paramsIL10KernelType3EL14SPHFormulation1EL20DensityDiffusionType3EL12BoundaryType4E12FullViscSpecIL12RheologyType0EL15TurbulenceModel1EL26ComputationalViscosityType0EL12ViscousModel0EL15AverageOperator0ELm517ELb0EELm517EL12ParticleType1ELSD_0EL7RunMode1ELb0ELb0ELb0ELb0E5emptyI18xsph_forces_paramsESF_I20volume_forces_paramsESF_I21grenier_forces_paramsESF_I25sa_boundary_forces_paramsESF_I28dummy_boundary_forces_paramsESF_I25water_depth_forces_paramsESF_I18keps_forces_paramsESF_I14tau_tex_paramsESF_I22eulerVel_forces_paramsESF_I29internal_energy_forces_paramsESF_I28effective_visc_forces_paramsEELS2_3ELS3_1ELS4_3ELS5_4ESC_Lm517ELSD_1ELSD_0EEEvT_)
; ModuleID = 'reduced.ll.ll'
source_filename = "<stdin>"
target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
target triple = "nvptx64-nvidia-cuda"

%struct.char3 = type { i8, i8, i8 }
%struct.float4 = type { float, float, float, float }
%struct.float3

Artem-B

; Compile with:
; 
; clang "-cc1" "-triple" "nvptx64-nvidia-cuda" "-aux-triple"  "x86_64-pc-linux-gnu" 
;  "-S" "-disable-llvm-verifier" "-discard-value-names" "-main-file-name"
;  "DamBreak3D.cu" "-mrelocation-model" "static" "-mframe-pointer=all"
;  "-fno-rounding-math" "-fno-verbose-asm" "-no-integrated-as" "-aux-target-cpu"
;  "x86-64" "-fcuda-is-device" 
;  "-target-feature" "+ptx70" "-target-sdk-version=11.0" "-target-cpu" "sm_70"
;  "-O3" "-x" "ir"
  

Artem-B

--- bin/res.clang	2021-10-05 16:31:10.824553505 -0700
+++ bin/res.clang11	2021-10-05 16:56:46.800860833 -0700
@@ -11,39 +11,39 @@
  Common:
   GLOBAL:402 CONSTANT[3]:2844
  Function _ZN13cupostprocess14calcVortDeviceIL10KernelType3EL12BoundaryType4EEEv24neibs_interaction_paramsIXT0_ENSt11conditionalIXcvbeqT0_LS2_2EE18sa_boundary_params5emptyIS5_EE4typeEEP6float3:
-  REG:47 STACK:112 SHARED:0 LOCAL:0 CONSTANT[0]:424 CONSTANT[2]:16 TEXTURE:0 SURFACE:0 SAMPLER:0
+  REG:46 STACK:0 SHARED:0 LOCAL:0 CONSTANT[0]:424 CONSTANT[2]:16 TEXTURE:0 SURFACE:0 SAMPLER:0
  Function _ZN13cupostprocess20calcTestpointsDeviceIL10KernelType3EL12BoundaryType4E12FullViscSpecIL12RheologyType0EL15TurbulenceModel1EL26ComputationalViscosityType0EL12ViscousModel0EL15AverageOperator0ELm513ELb0EEEEvNS_17testpoints_paramsIXT0_ET1_XeqsrSB_9turbmodelLS5_3EE24neibs_interaction_paramsIXT0_ENSt11conditionalIXcvbeqT0_LS2_2EE18sa_boundary_params5emptyISE_EE4typeEENSD_IXcvbeqsrSB_9turbmodelLS5_3EE15keps_tex_paramsSF_ISK_EE4typeENSD_IXcvbeqsrSB_9turb

Artem-B

--- bin/res.clang	2021-10-05 16:31:10.824553505 -0700
+++ bin/res.nvcc	2021-10-05 16:31:00.712472386 -0700
@@ -9,219 +9,232 @@
 
 Resource usage:
  Common:
-  GLOBAL:402 CONSTANT[3]:2844
+  GLOBAL:0
+
+Fatbin elf code:

Artem-B

namespace {

template <int N>
struct __Tag;
# 54 "__clang_cuda_texture_intrinsics.h" 3
template <class>
struct __FT;

template <>