Add SST integration into gpgpusim (#44)

* Add accommodations to run gpgpusim with SST simulation framework through balar

* Output setup_environment options when sourcing

* Add SST directive check when creating sim thread

* Add sst side test for jenkins

* sst-integration: update Jenkinsfile with offical sst-elements repo and fix bugs in pipeline script

* sst-integration: direct jenkins to rebuild gpgpusim before testing for sst

* sst-integration: fix bugs in sst repos config

* sst-integration: let Jenkins rebuilds simulator

Since the simulator needs to be configured with both normal mode and sst mode, need to rebuild make target to clean prior runs.

* sst-integration: Update Jenkinsfile to source env vars when running balar test

* sst-integration: refactor code to remove __SST__ flag

* sst-integration: fix a bug that init cluster twice for sst

* sst-integration: fix a bug of not sending mem packets to SST

* sst-integration: remove sst flags from makefiles and setup_env

* sst-integration: add comments to SST changes

* sst-integration: remove rebuilding simulator in jenkins when testing for SST

* sst-integration: revert simulator build script

* Add a function to support querying function argument info for SST

* sst-integration: add version detection for vanadis binary

* Automated Format

* add version detection support for gcc 10+

* sst-integration: add cudaMallocHost for SST

* sst-integration: fix a compilation bug

* sst-integration: add sst balar unittest CI

* sst-integration: specify GPU_ARCH for CI test

* sst-integration: use bash for github actions

* sst-integration: use https links for sst repos

* sst-integration: add SST dependencies to CI config

* sst-integration: remove sudo

* sst-integration: default to yes for apt install

* sst-integration: add manual trigger for github action

* sst-integration: remove wrong on event

* sst-integration: limit CPU usage for compilation

* sst-integration: fix wrong path

* sst-integration: use personal repo for testing

* sst-integration: remove sst-core source in CI to free space

* sst-integration: SST_Cycle use print stats with stream id

* Automated Format

* sst-integration: check for diskspace and try to clean it

* sst-integration: move out of docker image

* sst-integration: testing for ci path

* sst-integration: fix syntax

* sst-integration: pass env vars

* sst-integration: set env properly

* sst-integration: merge LLVM build and test into same job

* sst-integration: fix step order

* sst-integration: checkout correct branch for env-setup

* sst-integration: remove resourcing gpu apps

* sst-integration: revert back to docker github action

* sst-integration: enable debug trace for sst testing

* sst-integration: resourcing gpu app for env vars

* sst-integration: use GPUAPPS_ROOT for path for gpu app

* sst-integration: use GPUAPPS_ROOT for path for gpu app

* sst-integration: enable parallel ci tests and fix not returning with cudaMallocHostSST

* sst-integration: using debug flag for CI run

* sst-integration: revert debug ci run

* sst-integration: CI skips cuda sdk download and launch multiple jobs

* sst-integration: reenable parallel tests

* sst-integration: reduce concurrent test thread count

* sst-integration: skip long test for github runner

* sst-integration: try running CI with single core

* sst-integrtion: add callback to SST to check thread sync is done in SST_Cycle()

* sst-integration: ignore lookup if already found and add callbacks to SST

* Automated Format

* sst-integration: add support for indirect texture access

* Automated Format

* sste-integration: fix up for PR

* Automated Format

---------

Co-authored-by: purdue-jenkins <[email protected]>

5 files changed, 67 insertions, 10 deletions

diff --git a/src/cuda-sim/cuda-sim.cc b/src/cuda-sim/cuda-sim.cc
index 833d33f..2fd90c0 100644
--- a/src/cuda-sim/cuda-sim.cc
+++ b/src/cuda-sim/cuda-sim.cc
@@ -1305,7 +1305,12 @@ void function_info::add_param_name_type_size(unsigned index, std::string name,
 void function_info::add_param_data(unsigned argn,
                                    struct gpgpu_ptx_sim_arg *args) {
   const void *data = args->m_start;
-
+  if (g_debug_execution >= 3) {
+    if (args->m_nbytes == 4)
+      printf("ADD_PARAM_DATA %d\n", *((uint32_t *)data));
+    else
+      printf("ADD_PARAM_DATA %p\n", *((void **)data));
+  }
   bool scratchpad_memory_param =
       false;  // Is this parameter in CUDA shared memory or OpenCL local memory
 
@@ -1746,6 +1751,17 @@ static unsigned get_tex_datasize(const ptx_instruction *pI,
                                  ptx_thread_info *thread) {
   const operand_info &src1 = pI->src1();  // the name of the texture
   std::string texname = src1.name();
+  // If indirect access, use register's value as address
+  // to find the symbol
+  if (src1.is_reg()) {
+    const operand_info &dst = pI->dst();
+    ptx_reg_t src1_data =
+        thread->get_operand_value(src1, dst, pI->get_type(), thread, 1);
+    addr_t sym_addr = src1_data.u64;
+    symbol *texRef = thread->get_symbol_table()->lookup_by_addr(sym_addr);
+    assert(texRef != NULL);
+    texname = texRef->name();
+  }
 
   /*
     For programs with many streams, textures can be bound and unbound
@@ -2285,15 +2301,24 @@ void cuda_sim::gpgpu_ptx_sim_memcpy_symbol(const char *hostVar, const void *src,
     sym_name = g->second;
     mem_region = global_space;
   }
-  if (g_globals.find(hostVar) != g_globals.end()) {
-    found_sym = true;
-    sym_name = hostVar;
-    mem_region = global_space;
-  }
-  if (g_constants.find(hostVar) != g_constants.end()) {
-    found_sym = true;
-    sym_name = hostVar;
-    mem_region = const_space;
+
+  // Weili: Only attempt to find symbol as it is a string
+  // if we could not find it in previously registered variable.
+  // This will avoid constructing std::string() from hostVar address
+  // where it is not a string as
+  // Use of a string naming a variable as the symbol parameter was deprecated in
+  // CUDA 4.1 and removed in CUDA 5.0.
+  if (!found_sym) {
+    if (g_globals.find(hostVar) != g_globals.end()) {
+      found_sym = true;
+      sym_name = hostVar;
+      mem_region = global_space;
+    }
+    if (g_constants.find(hostVar) != g_constants.end()) {
+      found_sym = true;
+      sym_name = hostVar;
+      mem_region = const_space;
+    }
   }
 
   if (!found_sym) {
diff --git a/src/cuda-sim/instructions.cc b/src/cuda-sim/instructions.cc
index 108de97..843bf0b 100644
--- a/src/cuda-sim/instructions.cc
+++ b/src/cuda-sim/instructions.cc
@@ -6055,6 +6055,17 @@ void tex_impl(const ptx_instruction *pI, ptx_thread_info *thread) {
                    // to be fetched
 
   std::string texname = src1.name();
+  // If indirect access, use register's value as address
+  // to find the symbol
+  if (src1.is_reg()) {
+    ptx_reg_t src1_data =
+        thread->get_operand_value(src1, dst, pI->get_type(), thread, 1);
+    addr_t sym_addr = src1_data.u64;
+    symbol *texRef = thread->get_symbol_table()->lookup_by_addr(sym_addr);
+    assert(texRef != NULL);
+    texname = texRef->name();
+  }
+
   unsigned to_type = pI->get_type();
   unsigned c_type = pI->get_type2();
   fflush(stdout);
diff --git a/src/cuda-sim/ptx_ir.cc b/src/cuda-sim/ptx_ir.cc
index 1399209..4e500cc 100644
--- a/src/cuda-sim/ptx_ir.cc
+++ b/src/cuda-sim/ptx_ir.cc
@@ -139,6 +139,22 @@ symbol *symbol_table::lookup(const char *identifier) {
   return NULL;
 }
 
+symbol *symbol_table::lookup_by_addr(addr_t addr) {
+  for (auto it = m_symbols.begin(); it != m_symbols.end(); ++it) {
+    symbol *sym = it->second;
+
+    // check if symbol has the addr to be found
+    if ((!sym->is_reg()) && (sym->has_valid_address()) &&
+        (sym->get_address() == addr)) {
+      return sym;
+    }
+  }
+  if (m_parent) {
+    return m_parent->lookup_by_addr(addr);
+  }
+  return NULL;
+}
+
 symbol *symbol_table::add_variable(const char *identifier,
                                    const type_info *type, unsigned size,
                                    const char *filename, unsigned line) {
diff --git a/src/cuda-sim/ptx_ir.h b/src/cuda-sim/ptx_ir.h
index d253866..b08a692 100644
--- a/src/cuda-sim/ptx_ir.h
+++ b/src/cuda-sim/ptx_ir.h
@@ -205,6 +205,7 @@ class symbol {
   const std::string &name() const { return m_name; }
   const std::string &decl_location() const { return m_decl_location; }
   const type_info *type() const { return m_type; }
+  bool has_valid_address() const { return m_address_valid; }
   addr_t get_address() const {
     assert(m_is_label ||
            !m_type->get_key().is_reg());  // todo : other assertions
@@ -310,6 +311,7 @@ class symbol_table {
   void set_ptx_version(float ver, unsigned ext);
   void set_sm_target(const char *target, const char *ext, const char *ext2);
   symbol *lookup(const char *identifier);
+  symbol *lookup_by_addr(addr_t addr);
   std::string get_scope_name() const { return m_scope_name; }
   symbol *add_variable(const char *identifier, const type_info *type,
                        unsigned size, const char *filename, unsigned line);
diff --git a/src/cuda-sim/ptx_sim.h b/src/cuda-sim/ptx_sim.h
index f0c26ef..8eec922 100644
--- a/src/cuda-sim/ptx_sim.h
+++ b/src/cuda-sim/ptx_sim.h
@@ -459,6 +459,9 @@ class ptx_thread_info {
   // Jin: get corresponding kernel grid for CDP purpose
   kernel_info_t &get_kernel() { return m_kernel; }
 
+  // Weili: access symbol_table
+  symbol_table *get_symbol_table() { return m_symbol_table; }
+
  public:
   addr_t m_last_effective_address;
   bool m_branch_taken;