Merge branch 'develop' into api_fp8_quantize

.github/workflows/config.md

@@ -1,7 +1,7 @@
 #=====ROCM INFO=====
-ROCM_VERSION : '6.0.2'
+ROCM_VERSION : '6.3.1'
 #default ROCm version to be used
-ROCM_BASE_IMAGE : 'rocm/dev-ubuntu-20.04'
+ROCM_BASE_IMAGE : 'rocm/dev-ubuntu-22.04'
 #base image from dockerhub to be used
 ROCM_BUILT_IMAGE : 'rocm-migraphx'
 #name of the docker image built upon ROCm base
@@ -26,4 +26,4 @@ PERFORMANCE_TEST_TIMEOUT : '30m'
 
 #===== W A R N I N G =====
 #VARIABLE NAMES NOT TO BE CHANGED, VALUES ONLY!
-#VALUES MUST BE ENGLOSED IN SINGLE QUOTES!
+#VALUES MUST BE ENGLOSED IN SINGLE QUOTES!

.github/workflows/performance.yaml

@@ -12,7 +12,7 @@ on:
       rocm_release:
         description: ROCm Version
         required: true
-        default: '6.0.2'
+        default: '6.3.1'
       performance_reports_repo:
         description: Repository where performance reports are stored
         required: true
@@ -96,4 +96,4 @@ jobs:
     secrets:
       gh_token: ${{ secrets.MIGRAPHX_BOT_TOKEN }}
       mail_user: ${{ secrets.MAIL_USERNAME }}
-      mail_pass: ${{ secrets.MAIL_PASSWORD }}
+      mail_pass: ${{ secrets.MAIL_PASSWORD }}

CMakeLists.txt

@@ -208,7 +208,6 @@ rocm_enable_clang_tidy(
         -clang-diagnostic-disabled-macro-expansion
         -clang-diagnostic-extern-c-compat
         -clang-diagnostic-unused-command-line-argument
-        -cppcoreguidelines-avoid-capture-default-when-capturing-this
         -cppcoreguidelines-avoid-const-or-ref-data-members
         -cppcoreguidelines-avoid-do-while
         -cppcoreguidelines-explicit-virtual-functions
@@ -222,7 +221,6 @@ rocm_enable_clang_tidy(
         -cppcoreguidelines-pro-type-reinterpret-cast
         -cppcoreguidelines-pro-type-union-access
         -cppcoreguidelines-pro-type-vararg
-        -cppcoreguidelines-rvalue-reference-param-not-moved
         -cppcoreguidelines-special-member-functions
         -cppcoreguidelines-use-default-member-init
         -cppcoreguidelines-virtual-class-destructor

docs/driver/read.rst

@@ -78,6 +78,10 @@ Print out the program as cpp program.
 
 Print out program as json.
 
+.. option::  --netron
+
+Print out program as a Netron viewable json file.
+
 .. option::  --text
 
 Print out program in text format.

docs/migraphx-driver.rst

@@ -85,6 +85,8 @@ To learn which options can be used with which commands, see the :ref:`MIGraphX d
       - Prints the program in .txt format
    *  - --binary
       - Prints the program in binary format
+   *  - --netron
+      - Prints the program in Netron viewable JSON format
    *  - --output | -o
       - Writes output in a file
    *  - --fill0

docs/reference/driver-options.rst

@@ -16,7 +16,7 @@ read
 
 Loads and prints input graph.
 
-.. include:: ./driver/read.rst
+.. include:: ../driver/read.rst
 
 compile
 -------
@@ -25,8 +25,8 @@ compile
 
 Compiles and prints input graph.
 
-.. include:: ./driver/read.rst
-.. include:: ./driver/compile.rst
+.. include:: ../driver/read.rst
+.. include:: ../driver/compile.rst
 
 run
 ---
@@ -35,8 +35,8 @@ run
 
 Loads and prints input graph.
 
-.. include:: ./driver/read.rst
-.. include:: ./driver/compile.rst
+.. include:: ../driver/read.rst
+.. include:: ../driver/compile.rst
 
 perf
 ----
@@ -45,8 +45,8 @@ perf
 
 Compiles and runs input graph then prints performance report.
 
-.. include:: ./driver/read.rst
-.. include:: ./driver/compile.rst
+.. include:: ../driver/read.rst
+.. include:: ../driver/compile.rst
 
 .. option::  --iterations, -n [unsigned int]
 
@@ -59,8 +59,8 @@ verify
 
 Runs reference and CPU or GPU implementations and checks outputs for consistency.
 
-.. include:: ./driver/read.rst
-.. include:: ./driver/compile.rst
+.. include:: ../driver/read.rst
+.. include:: ../driver/compile.rst
 
 .. option::  --rms-tol [double]
 
@@ -104,5 +104,5 @@ Here is how you can use ``roctx`` combined with :doc:`rocprof <rocprofiler:rocpr
 Running :doc:`rocprof <rocprofiler:rocprofv1>` generates trace information for HIP, HCC and ROCTX in separate ``.txt`` files.
 To understand the interactions between API calls, utilize the :ref:`roctx.py <tools>` helper script.
 
-.. include:: ./driver/read.rst
-.. include:: ./driver/compile.rst
+.. include:: ../driver/read.rst
+.. include:: ../driver/compile.rst

src/include/migraphx/program.hpp

@@ -112,7 +112,7 @@ struct MIGRAPHX_EXPORT program
                      std::size_t batch = 1,
                      bool detailed     = false) const;
 
-    void mark(const parameter_map& params, marker&& m);
+    void mark(const parameter_map& params, marker m);
 
     value to_value() const;
     void from_value(const value& v);

src/program.cpp

@@ -887,13 +887,12 @@ std::string perf_group(instruction_ref ins, bool detailed)
     return result;
 }
 
-void program::mark(const parameter_map& params, marker&& m)
+void program::mark(const parameter_map& params, marker m)
 {
     auto& ctx = this->impl->contexts;
     // Run once by itself
     eval(params);
     this->finish();
-    // Start marking
     m.mark_start(*this);
     generic_eval(*this, ctx, params, [&](auto ins, auto f) {
         argument result;

test/ref/add.cpp

@@ -170,7 +170,7 @@ TEST_CASE(fp32_fp16_test)
         return p;
     };
 
-    auto test_case = [&](std::vector<std::string>&& op_names) {
+    auto test_case = [&](const std::vector<std::string>& op_names) {
         std::vector<float> gold_res = {2.0, 4.0, 6.0, 8.0, 10.0, 12.0};
         auto p                      = create_program();
         migraphx::quantize_fp16(p, op_names);