Fixes for roofline datatype plot outputs (#659)

Profile mode:
Fix roofline plots for datatypes that have peakVALU only. Check for highest roofline to plot the bandwidth lines to proper height, don't rely on existence of peakMFMA for every datatype.
Analyze mode:
Add roofline-data-type option for viewing pdfs in standalone gui. Default is same as profile mode, FP32.

---------

Signed-off-by: Carrie Fallows <Carrie.Fallows@amd.com>

docs/how-to/analyze/standalone-gui.rst

@@ -75,6 +75,11 @@ application's profiling data:
 
 #. Memory Chart Analysis
 #. Empirical Roofline Analysis
+
+   Use ``--roofline-data-type`` option to specify which datatype(s) you would like displayed on the roofline PDFs in the standalone analysis GUI.
+   Datatypes can be stacked- for example, "--roofline-data-type FP32 FP64 I32" would display one PDF with FP32 and FP64 stacked, and one PDF with INT32.
+   Default roofline datatype plotted is FP32.
+
 #. Top Stats (Top Kernel Statistics)
 #. System Info
 #. System Speed-of-Light

src/argparser.py

@@ -386,7 +386,7 @@ Examples:
         nargs="+",
         type=str,
         default=["FP32"],
-        help="\t\t\tChoose datatypes to generate plotted roofline PDFs for: (DEFAULT: FP32)\n\t\t\t   FP8\n\t\t\t   FP16\n\t\t\t   BF16\n\t\t\t   FP32\n\t\t\t   FP64\n\t\t\t   I8",
+        help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t   FP8\n\t\t\t   FP16\n\t\t\t   BF16\n\t\t\t   FP32\n\t\t\t   FP64\n\t\t\t   I8\n\t\t\t  I32\n\t\t\t I64\n\t\t\t ",
     )
 
     # roofline_group.add_argument('-w', '--workgroups', required=False, default=-1, type=int, help="\t\t\tNumber of kernel workgroups (DEFAULT: 1024)")
@@ -591,6 +591,19 @@ Examples:
         const=8050,
         help="\t\tActivate a GUI to interate with rocprofiler-compute metrics.\n\t\tOptionally, specify port to launch application (DEFAULT: 8050)",
     )
+
+    analyze_group.add_argument(
+        "-R",
+        "--roofline-data-type",
+        required=False,
+        choices=["FP8", "FP16", "BF16", "FP32", "FP64", "I8", "I32", "I64"],
+        metavar="",
+        nargs="+",
+        type=str,
+        default=["FP32"],
+        help="\t\t\tChoose datatypes to view roofline PDFs for: (DEFAULT: FP32)\n\t\t\t   FP8\n\t\t\t   FP16\n\t\t\t   BF16\n\t\t\t   FP32\n\t\t\t   FP64\n\t\t\t   I8\n\t\t\t  I32\n\t\t\t I64\n\t\t\t ",
+    )
+
     analyze_advanced_group.add_argument(
         "--random-port",
         action="store_true",

src/rocprof_compute_analyze/analysis_webui.py

@@ -61,6 +61,9 @@ class webui_analysis(OmniAnalyze_Base):
         # define any elements which will have full width
         self.__full_width_elements = {1801}
 
+        if hasattr(args, "roofline_data_type") and args.roofline_data_type != ["FP32"]:
+            self.__roofline_data_type = args.roofline_data_type
+
     @demarcate
     def build_layout(self, input_filters, arch_configs):
         """
@@ -186,6 +189,7 @@ class webui_analysis(OmniAnalyze_Base):
                         "mem_level": "ALL",
                         "include_kernel_names": False,
                         "is_standalone": False,
+                        "roofline_data_type": self.__roofline_data_type,
                     }
                 )
                 roof_obj = self.get_socs()[self.arch].roofline_obj

src/roofline.py

@@ -302,7 +302,7 @@ class Roofline:
                             None
                             if self.__run_parameters["is_standalone"]
                             else "{} G{}/s".format(
-                                to_int(self.__ceiling_data["valu"][2], ops_flops)
+                                to_int(self.__ceiling_data["valu"][2]), ops_flops
                             )
                         ),
                         "{} G{}/s".format(

src/utils/roofline_calc.py

@@ -153,13 +153,21 @@ def calc_ceilings(roofline_parameters, dtype, benchmark_data):
             x2_mfma = peakMFMA / peakBw
             y2_mfma = peakMFMA
 
+        # Check which peak is higher for formatting bandwidth lines
+        if y2_mfma > y1_mfma:  # peakMFMA
+            peakX = x2_mfma
+            peakY = y2_mfma
+        else:  # peakVALU
+            peakX = x1_mfma
+            peakY = y1_mfma
+
         # These are the points to use:
         console_debug("roofline", "coordinate points:")
-        console_debug("x = [{}, {}]".format(x1, x2_mfma))
-        console_debug("y = [{}, {}]".format(y1, y2_mfma))
+        console_debug("x = [{}, {}]".format(x1, peakX))
+        console_debug("y = [{}, {}]".format(y1, peakY))
 
-        graphPoints[cacheHierarchy[i].lower()].append([x1, x2_mfma])
-        graphPoints[cacheHierarchy[i].lower()].append([y1, y2_mfma])
+        graphPoints[cacheHierarchy[i].lower()].append([x1, peakX])
+        graphPoints[cacheHierarchy[i].lower()].append([y1, peakY])
         graphPoints[cacheHierarchy[i].lower()].append(peakBw)
 
     # -------------------------------------------------------------------------------------
@@ -177,7 +185,7 @@ def calc_ceilings(roofline_parameters, dtype, benchmark_data):
         graphPoints["valu"].append(peakOps)
 
     # Plot MFMA roof
-    if x1_mfma != -1 and (dtype in MFMA_DATATYPES):  # assert that mfma has been assigned
+    if dtype in MFMA_DATATYPES:  # assert that mfma has been assigned
         x0_mfma = XMAX
         if x2_mfma < x0_mfma:
             x0_mfma = x2_mfma