tests: benchmarks/app_kernel: enable for floating point

The app_kernel benchmarking app has the config file for benchmarking
with floating point enabled, but it was never used. So add it
to the testcase.yaml.

Note that this also limits to run on one CPU on a SMP system as
the resulting numbers would be more consistent among runs.

Signed-off-by: Daniel Leung <daniel.leung@intel.com>

tests/benchmarks/app_kernel/prj_fp.conf

@@ -4,9 +4,7 @@ CONFIG_STDOUT_CONSOLE=y
 CONFIG_MAIN_THREAD_PRIORITY=6
 
 CONFIG_FPU=y
-CONFIG_SSE=y
 CONFIG_FPU_SHARING=y
-CONFIG_SSE_FP_MATH=y
 
 # eliminate timer interrupts during the benchmark
 CONFIG_SYS_CLOCK_TICKS_PER_SEC=1
@@ -17,3 +15,5 @@ CONFIG_FORCE_NO_ASSERT=y
 # Disable HW Stack Protection (see #28664)
 CONFIG_TEST_HW_STACK_PROTECTION=n
 CONFIG_HW_STACK_PROTECTION=n
+
+CONFIG_MP_NUM_CPUS=1

tests/benchmarks/app_kernel/testcase.yaml

@@ -5,6 +5,39 @@ tests:
     min_ram: 32
     tags: benchmark
     timeout: 300
+  benchmark.kernel.application.fp.arm:
+    extra_args: CONF_FILE=prj_fp.conf
+    arch_allow: arm
+    filter: CONFIG_ARMV7_M_ARMV8_M_FP
+    min_flash: 34
+    min_ram: 32
+    tags: benchmark
+    slow: true
+    timeout: 300
+  benchmark.kernel.application.fp.x86.fpu:
+    extra_args: CONF_FILE=prj_fp.conf
+    extra_configs:
+      - CONFIG_SSE=y
+      - CONFIG_SSE_FP_MATH=n
+    arch_allow: x86
+    filter: CONFIG_CPU_HAS_FPU
+    min_flash: 34
+    min_ram: 32
+    tags: benchmark
+    slow: true
+    timeout: 300
+  benchmark.kernel.application.fp.x86.sse:
+    extra_args: CONF_FILE=prj_fp.conf
+    extra_configs:
+      - CONFIG_SSE=y
+      - CONFIG_SSE_FP_MATH=y
+    arch_allow: x86
+    filter: CONFIG_CPU_HAS_FPU
+    min_flash: 34
+    min_ram: 32
+    tags: benchmark
+    slow: true
+    timeout: 300
   benchmark.kernel.application.posix:
     arch_allow: posix
     min_ram: 32