Merge branch 'develop' into amd-develop

test/gemm_universal/test_gemm_universal_xdl.cpp

@@ -56,7 +56,7 @@ class TestGemmUniversal_KM_NK
 using KernelTypes_MK_KN = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
     std::tuple<      F16,       F16,             F16,     F16>,
-#if (defined CK_ENABLE_FP8)
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_FP8_ON_UNSUPPORTED_ARCH)
     std::tuple<      F16,        F8,             F16,     F16>,
     std::tuple<       F8,       F16,             F16,     F16>,
     std::tuple<       F8,        F8,              F8,    BF16>,
@@ -66,7 +66,7 @@ using KernelTypes_MK_KN = ::testing::Types<
 using KernelTypes_MK_NK = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
     std::tuple<      F16,       F16,             F16,     F16>,
-#if (defined CK_ENABLE_FP8)
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_FP8_ON_UNSUPPORTED_ARCH)
     std::tuple<      F16,        F8,             F16,     F16>,
     std::tuple<       F8,       F16,             F16,     F16>,
     std::tuple<       F8,        F8,              F8,    BF16>,

test/grouped_convnd_fwd/test_grouped_convnd_fwd.cpp

@@ -58,13 +58,13 @@ using KernelTypes1d = ::testing::Types<std::tuple<float, GNWC, GKXC, GNWK>,
 using KernelTypes2d = ::testing::Types<std::tuple<float, GNHWC, GKYXC, GNHWK>,
                                        std::tuple<ck::half_t, GNHWC, GKYXC, GNHWK>,
                                        std::tuple<ck::bhalf_t, GNHWC, GKYXC, GNHWK>,
-                                       std::tuple<int8_t, GNHWC, GKYXC, GNHWK>,
                                        std::tuple<float, NHWGC, GKYXC, NHWGK>,
                                        std::tuple<ck::half_t, NHWGC, GKYXC, NHWGK>,
                                        std::tuple<ck::bhalf_t, NHWGC, GKYXC, NHWGK>,
                                        std::tuple<int8_t, NHWGC, GKYXC, NHWGK>,
                                        std::tuple<float, NGCHW, GKYXC, NGKHW>,
-                                       std::tuple<ck::half_t, NGCHW, GKYXC, NGKHW>>;
+                                       std::tuple<ck::half_t, NGCHW, GKYXC, NGKHW>,
+                                       std::tuple<int8_t, NGCHW, GKYXC, NGKHW>>;
 
 using KernelTypes3d = ::testing::Types<std::tuple<float, GNDHWC, GKZYXC, GNDHWK>,
                                        std::tuple<ck::half_t, GNDHWC, GKZYXC, GNDHWK>,

test/grouped_convnd_fwd/test_grouped_convnd_fwd_large_cases_xdl.cpp

@@ -52,7 +52,8 @@ using namespace ck::tensor_layout::convolution;
 
 using KernelTypes2d = ::testing::Types<std::tuple<float, NHWGC, GKYXC, NHWGK>,
                                        std::tuple<ck::half_t, NHWGC, GKYXC, NHWGK>,
-                                       std::tuple<ck::bhalf_t, NHWGC, GKYXC, NHWGK>>;
+                                       std::tuple<ck::bhalf_t, NHWGC, GKYXC, NHWGK>,
+                                       std::tuple<int8_t, NHWGC, GKYXC, NHWGK>>;
 
 using KernelTypes3d = ::testing::Types<std::tuple<float, NDHWGC, GKZYXC, NDHWGK>,
                                        std::tuple<ck::half_t, NDHWGC, GKZYXC, NDHWGK>,