From a27dcaba32212e226aaf6e565e79925731f2c189 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Nicol=C3=B2=20Scipione?= <nicolo.scipione@codeplay.com>
Date: Mon, 27 May 2024 11:16:47 +0200
Subject: [PATCH] Enable trsm test on NVIDIA GPUs when using DEFAULT
 TUNING_TARGET (#518)

---
 CMakeLists.txt                                  |  1 +
 cmake/Modules/FindDPCPP.cmake                   |  1 +
 src/operations/blas3/gemm_no_local_full_vec.hpp |  2 +-
 test/unittest/CMakeLists.txt                    | 10 ----------
 4 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index e5d18a742..49385a914 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -169,6 +169,7 @@ if (INSTALL_HEADER_ONLY)
     (${TUNING_TARGET} STREQUAL "INTEL_GPU") )
       target_compile_options(portblas INTERFACE -fno-fast-math)
       target_compile_options(portblas INTERFACE -mllvm=-loopopt=0)
+      target_link_options(portblas INTERFACE -mllvm=-loopopt=0)
       message(STATUS "Adding -fno-fast-math -mllvm=-loopopt=0 to portblas")
   endif()
 else()
diff --git a/cmake/Modules/FindDPCPP.cmake b/cmake/Modules/FindDPCPP.cmake
index e07be408b..7e8bf1299 100644
--- a/cmake/Modules/FindDPCPP.cmake
+++ b/cmake/Modules/FindDPCPP.cmake
@@ -102,6 +102,7 @@ function(add_sycl_to_target)
     (${TUNING_TARGET} STREQUAL "INTEL_GPU") )
     target_compile_options(${SB_ADD_SYCL_TARGET} PRIVATE -fno-fast-math)
     target_compile_options(${SB_ADD_SYCL_TARGET} PRIVATE -mllvm=-loopopt=0)
+    target_link_options(${SB_ADD_SYCL_TARGET} PRIVATE -mllvm=-loopopt=0)
     message(STATUS "Adding -fno-fast-math -mllvm=-loopopt=0 to target ${SB_ADD_SYCL_TARGET}")
   endif()
   if ((${CMAKE_CXX_COMPILER_ID} STREQUAL "IntelLLVM"
diff --git a/src/operations/blas3/gemm_no_local_full_vec.hpp b/src/operations/blas3/gemm_no_local_full_vec.hpp
index 3eb7a57c1..24d9e50ac 100644
--- a/src/operations/blas3/gemm_no_local_full_vec.hpp
+++ b/src/operations/blas3/gemm_no_local_full_vec.hpp
@@ -381,7 +381,7 @@ class Gemm<input_t, output_t, DoubleBuffer, NbcA, NbcB, ClSize, tile_type,
       auto C = orig_C;
 
       /* register array used to store the result*/
-      value_t reg_res[item_rows * item_cols];
+      element_t reg_res[item_rows * item_cols];
       scaling_c<need_check_boundary, packet_size>(
           reg_res, C, ldc, dim_m_a_start, dim_n_b_start, boundary_check_c,
           out_of_range);
diff --git a/test/unittest/CMakeLists.txt b/test/unittest/CMakeLists.txt
index c78d8cb15..1c90530c4 100644
--- a/test/unittest/CMakeLists.txt
+++ b/test/unittest/CMakeLists.txt
@@ -103,16 +103,6 @@ if(is_dpcpp)
   )
 endif()
 
-if(is_dpcpp AND ${TUNING_TARGET} STREQUAL "DEFAULT")
-  if (${DPCPP_SYCL_TARGET} MATCHES "nvidia")
-    set(TESTS_TO_SKIP
-      ${PORTBLAS_UNITTEST}/blas3/blas3_trsm_test.cpp
-      )
-    message(WARNING "Targetting NVIDIA hardware with DEFAULT TUNING_TARGET.
-    Disabling tests for following operator: trsm.")
-  endif()
-endif()
-
 if(GEMM_TALL_SKINNY_SUPPORT)
   list(APPEND SYCL_UNITTEST_SRCS ${PORTBLAS_UNITTEST}/blas3/blas3_gemm_tall_skinny_test.cpp)
 endif()