Merge release-5-0 into master

[alexxy/gromacs.git] / cmake / gmxTestSimd.cmake

diff --git a/cmake/gmxTestSimd.cmake b/cmake/gmxTestSimd.cmake
index 3dd7407e4e7a74b0535e11accbc3a6c58ad699db..db57dd3f36771c081bf0d5693486ec9e9b57cd17 100644 (file)
--- a/cmake/gmxTestSimd.cmake
+++ b/cmake/gmxTestSimd.cmake
@@ -249,6 +249,56 @@ elseif(${GMX_SIMD} STREQUAL "AVX2_256")
     set(GMX_SIMD_X86_AVX2_256 1)
     set(SIMD_STATUS_MESSAGE "Enabling 256-bit AVX2 SIMD instructions")
 
+elseif(${GMX_SIMD} STREQUAL "ARM_NEON")
+
+    gmx_find_cflag_for_source(CFLAGS_ARM_NEON "C compiler 32-bit ARM NEON flag"
+                              "#include<arm_neon.h>
+                              int main(){float32x4_t x=vdupq_n_f32(0.5);x=vmlaq_f32(x,x,x);return vgetq_lane_f32(x,0)>0;}"
+                              SIMD_C_FLAGS
+                              "-mfpu=neon" "")
+    gmx_find_cxxflag_for_source(CXXFLAGS_ARM_NEON "C++ compiler 32-bit ARM NEON flag"
+                                "#include<arm_neon.h>
+                                int main(){float32x4_t x=vdupq_n_f32(0.5);x=vmlaq_f32(x,x,x);return vgetq_lane_f32(x,0)>0;}"
+                                SIMD_CXX_FLAGS
+                                "-mfpu=neon" "-D__STDC_CONSTANT_MACROS" "")
+
+    if(NOT CFLAGS_ARM_NEON OR NOT CXXFLAGS_ARM_NEON)
+        message(FATAL_ERROR "Cannot find ARM 32-bit NEON compiler flag. Use a newer compiler, or disable NEON SIMD.")
+    endif()
+
+    set(GMX_SIMD_ARM_NEON 1)
+    set(SIMD_STATUS_MESSAGE "Enabling 32-bit ARM NEON SIMD instructions")
+
+elseif(${GMX_SIMD} STREQUAL "ARM_NEON_ASIMD")
+    # Gcc-4.8.1 appears to have a bug where the c++ compiler requires
+    # -D__STDC_CONSTANT_MACROS if we include arm_neon.h
+
+    gmx_find_cflag_for_source(CFLAGS_ARM_NEON_ASIMD "C compiler ARM NEON Advanced SIMD flag"
+                              "#include<arm_neon.h>
+                              int main(){float64x2_t x=vdupq_n_f64(0.5);x=vfmaq_f64(x,x,x);return vgetq_lane_f64(x,0)>0;}"
+                              SIMD_C_FLAGS
+                              "")
+    gmx_find_cxxflag_for_source(CXXFLAGS_ARM_NEON_ASIMD "C++ compiler ARM NEON Advanced SIMD flag"
+                                "#include<arm_neon.h>
+                                int main(){float64x2_t x=vdupq_n_f64(0.5);x=vfmaq_f64(x,x,x);return vgetq_lane_f64(x,0)>0;}"
+                                SIMD_CXX_FLAGS
+                                "-D__STDC_CONSTANT_MACROS" "")
+
+    if(NOT CFLAGS_ARM_NEON_ASIMD OR NOT CXXFLAGS_ARM_NEON_ASIMD)
+        message(FATAL_ERROR "Cannot find ARM (AArch64) NEON Advanced SIMD compiler flag. Use a newer compiler, or disable SIMD.")
+    endif()
+
+    if(CMAKE_C_COMPILER_ID MATCHES "GNU" AND CMAKE_C_COMPILER_VERSION VERSION_LESS "4.9")
+        message(WARNING "At least gcc-4.8.1 has many bugs for ARM (AArch64) NEON Advanced SIMD compilation. You might need gcc version 4.9 or later.")
+    endif()
+
+    if(CMAKE_C_COMPILER_ID MATCHES "Clang" AND CMAKE_C_COMPILER_VERSION VERSION_LESS "3.4")
+        message(FATAL_ERROR "Clang version 3.4 or later is required for ARM (AArch64) NEON Advanced SIMD.")
+    endif()
+
+    set(GMX_SIMD_ARM_NEON_ASIMD 1)
+    set(SIMD_STATUS_MESSAGE "Enabling ARM (AArch64) NEON Advanced SIMD instructions")
+
 elseif(${GMX_SIMD} STREQUAL "IBM_QPX")
 
     try_compile(TEST_QPX ${CMAKE_BINARY_DIR}
@@ -263,6 +313,26 @@ elseif(${GMX_SIMD} STREQUAL "IBM_QPX")
         message(FATAL_ERROR "Cannot compile the requested IBM QPX intrinsics. If you are compiling for BlueGene/Q with the XL compilers, use 'cmake .. -DCMAKE_TOOLCHAIN_FILE=Platform/BlueGeneQ-static-XL-C' to set up the tool chain.")
     endif()
 
+elseif(${GMX_SIMD} STREQUAL "IBM_VMX")
+
+    gmx_find_cflag_for_source(CFLAGS_IBM_VMX "C compiler IBM VMX SIMD flag"
+                              "#include<altivec.h>
+                              int main(){vector float x,y=vec_ctf(vec_splat_s32(1),0);x=vec_madd(y,y,y);return vec_all_ge(y,x);}"
+                              SIMD_C_FLAGS
+                              "-maltivec -mabi=altivec" "-qarch=auto -qaltivec")
+    gmx_find_cxxflag_for_source(CXXFLAGS_IBM_VMX "C++ compiler IBM VMX SIMD flag"
+                                "#include<altivec.h>
+                                int main(){vector float x,y=vec_ctf(vec_splat_s32(1),0);x=vec_madd(y,y,y);return vec_all_ge(y,x);}"
+                                SIMD_CXX_FLAGS
+                                "-maltivec -mabi=altivec" "-qarch=auto -qaltivec")
+
+    if(NOT CFLAGS_IBM_VMX OR NOT CXXFLAGS_IBM_VMX)
+        message(FATAL_ERROR "Cannot find IBM VMX SIMD compiler flag. Use a newer compiler, or disable VMX SIMD.")
+    endif()
+
+    set(GMX_SIMD_IBM_VMX 1)
+    set(SIMD_STATUS_MESSAGE "Enabling IBM VMX SIMD instructions")
+
 elseif(${GMX_SIMD} STREQUAL "SPARC64_HPC_ACE")
 
     # Note that GMX_RELAXED_DOUBLE_PRECISION is enabled by default in the top-level CMakeLists.txt