What's new in AOCL 3.1 (#27988)

* What's new in AOCL 3.1

1) AMD BLIS:
    1.a) Supports Dynamic Dispatch and AOCL Dynamic feature
    1.b) Improvements in DGEMM, ZGEMM, DTRSM, DSYRK, xGEMV, and DOTV
2) AMD libFLAME:
    2.a) Supports LAPACK 3.10.0 specification
    2.b) Optimized factorization and ZGEEV routines
3) AMD FFTW:
    3.a) Features like 'AMD application optimization layer', 'Fast MPI transpose algorithm' and 'Top N planner' are added
4) AMD LibM:
    4.a) Optimized exp2, log2 (Single and Double precision) scalar and vector
    4.b) Optimized log10f (scalar and vector) and powf vector variants to support WRF4.1.2 benchmark
5) AOCL-Sparse:
    5.a) New API for sparse matrix and dense matrix multiplication
6) AMD ScaLAPACK:
    6.a) ILP64 support has been enabled
7) AOCL enabled MUMPS library:
    7.a) CMake based build system on Windows for AOCL enabled MUMPS sparse solver library will be available shortly on GitHub
        7.a.i)	Refer https://github.com/amd/mumps-build
    7.b) Spack-based recipe on Linux for AOCL enabled MUMPS sparse solver library will be enabled shortly

* Fix invalid version range error

* Incorporated review comments

1) Restore to previous url value
2) Instead of if else statements, used spack's enable_or_disable feature

* Incorporated following review comments:

1. Use of satisfies() for spec checks
2. Seperate conflict statements to check for minimum and maximum GCC versions
3. Used CMakePackage helpers
4. Code rearrangement to have the directives listed before methods

1 files changed, 142 insertions, 38 deletions

diff --git a/var/spack/repos/builtin/packages/amdfftw/package.py b/var/spack/repos/builtin/packages/amdfftw/package.py
index a43baa1094..8e77b17199 100644
--- a/var/spack/repos/builtin/packages/amdfftw/package.py
+++ b/var/spack/repos/builtin/packages/amdfftw/package.py
@@ -31,36 +31,150 @@ class Amdfftw(FftwBase):
 
     maintainers = ['amd-toolchain-support']
 
+    version('3.1', sha256='3e777f3acef13fa1910db097e818b1d0d03a6a36ef41186247c6ab1ab0afc132')
+    version('3.0.1', sha256='87030c6bbb9c710f0a64f4f306ba6aa91dc4b182bb804c9022b35aef274d1a4c')
     version('3.0', sha256='a69deaf45478a59a69f77c4f7e9872967f1cfe996592dd12beb6318f18ea0bcd')
     version('2.2', sha256='de9d777236fb290c335860b458131678f75aa0799c641490c644c843f0e246f8')
 
-    variant('shared', default=True, description="Builds a shared version of the library")
-    variant('openmp', default=True, description="Enable OpenMP support")
-    variant('threads', default=False, description="Enable SMP threads support")
-    variant('debug', default=False, description="Builds a debug version of the library")
+    variant('shared', default=True,
+            description='Builds a shared version of the library')
+    variant('openmp', default=True,
+            description='Enable OpenMP support')
+    variant('threads', default=False,
+            description='Enable SMP threads support')
+    variant('debug', default=False,
+            description='Builds a debug version of the library')
     variant(
         'amd-fast-planner',
         default=False,
-        description="Option to reduce the planning time without much"
-                    "tradeoff in the performance. It is supported for"
-                    "Float and double precisions only.")
+        description='Option to reduce the planning time without much'
+                    'tradeoff in the performance. It is supported for'
+                    'Float and double precisions only.')
+    variant(
+        'amd-top-n-planner',
+        default=False,
+        description='Build with amd-top-n-planner support')
+    variant(
+        'amd-mpi-vader-limit',
+        default=False,
+        description='Build with amd-mpi-vader-limit support')
+    variant(
+        'static',
+        default=False,
+        description='Build with static suppport')
+    variant(
+        'amd-trans',
+        default=False,
+        description='Build with amd-trans suppport')
+    variant(
+        'amd-app-opt',
+        default=False,
+        description='Build with amd-app-opt suppport')
 
     depends_on('texinfo')
 
     provides('fftw-api@3', when='@2:')
 
-    conflicts('precision=quad', when='@2.2 %aocc', msg="AOCC clang doesn't support quad precision")
-    conflicts('+debug', when='@2.2 %aocc', msg="AOCC clang doesn't support debug")
-    conflicts('%gcc@:7.2', when="@2.2:", msg="Required GCC version above 7.2 for AMDFFTW")
-    conflicts('+amd-fast-planner', when="@2.2", msg="amd-fast-planner is supported from 3.0 onwards")
+    conflicts(
+        'precision=quad',
+        when='@2.2 %aocc',
+        msg='Quad precision is not supported by AOCC clang version 2.2')
+    conflicts(
+        '+debug',
+        when='@2.2 %aocc',
+        msg='debug mode is not supported by AOCC clang version 2.2')
+    conflicts(
+        '%gcc@:7.2',
+        when='@2.2:',
+        msg='GCC version above 7.2 is required for AMDFFTW')
+    conflicts(
+        '+amd-fast-planner ',
+        when='+mpi',
+        msg='mpi thread is not supported with amd-fast-planner')
+    conflicts(
+        '+amd-fast-planner',
+        when='@2.2',
+        msg='amd-fast-planner is supported from 3.0 onwards')
     conflicts(
         '+amd-fast-planner',
         when='precision=quad',
-        msg="amd-fast-planner doesn't support quad precision")
+        msg='Quad precision is not supported with amd-fast-planner')
     conflicts(
         '+amd-fast-planner',
         when='precision=long_double',
-        msg="amd-fast-planner doesn't support long_double precision")
+        msg='long_double precision is not supported with amd-fast-planner')
+    conflicts(
+        '+amd-top-n-planner',
+        when='@:3.0.0',
+        msg='amd-top-n-planner is supported from 3.0.1 onwards')
+    conflicts(
+        '+amd-top-n-planner',
+        when='precision=long_double',
+        msg='long_double precision is not supported with amd-top-n-planner')
+    conflicts(
+        '+amd-top-n-planner',
+        when='precision=quad',
+        msg='Quad precision is not supported with amd-top-n-planner')
+    conflicts(
+        '+amd-top-n-planner',
+        when='+amd-fast-planner',
+        msg='amd-top-n-planner cannot be used with amd-fast-planner')
+    conflicts(
+        '+amd-top-n-planner',
+        when='+threads',
+        msg='amd-top-n-planner works only for single thread')
+    conflicts(
+        '+amd-top-n-planner',
+        when='+mpi',
+        msg='mpi thread is not supported with amd-top-n-planner')
+    conflicts(
+        '+amd-top-n-planner',
+        when='+openmp',
+        msg='openmp thread is not supported with amd-top-n-planner')
+    conflicts(
+        '+amd-mpi-vader-limit',
+        when='@:3.0.0',
+        msg='amd-mpi-vader-limit is supported from 3.0.1 onwards')
+    conflicts(
+        '+amd-mpi-vader-limit',
+        when='precision=quad',
+        msg='Quad precision is not supported with amd-mpi-vader-limit')
+    conflicts(
+        '+amd-trans',
+        when='+threads',
+        msg='amd-trans works only for single thread')
+    conflicts(
+        '+amd-trans',
+        when='+mpi',
+        msg='mpi thread is not supported with amd-trans')
+    conflicts(
+        '+amd-trans',
+        when='+openmp',
+        msg='openmp thread is not supported with amd-trans')
+    conflicts(
+        '+amd-trans',
+        when='precision=long_double',
+        msg='long_double precision is not supported with amd-trans')
+    conflicts(
+        '+amd-trans',
+        when='precision=quad',
+        msg='Quad precision is not supported with amd-trans')
+    conflicts(
+        '+amd-app-opt',
+        when='@:3.0.1',
+        msg='amd-app-opt is supported from 3.1 onwards')
+    conflicts(
+        '+amd-app-opt',
+        when='+mpi',
+        msg='mpi thread is not supported with amd-app-opt')
+    conflicts(
+        '+amd-app-opt',
+        when='precision=long_double',
+        msg='long_double precision is not supported with amd-app-opt')
+    conflicts(
+        '+amd-app-opt',
+        when='precision=quad',
+        msg='Quad precision is not supported with amd-app-opt')
 
     def configure(self, spec, prefix):
         """Configure function"""
@@ -72,28 +186,13 @@ class Amdfftw(FftwBase):
 
         # Check if compiler is AOCC
         if '%aocc' in spec:
-            options.append("CC={0}".format(os.path.basename(spack_cc)))
-            options.append("FC={0}".format(os.path.basename(spack_fc)))
-            options.append("F77={0}".format(os.path.basename(spack_fc)))
-
-        if '+shared' in spec:
-            options.append('--enable-shared')
-        else:
-            options.append('--disable-shared')
+            options.append('CC={0}'.format(os.path.basename(spack_cc)))
+            options.append('FC={0}'.format(os.path.basename(spack_fc)))
+            options.append('F77={0}'.format(os.path.basename(spack_fc)))
 
         if '+debug' in spec:
             options.append('--enable-debug')
 
-        if '+openmp' in spec:
-            options.append('--enable-openmp')
-        else:
-            options.append('--disable-openmp')
-
-        if '+threads' in spec:
-            options.append('--enable-threads')
-        else:
-            options.append('--disable-threads')
-
         if '+mpi' in spec:
             options.append('--enable-mpi')
             options.append('--enable-amd-mpifft')
@@ -101,13 +200,18 @@ class Amdfftw(FftwBase):
             options.append('--disable-mpi')
             options.append('--disable-amd-mpifft')
 
-        if '+amd-fast-planner' in spec:
-            options.append('--enable-amd-fast-planner')
-        else:
-            options.append('--disable-amd-fast-planner')
+        options.extend(self.enable_or_disable('shared'))
+        options.extend(self.enable_or_disable('openmp'))
+        options.extend(self.enable_or_disable('threads'))
+        options.extend(self.enable_or_disable('amd-fast-planner'))
+        options.extend(self.enable_or_disable('amd-top-n-planner'))
+        options.extend(self.enable_or_disable('amd-mpi-vader-limit'))
+        options.extend(self.enable_or_disable('static'))
+        options.extend(self.enable_or_disable('amd-trans'))
+        options.extend(self.enable_or_disable('amd-app-opt'))
 
         if not self.compiler.f77 or not self.compiler.fc:
-            options.append("--disable-fortran")
+            options.append('--disable-fortran')
 
         # Cross compilation is supported in amd-fftw by making use of target
         # variable to set AMD_ARCH configure option.
@@ -115,9 +219,9 @@ class Amdfftw(FftwBase):
         # use target variable to set appropriate -march option in AMD_ARCH.
         arch = spec.architecture
         options.append(
-            "AMD_ARCH={0}".format(
+            'AMD_ARCH={0}'.format(
                 arch.target.optimization_flags(
-                    spec.compiler).split("=")[-1]))
+                    spec.compiler).split('=')[-1]))
 
         # Specific SIMD support.
         # float and double precisions are supported