gnu: Add intel-xed.

* gnu/packages/assembly.scm (intel-xed): New variable.
* gnu/packages/patches/intel-xed-fix-nondeterminism.patch: New file.
* gnu/local.mk (dist_patch_DATA): Add reference to new patch.

Signed-off-by: Marius Bakke <marius@gnu.org>

2 files changed, 207 insertions, 0 deletions

diff --git a/gnu/packages/assembly.scm b/gnu/packages/assembly.scm
index 50b64a7f65..cd02541514 100644
--- a/gnu/packages/assembly.scm
+++ b/gnu/packages/assembly.scm
@@ -8,6 +8,7 @@
 ;;; Copyright © 2019 Andy Tai <atai@atai.org>
 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
 ;;; Copyright © 2020 Christopher Lemmer Webber <cwebber@dustycloud.org>
+;;; Copyright © 2020 B. Wilson <elaexuotee@wilsonb.com>
 ;;;
 ;;; This file is part of GNU Guix.
 ;;;
@@ -47,6 +48,7 @@
   #:use-module (gnu packages texinfo)
   #:use-module (gnu packages python)
   #:use-module (gnu packages sphinx)
+  #:use-module (gnu packages shells)
   #:use-module (gnu packages xml)
   #:use-module ((guix utils)
                 #:select (%current-system)))
@@ -405,3 +407,95 @@ Allegrex and RSP instruction sets, partial support for the EmotionEngine
 instruction set, as well as complete support for the ARM7 and ARM9 instruction
 sets, both THUMB and ARM mode.")
     (license license:expat)))
+
+(define-public intel-xed
+  (package
+    (name "intel-xed")
+    (version "11.2.0")
+    (source
+     (origin
+       (method git-fetch)
+       (uri (git-reference
+             (url "https://github.com/intelxed/xed")
+             (commit version)))
+       (sha256 (base32 "1jffayski2gpd54vaska7fmiwnnia8v3cka4nfyzjgl8xsky9v2s"))
+       (file-name (git-file-name name version))
+       (patches (search-patches "intel-xed-fix-nondeterminism.patch"))))
+    (build-system gnu-build-system)
+    (native-inputs
+     `(("python-wrapper" ,python-wrapper)
+       ("tcsh" ,tcsh)
+       ;; As of the time of writing this comment, mbuild does not exist in the
+       ;; Python Package Index and seems to only be used by intel-xed, so we
+       ;; opt to include it here instead of packaging separately.  Note also
+       ;; that the git repository contains no version tags, so we directly
+       ;; reference the "version" variable from setup.py instead.
+       ("mbuild"
+        ,(let ((name "mbuild")
+               (version "0.2496"))
+           (origin
+             (method git-fetch)
+             (uri (git-reference
+                   (url "https://github.com/intelxed/mbuild.git")
+                   (commit "5304b94361fccd830c0e2417535a866b79c1c297")))
+             (sha256
+              (base32
+               "0r3avc3035aklqxcnc14rlmmwpj3jp09vbcbwynhvvmcp8srl7dl"))
+             (file-name (git-file-name name version)))))))
+    (outputs '("out" "lib"))
+    (arguments
+     `(#:phases
+       ;; Upstream uses the custom Python build tool `mbuild', so we munge
+       ;; gnu-build-system to fit.  The build process for this package is
+       ;; documented at https://intelxed.github.io/build-manual/.
+       (let* ((build-dir "build")
+              (kit-dir "kit"))
+         (modify-phases %standard-phases
+           (delete 'configure)
+           (replace 'build
+             (lambda* (#:key inputs #:allow-other-keys)
+               (let ((mbuild (assoc-ref inputs "mbuild")))
+                 (setenv "PYTHONPATH" (string-append
+                                       (getenv "PYTHONPATH") ":" mbuild))
+                 (invoke "./mfile.py"
+                         (string-append "--build-dir=" build-dir)
+                         (string-append "--install-dir=" kit-dir)
+                         "examples"
+                         "doc"
+                         "install"))))
+           (replace 'check
+             (lambda _
+               ;; Skip broken test group `tests/tests-avx512pf'.
+               (invoke "tests/run-cmd.py"
+                       (string-append "--build-dir=" kit-dir "/bin")
+                       "--tests" "tests/tests-base"
+                       "--tests" "tests/tests-avx512"
+                       "--tests" "tests/tests-cet"
+                       "--tests" "tests/tests-via"
+                       "--tests" "tests/tests-syntax"
+                       "--tests" "tests/tests-xop")))
+           (replace 'install
+             (lambda* (#:key outputs #:allow-other-keys)
+               (let* ((out (assoc-ref outputs "out"))
+                      (lib (assoc-ref outputs "lib")))
+                 (copy-recursively (string-append kit-dir "/bin")
+                                   (string-append out "/bin"))
+                 (copy-recursively (string-append kit-dir "/include")
+                                   (string-append lib "/include"))
+                 (copy-recursively (string-append kit-dir "/lib")
+                                   (string-append lib "/lib"))
+                 #t)))))))
+    (home-page "https://intelxed.github.io/")
+    (synopsis "Encoder and decoder for x86 (IA32 and Intel64) instructions")
+    (description "The Intel X86 Encoder Decoder (XED) is a software library and
+for encoding and decoding X86 (IA32 and Intel64) instructions.  The decoder
+takes sequences of 1-15 bytes along with machine mode information and produces
+a data structure describing the opcode, operands, and flags.  The encoder takes
+a similar data structure and produces a sequence of 1 to 15 bytes.  Disassembly
+is essentially a printing pass on the data structure.
+
+The library and development files are under the @code{lib} output, with a
+family of command line utility wrappers in the default output.  Each of the cli
+tools is named like @code{xed*}.  Documentation for the cli tools is sparse, so
+this is a case where ``the code is the documentation.''")
+    (license license:asl2.0)))
diff --git a/gnu/packages/patches/intel-xed-fix-nondeterminism.patch b/gnu/packages/patches/intel-xed-fix-nondeterminism.patch
new file mode 100644
index 0000000000..c81bd0edde
--- /dev/null
+++ b/gnu/packages/patches/intel-xed-fix-nondeterminism.patch
@@ -0,0 +1,113 @@
+This patch removes sources of build non-determinism in the upstream sources.
+
+In particular, many of the compiled sources are generated with Python code,
+which in turn uses dictionaries to index the output C functions.  However,
+iterators over Python dictionaries have no guaranteed order, thus resulting in
+the C functions being output in a random order between builds.
+
+The patch below fixes this by forcing an order during output in several key
+places.  Note, however, that future updates may uncover new such places that
+just happen to be non-problematic at the time of this patch.  If you are
+reading this due to finding such issues, feel free to contact me at
+elaexuotee@wilsonb.com for help.
+
+diff --git a/pysrc/ild_codegen.py b/pysrc/ild_codegen.py
+index 628ec45..a9bff79 100755
+--- a/pysrc/ild_codegen.py
++++ b/pysrc/ild_codegen.py
+@@ -188,14 +188,14 @@ def gen_l2_func_list(agi, target_nt_dict, arg_nt_dict,
+                      ild_t_member):
+     """generate L2 functions"""
+     l2_func_list = []
+-    for (nt_name,array) in target_nt_dict.items():
++    for (nt_name,array) in sorted(target_nt_dict.items()):
+         target_opname = array.get_target_opname()
+         if array.is_const_lookup_fun():
+             fo = gen_const_l2_function(agi, nt_name,
+                                 target_opname, ild_t_member)
+             l2_func_list.append(fo)
+         else:
+-            for arg_nt_seq,arg_arr in arg_nt_dict.items():
++            for arg_nt_seq,arg_arr in sorted(arg_nt_dict.items()):
+                 fo = gen_scalable_l2_function(agi, nt_name,
+                      target_opname, ild_t_member, arg_arr, list(arg_nt_seq))
+                 l2_func_list.append(fo)
+diff --git a/pysrc/ild_disp.py b/pysrc/ild_disp.py
+index 942c036..cf80e29 100755
+--- a/pysrc/ild_disp.py
++++ b/pysrc/ild_disp.py
+@@ -350,7 +350,8 @@ def work(agi, united_lookup,  disp_nts, brdisp_nts, ild_gendir,
+     disp_dict = _gen_l3_array_dict(agi, disp_nts, _disp_token)
+ 
+     
+-    nt_arr_list = list(brdisp_dict.values()) + list(disp_dict.values())
++    nt_arr_list = ([v for (k,v) in sorted(brdisp_dict.items())] +
++                   [v for (k,v) in sorted(disp_dict.items())])
+     #create function that calls all initialization functions
+     init_f = ild_nt.gen_init_function(nt_arr_list, 'xed_ild_disp_l3_init')
+     
+@@ -367,7 +368,7 @@ def work(agi, united_lookup,  disp_nts, brdisp_nts, ild_gendir,
+     l2_functions = []
+     eosz_op = ild_eosz.get_target_opname()
+     easz_op = ild_easz.get_target_opname()
+-    for nt_name,array in list(disp_dict.items()) + list(brdisp_dict.items()):
++    for nt_name,array in sorted(disp_dict.items()) + sorted(brdisp_dict.items()):
+         #Some DISP NTs depend on EOSZ, others on EASZ, we need to know
+         #that when we generate L2 functions
+         if eosz_op in array.get_arg_names():
+diff --git a/pysrc/ild_easz.py b/pysrc/ild_easz.py
+index 02cd691..c53b9f2 100755
+--- a/pysrc/ild_easz.py
++++ b/pysrc/ild_easz.py
+@@ -165,9 +165,10 @@ def work(agi, united_lookup, easz_nts, ild_gendir, debug):
+             return
+         nt_seq_arrays[tuple(nt_seq)] = array
+     #init function calls all single init functions for the created tables
+-    init_f = ild_nt.gen_init_function(list(nt_seq_arrays.values()),
++    nt_seq_values = [v for (k,v) in sorted(nt_seq_arrays.items())]
++    init_f = ild_nt.gen_init_function(nt_seq_values,
+                                        'xed_ild_easz_init')
+-    ild_nt.dump_lu_arrays(agi, list(nt_seq_arrays.values()), _easz_c_fn, 
++    ild_nt.dump_lu_arrays(agi, nt_seq_values, _easz_c_fn, 
+                           mbuild.join('include-private', _easz_header_fn),
+                           init_f)
+     getter_fos = []
+diff --git a/pysrc/ild_eosz.py b/pysrc/ild_eosz.py
+index 6643bc3..89d2d89 100755
+--- a/pysrc/ild_eosz.py
++++ b/pysrc/ild_eosz.py
+@@ -200,10 +200,11 @@ def work(agi, united_lookup, eosz_nts, ild_gendir, debug):
+             return None
+         nt_seq_arrays[tuple(nt_seq)] = array
+     #init function calls all single init functions for the created tables
+-    init_f = ild_nt.gen_init_function(list(nt_seq_arrays.values()), 
++    nt_seq_values = [v for (k,v) in sorted(nt_seq_arrays.items())]
++    init_f = ild_nt.gen_init_function(nt_seq_values, 
+                                       'xed_ild_eosz_init')
+     #dump init and lookup functions for EOSZ sequences
+-    ild_nt.dump_lu_arrays(agi, list(nt_seq_arrays.values()), _eosz_c_fn,
++    ild_nt.dump_lu_arrays(agi, nt_seq_values, _eosz_c_fn,
+                           mbuild.join('include-private', _eosz_header_fn),
+                           init_f)
+     #generate EOSZ getter functions - they get xed_decoded_inst_t*
+diff --git a/pysrc/ild_imm.py b/pysrc/ild_imm.py
+index 51c413c..0530bae 100755
+--- a/pysrc/ild_imm.py
++++ b/pysrc/ild_imm.py
+@@ -322,12 +322,14 @@ def work(agi, united_lookup, imm_nts, ild_gendir, eosz_dict,
+                                      level='l3')
+         nt_dict[nt_name] = array
+ 
++    nt_dict_values = [v for (k,v) in sorted(nt_dict.items())]
++
+     #create function that calls all initialization functions for L3
+-    init_f = ild_nt.gen_init_function(list(nt_dict.values()),
++    init_f = ild_nt.gen_init_function(nt_dict_values,
+                                       'xed_ild_imm_l3_init')
+     
+     #dump L3 functions
+-    ild_nt.dump_lu_arrays(agi, list(nt_dict.values()), _l3_c_fn,
++    ild_nt.dump_lu_arrays(agi, nt_dict_values, _l3_c_fn,
+                           mbuild.join('include-private',_l3_header_fn),
+                           init_f)
+