Add files via upload

Makefile

@@ -0,0 +1,88 @@
+CC=g++ -fopenmp
+CFLAGS= -mavx2 -std=c++14 -O3 -Wall -Wextra -pedantic
+LDFLAGS=
+EXEC=evaluate evaluate_single search_GC_n3 search_GC_n4 search_depth_n3 search_depth_n4 filter_n3 filter_n4 gen_n3 gen_n4
+
+all: $(EXEC)
+
+evaluate: evaluate.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DEVA
+
+evaluate.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DEVA
+
+evaluate_single: evaluate_single.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DEVA_Single
+
+evaluate_single.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DEVA_Single
+
+search_GC_n3: search_GC_n3.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DGC -DSIZEINBIT=3
+
+search_GC_n3.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DGC -DSIZEINBIT=3
+
+search_GC_n4: search_GC_n4.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DGC -DSIZEINBIT=4
+
+search_GC_n4.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DGC -DSIZEINBIT=4
+
+
+search_depth_n3: search_depth_n3.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DDEPTH -DSIZEINBIT=3
+
+search_depth_n3.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DDEPTH -DSIZEINBIT=3
+
+search_depth_n4: search_depth_n4.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DDEPTH -DSIZEINBIT=4
+
+search_depth_n4.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DDEPTH -DSIZEINBIT=4
+
+
+filter_n3: filter_n3.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DFILTER -DSIZEINBIT=3
+
+filter_n3.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DFILTER -DSIZEINBIT=3
+
+filter_n4: filter_n4.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DFILTER -DSIZEINBIT=4
+
+filter_n4.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DFILTER -DSIZEINBIT=4
+
+
+gen_n3: gen_n3.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DGEN -DSIZEINBIT=3
+
+gen_n3.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DGEN -DSIZEINBIT=3
+
+gen_n4: gen_n4.o
+	$(CC) -o $@ $^ $(LDFLAGS) -DGEN -DSIZEINBIT=4
+
+gen_n4.o: main.cpp
+	$(CC) -o $@ -c $< $(CFLAGS) -DGEN -DSIZEINBIT=4
+
+
+clean:
+	rm -rf *.o
+
+mrproper: clean
+	rm -rf $(EXEC)
+	rm test_faster
+	rm test_lighter
+
+gencheck:
+	find ./R -maxdepth 1 -name "*.c" -print > results.c
+	$(CC) $(CFLAGS) genTest.cpp -o genTest && ./genTest
+
+checkfaster:
+	$(CC) $(CFLAGS) faster_test.cpp -o test_faster && ./test_faster
+
+checklighter:
+	$(CC) $(CFLAGS) faster_test.cpp -o test_lighter && ./test_lighter

MakefileSage

@@ -0,0 +1,41 @@
+# To build, rename this file as Makefile
+# Compile inside the Sage shell: sage -sh -c make
+# Then start Sage: from peigen import Lighter
+#                : A = Lighter()
+#                : A.evaluate_4bit()
+# Similiar for Faster: from peigen import Faster
+CC= g++
+CXXFLAGS= -fopenmp -mavx2 -std=c++14 -O3 -fPIC -fwrapv -fno-strict-aliasing \
+	-Wall -Wextra -pedantic -g -pg  \
+	-I$(SAGE_LOCAL)/include \
+	-I$(SAGE_LOCAL)/include/python2.7
+LDFLAGS = -fopenmp -lm -lstdc++
+
+OUTPUT_OPTION = -MMD -MP -o $@
+-include $(DEP)
+
+EXEC = peigen
+
+SRC = peigen.cpp
+OBJ = $(SRC:.cpp=.o)
+DEP = $(SRC:.cpp=.d)
+
+all: peigen.so
+
+peigen.cpp: peigen.pyx peigen.pxd
+	cython --cplus $<
+
+$(OBJ):$(SRC)
+
+peigen.so: $(OBJ)
+	$(CC) -shared -pthread -o peigen.so $^ $(LDFLAGS)
+
+$(EXEC): $(OBJ)
+	$(CC) $(LDFLAGS) $^ -o $@
+
+clean:
+	rm -f $(OBJ) $(DEP) $(EXEC)
+
+.PHONY: clean
+
+-include $(DEP)

OptimalSboxes.hpp

@@ -0,0 +1,62 @@
+/**
+ * PEIGEN: a Platform for Evaluation, Implementation, and Generation of S-boxes
+ *
+ *  Copyright 2019 by
+ *    Zhenzhen Bao <baozhenzhen10[at]gmail.com>
+ *    Jian Guo <guojian[at]ntu.edu.sg>
+ *    San Ling <lingsan[at]ntu.edu.sg>
+ *    Yu Sasaki <yu[dot]sasaki[dot][email protected]>
+ * 
+ * This platform is developed based on the open source application
+ * <http://jeremy.jean.free.fr/pub/fse2018_layer_implementations.tar.gz>
+ * Optimizing Implementations of Lightweight Building Blocks
+ *
+ *  Copyright 2017 by
+ *    Jade Tourteaux <Jade[dot]Tourteaux[at]gmail.com>
+ *    Jérémy Jean <Jean[dot]Jeremy[at]gmail.com>
+ * 
+ * We follow the same copyright policy.
+ * 
+ * This file is part of some open source application.
+ * 
+ * Some open source application is free software: you can redistribute 
+ * it and/or modify it under the terms of the GNU General Public 
+ * License as published by the Free Software Foundation, either 
+ * version 3 of the License, or (at your option) any later version.
+ * 
+ * Some open source application is distributed in the hope that it will 
+ * be useful, but WITHOUT ANY WARRANTY; without even the implied warranty 
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
+ * You should have received a copy of the GNU General Public License
+ * along with Foobar.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * @license GPL-3.0+ <http://spdx.org/licenses/GPL-3.0+>
+ */
+
+#ifndef GSBOXES_H__
+#define GSBOXES_H__
+
+#define OPTIMAL_G4_N 16
+
+const ALIGNED_TYPE_(uint8_t, 16) G4[OPTIMAL_G4_N][16] = {
+/* Optimal_S0  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 11, 12, 9, 3, 14, 10, 5},
+/* Optimal_S1  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 11, 14, 3, 5, 9, 10, 12},
+/* Optimal_S2  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 11, 14, 3, 10, 12, 5, 9},
+/* Optimal_S3  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 12, 5, 3, 10, 14, 11, 9},
+/* Optimal_S4  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 12, 9, 11, 10, 14, 5, 3},
+/* Optimal_S5  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 12, 11, 9, 10, 14, 3, 5},
+/* Optimal_S6  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 12, 11, 9, 10, 14, 5, 3},
+/* Optimal_S7  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 12, 14, 11, 10, 9, 3, 5},
+/* Optimal_S8  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 9, 5, 10, 11, 3, 12},
+/* Optimal_S9  */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 11, 3, 5, 9, 10, 12},
+/* Optimal_S10 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 11, 5, 10, 9, 3, 12},
+/* Optimal_S11 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 11, 10, 5, 9, 12, 3},
+/* Optimal_S12 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 11, 10, 9, 3, 12, 5},
+/* Optimal_S13 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 12, 9, 5, 11, 10, 3},
+/* Optimal_S14 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 12, 11, 3, 9, 5, 10},
+/* Optimal_S15 */ {0, 1, 2, 13, 4, 7, 15, 6, 8, 14, 12, 11, 9, 3, 10, 5}
+};
+
+#endif  //GSBOXES_H__

README.md

@@ -1,4 +1,4 @@
-# PEIGEN: a Platform for Evaluation, Implementation, and Generation of S-boxes
+# PEIGEN: a Platform for Evaluation, Implementation, and Generation of S-boxes
 
 PEIGEN is a tool for study S-boxes.
 
@@ -145,25 +145,25 @@ Concrete usage are as follows.
     - same as in [LIGHTER](http://jeremy.jean.free.fr/pub/fse2018_layer_implementations.tar.gz), if `[-a]` is not enabled, available logic gates should be explicitly added in this command line (and weight of each gate should be specified in the provided configure file):
 
       --not1
-      
+
       --and2
-      
+
       --nand2
-      
+
       --or2
-      
+
       --nor2
-      
+
       --nand3
-      
+
       --nor3
-      
+
       --xor2
-      
+
       --xnor2
-      
+
       --maoi1
-      
+
       --moai1
 
   - use `sboxn_GC.pre_compute(args);` to precompute the graph, this will expand the graph from the Identity function, with parameters encoded in `args`, and store the generated graph in binary files. For each configuration (the library of gates `-f <file>` and the limitation for precomputation `-c <value>`), this can be done once for all. Thus, if this has been done, the generated binary files are stored and available, we can directly call the search function.
@@ -293,33 +293,28 @@ Concrete usage are as follows.
 - Sorry for the inconvenience again, but for small efficiency gain, bitslicing of the S-boxes is done in little endian byte and little endian bit order (this is inconsistent with that in [LIGHTER](http://jeremy.jean.free.fr/pub/fse2018_layer_implementations.tar.gz)): the least significant value is placed at the leftmost side in memory and, the least significant bit of the value is placed at the leftmost side in the value, e.g., suppose the LUT:
 
     LUT in hexadecimal (**big endian byte** order and **little endian bit** order):
-
     | 0x0 | 0x1 | 0x2 | 0x3 | 0x4 | 0x5 | 0x6 | 0x7 | 0x8 | 0x9 | 0xa | 0xb | 0xc | 0xd | 0xe | 0xf |
     | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
     | 0xc | 0x5 | 0x6 | 0xb | 0x9 | 0x0 | 0xa | 0xd | 0x3 | 0xe | 0xf | 0x8 | 0x4 | 0x7 | 0x1 | 0x2 |
 
     LUT in binary (**big endian byte** order and **little endian bit** order):
-
     | 0000 | 0001 | 0010 | 0011 | 0100 | 0101 | 0110 | 0111 | 1000 | 1001 | 1010 | 1011 | 1100 | 1101 | 1110 | 1111 |
     | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
     | 1100 | 0101 | 0110 | 1011 | 1001 | 0000 | 1010 | 1101 | 0011 | 1110 | 1111 | 1000 | 0100 | 0111 | 0001 | 0010 |
 
     In PEIGEN, bitslicing is done as follows:
 
     LUT in binary in memory (**little endian byte** order and **little endian bit** order):
-
     | 1111 | 1110 | 1101 | 1100 | 1011 | 1010 | 1001 | 1000 | 0111 | 0110 | 0101 | 0100 | 0011 | 0010 | 0001 | 0000 |
     | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
     | 0010 | 0001 | 0111 | 0100 | 1000 | 1111 | 1110 | 0011 | 1101 | 1010 | 0000 | 1001 | 1011 | 0110 | 0101 | 1100 |
 
     Bitslicing (**little endian byte** order and **little endian bit** order):
-
     | 1111111100000000 | 1111000011110000 | 1100110011001100 | 1010101010101010 |
     | ---------------- | ---------------- | ---------------- | ---------------- |
     | 0000111011011001 | 0011011010000111 | 1010011101001100 | 0110010110011010 |
 
     Condensed bitsliced representation (directly indicate memory):
-
     | ff00_f0f0_cccc_aaaa |
     | ------------------- |
     | 0ed9_3687_a74c_659a |

STM65nm.conf

@@ -0,0 +1,15 @@
+not1_cost=0.5
+and2_cost=1.5
+nand2_cost=1.00
+or2_cost=1.5
+nor2_cost=1.00
+xor2_cost=2.00
+xnor2_cost=2.00
+maoi1_cost=2.50
+moai1_cost=2.50
+nand3_cost=1.5
+nor3_cost=1.5
+and3_cost=2
+or3_cost=2
+andn2_cost=1.5
+orn2_cost=1.5

TSMC65nm.conf

@@ -0,0 +1,30 @@
+not1_cost=0.5
+and2_cost=1.5
+nand2_cost=1.00
+or2_cost=1.5
+nor2_cost=1.00
+xor2_cost=3.00
+xnor2_cost=3.00
+maoi1_cost=2.50
+moai1_cost=2.50
+nand3_cost=1.5
+nor3_cost=1.5
+and3_cost=2
+or3_cost=2
+andn2_cost=1.5
+orn2_cost=1.5
+#not1_cost=0.5
+#and2_cost=1.5
+#nand2_cost=1.00
+#or2_cost=1.5
+#nor2_cost=1.00
+#xor2_cost=2.00
+#xnor2_cost=2.00
+#maoi1_cost=2.50
+#moai1_cost=2.50
+#nand3_cost=1.5
+#nor3_cost=1.5
+#and3_cost=2
+#or3_cost=2
+#andn2_cost=1.5
+#orn2_cost=1.5

UMC180nm.conf

@@ -0,0 +1,15 @@
+not1_cost=0.67
+and2_cost=1.33
+nand2_cost=1.00
+or2_cost=1.33
+nor2_cost=1.00
+xor2_cost=3.00
+xnor2_cost=3.00
+maoi1_cost=2.67
+moai1_cost=2.00
+nand3_cost=1.33
+nor3_cost=1.33
+and3_cost=2.33
+or3_cost=2.33
+andn2_cost=1.67
+orn2_cost=1.67