cpp/Dockerfile

@@ -1,15 +1,15 @@
-FROM nvidia/cuda:12.5.0-devel-ubi9 as builder
+FROM nvidia/cuda:12.4.1-devel-ubi9 as builder
 
 WORKDIR /home/ViolaJones/cpp
 
 COPY *.cu *.cpp *.hpp Makefile ./
 RUN make -j "$(nproc)"
 
-FROM nvidia/cuda:12.5.0-base-ubi9
+FROM nvidia/cuda:12.4.1-base-ubi9
 
 WORKDIR /home/ViolaJones/cpp
 
-RUN dnf install -y make-1:4.3-8.el9 && dnf clean all
+RUN dnf install -y make-1:4.3-7.el9 && dnf clean all
 COPY --from=builder /home/ViolaJones/cpp/bin ./bin
 COPY --from=builder /home/ViolaJones/cpp/Makefile .
 

cpp/Makefile

@@ -8,7 +8,7 @@ DATA_PATH := ../data
 #CFLAGS := -O0 -g -G -pg -Xptxas=-w -Xcompiler -O0,-rdynamic,-g
 CFLAGS := -dlto -O2 -Xcompiler -O2
 #CFLAGS := -dlto -O2 -g -Xcompiler -O2,-g,-ggdb
-CFLAGS := $(CFLAGS) -MMD -MP -Werror=all-warnings -Xcompiler -Wall,-Werror,-Wextra
+CFLAGS := $(CFLAGS) -MMD -MP -Werror=all-warnings -Xcompiler -Wall,-Werror,-Werror=implicit-fallthrough=0,-Wextra
 EXEC := $(OBJ_DIR)/ViolaJones
 DATA := $(DATA_PATH)/X_train.bin $(DATA_PATH)/X_test.bin $(DATA_PATH)/y_train.bin $(DATA_PATH)/y_test.bin
 SRC := $(shell find $(SRC_DIR) -name '*.cpp' -o -name '*.cu')
@@ -63,7 +63,7 @@ check: $(EXEC) $(DATA) | check-valgrind-works
 	@valgrind -q -s --leak-check=full --show-leak-kinds=all $(EXEC)
 
 .PHONY: cudacheck
-cudacheck: $(EXEC) $(DATA) | check-compute-sanitizer-works
+cudacheck: $(EXEC) $(DATA) | check-computer-sanitizer-works
 	@compute-sanitizer --destroy-on-device-error kernel --tool memcheck --leak-check full --report-api-errors all --track-stream-ordered-races all --target-processes all $(EXEC)
 	#@compute-sanitizer --destroy-on-device-error kernel --tool racecheck --racecheck-detect-level info --racecheck-report all $(EXEC)
 	#@compute-sanitizer --destroy-on-device-error kernel --tool initcheck --track-unused-memory yes $(EXEC)
@@ -88,7 +88,9 @@ log: $(DATA) reset
 .PHONY: reset
 reset:
 	@echo 'Deleting generated states and models'
-	@rm -frv $(OUT_DIR) $(MODELS_DIR)
+	@rm -frv $(OUT_DIR)/* $(MODELS_DIR)/*
+#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/models .
+#@ln -sv /mnt/pierre_stuffs/ViolaJones/cpp/out .
 
 .PHONY: clean
 clean:
@@ -128,8 +130,8 @@ check-dot-works:
 check-valgrind-works:
 	@valgrind --version >/dev/null 2>&1 || (echo 'Please install valgrind.' && exit 1)
 
-.PHONY: check-compute-sanitizer-works
-check-compute-sanitizer-works:
-	@compute-sanitizer --version >/dev/null 2>&1 || (echo 'Please install Compute Sanitizer from Cuda toolkit.' && exit 1)
+.PHONY: check-computer-sanitizer-works
+check-computer-sanitizer-works:
+	@computer-sanitizer --version >/dev/null 2>&1 || (echo 'Please install Compute Sanitizer from Cuda toolkit.' && exit 1)
 
 -include $(OBJ:.o=.d)

cpp/test.cpp

@@ -0,0 +1,62 @@
+#include <iostream>
+#include <iomanip>
+#include "data.hpp"
+#include "toolbox.hpp"
+
+#define PBSTR "||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||"
+#define PBWIDTH 60
+
+void printProgress(const float64_t& percentage) noexcept {
+	const uint64_t val = static_cast<uint64_t>(percentage * 100);
+	const int32_t lpad = static_cast<int32_t>(percentage * PBWIDTH);
+	const int32_t rpad = PBWIDTH - lpad;
+	fprintf(stderr, "%3lu%% [%.*s%*s]\r", val, lpad, PBSTR, rpad, "");
+	fflush(stderr);
+}
+
+void clearProgress(void) noexcept {
+	// Progress bar width + space before + num space + space after
+	fprintf(stderr, "%*c\r", PBWIDTH + 1 + 3 + 3, ' ');
+}
+
+template<typename T>
+void test(const uint64_t& N) noexcept {
+#if __DEBUG
+	printf("DETERMINISTIC for N=%s of %s sized %s\n", thousand_sep(N).c_str(), typeid(T).name(), format_byte_size(sizeof(T)).c_str());
+	printf("Estimating memory footprint at : %s\n", format_byte_size(3 * N * sizeof(T)).c_str());
+#endif
+
+	T *a = new T[N], *b = new T[N], *c = new T[N];
+
+	T mean = static_cast<T>(0.0);
+	const size_t percent = N / 100;
+	for(size_t i = 0; i < N; ++i){
+		if (i % percent == 0) printProgress(static_cast<float64_t>(i) / N);
+		a[i] = static_cast<T>(i < N>>1 ? 0.1 : 1.0);
+		b[i] = static_cast<T>(1.0);
+		c[i] = a[i] * b[i];
+		mean += c[i];
+	}
+	mean /= static_cast<T>(N);
+
+	clearProgress();
+	std::cout << mean << std::endl;
+
+	delete[] a, delete[] b, delete[] c;
+}
+
+void test_float(void) noexcept {
+	std::cout << std::setprecision(1<<8);
+	const uint64_t N = static_cast<uint64_t>(1)<<28;
+	test<float128_t>(N);
+	test<float64_t>(N);
+	test<float32_t>(N);
+
+	//printf("%.128af\n", static_cast<float64_t>(1) / 3);
+	//std::cout << static_cast<float64_t>(1) / 3 << std::endl;
+	//std::cout << std::hexfloat << static_cast<float64_t>(1) / 3 << std::endl;
+
+	//printf("%.128Lf\n", static_cast<long float64_t>(1) / 3);
+	//printf("%.128lf\n", static_cast<float64_t>(1) / 3);
+	//printf("%.128f\n", static_cast<float>(1) / 3);
+}

downloader/Dockerfile

@@ -1,6 +1,6 @@
-FROM alpine:3.20.0
+FROM alpine:3.19.1
 
-RUN apk add --no-cache curl=8.7.1-r0 python3=3.12.3-r1 && rm -rf /var/cache/apk*
+RUN apk add --no-cache curl=8.5.0-r0 python3=3.11.9-r0 && rm -rf /var/cache/apk*
 
 WORKDIR /home/ViolaJones/downloader
 COPY requirements.txt activate.sh ./

python/Dockerfile

@@ -1,8 +1,7 @@
-FROM nvidia/cuda:12.5.0-devel-ubi9 as builder
+FROM nvidia/cuda:12.4.1-devel-ubi9 as builder
 
-RUN dnf install -y python3.11-3.11.7-1.el9 \
-	&& dnf clean all \
-	&& ln -s /usr/bin/python3 /usr/bin/python
+RUN dnf install -y python3.11-3.11.5-1.el9_3 && dnf clean all
+RUN ln -s /usr/bin/python3 /usr/bin/python
 
 WORKDIR /home/ViolaJones/python
 COPY Makefile activate.sh requirements.txt ./