diff --git a/.ci/gdbstub-test.sh b/.ci/gdbstub-test.sh
index 6bba5668..6128ddf8 100755
--- a/.ci/gdbstub-test.sh
+++ b/.ci/gdbstub-test.sh
@@ -2,12 +2,12 @@
 
 set -e -u -o pipefail
 
-export PATH=`pwd`/toolchain/riscv/bin:$PATH
+export PATH=`pwd`/toolchain/bin:$PATH
 
 GDB=
-prefixes=("${CROSS_COMPILE}" "riscv32-unknown-elf" "riscv-none-elf")
+prefixes=("${CROSS_COMPILE}" "riscv32-unknown-elf-" "riscv-none-elf-")
 for prefix in "${prefixes[@]}"; do
-    utility=${prefix}-gdb
+    utility=${prefix}gdb
     set +e # temporarily disable exit on error
     command -v "${utility}" &> /dev/null
     if [[ $? == 0 ]]; then
@@ -21,7 +21,7 @@ if [ -z ${GDB} ]; then
     exit 1
 fi
 
-build/rv32emu -g build/puzzle.elf &
+build/rv32emu -g build/riscv32/puzzle &
 PID=$!
 
 # Before starting GDB, we should ensure rv32emu is still running.
@@ -31,9 +31,9 @@ fi
 
 OPTS=
 tmpfile=/tmp/rv32emu-gdbstub.$PID
-breakpoints=(0x10700 0x10800 0x10900)
+breakpoints=(0x10500 0x10600 0x10700)
 bkpt_count=${#breakpoints[@]}
-OPTS+="-ex 'file build/puzzle.elf' "
+OPTS+="-ex 'file build/riscv32/puzzle' "
 OPTS+="-ex 'target remote :1234' "
 for t in ${breakpoints[@]}; do
     OPTS+="-ex 'break *$t' "
diff --git a/.ci/riscv-tests.sh b/.ci/riscv-tests.sh
index ad11fda7..8d5b5d72 100755
--- a/.ci/riscv-tests.sh
+++ b/.ci/riscv-tests.sh
@@ -7,7 +7,7 @@ pip3 install git+https://github.com/riscv/riscof.git@d38859f85fe407bcacddd2efcd3
 
 set -x
 
-export PATH=`pwd`/toolchain/riscv/bin:$PATH
+export PATH=`pwd`/toolchain/bin:$PATH
 
 make clean
 make arch-test RISCV_DEVICE=IMAFCZicsrZifencei || exit 1
diff --git a/.ci/riscv-toolchain-install.sh b/.ci/riscv-toolchain-install.sh
index 23f8edf6..d9eadae0 100755
--- a/.ci/riscv-toolchain-install.sh
+++ b/.ci/riscv-toolchain-install.sh
@@ -8,10 +8,15 @@ check_platform
 
 mkdir -p toolchain
 
-# GNU Toolchain for RISC-V
-GCC_VER=2024.04.12
-TOOLCHAIN_REPO=https://github.com/riscv-collab/riscv-gnu-toolchain/releases
+if [[ "$#" == "0" ]] || [[ "$1" != "riscv-collab" ]]; then
+    GCC_VER=14.2.0-1
+    TOOLCHAIN_REPO=https://github.com/xpack-dev-tools/riscv-none-elf-gcc-xpack
+    TOOLCHAIN_URL=${TOOLCHAIN_REPO}/releases/download/v${GCC_VER}/xpack-riscv-none-elf-gcc-${GCC_VER}-linux-x64.tar.gz
+else
+    UBUNTU_VER=`lsb_release -r | cut -f2`
+    GCC_VER=2024.04.12
+    TOOLCHAIN_REPO=https://github.com/riscv-collab/riscv-gnu-toolchain
+    TOOLCHAIN_URL=${TOOLCHAIN_REPO}/releases/download/${GCC_VER}/riscv32-elf-ubuntu-${UBUNTU_VER}-gcc-nightly-${GCC_VER}-nightly.tar.gz
+fi
 
-wget -q \
-    ${TOOLCHAIN_REPO}/download/${GCC_VER}/riscv32-elf-ubuntu-22.04-gcc-nightly-${GCC_VER}-nightly.tar.gz -O- \
-| tar -C toolchain -xz
+wget -q ${TOOLCHAIN_URL} -O- | tar -C toolchain --strip-components=1 -xz
diff --git a/.github/workflows/build-artifact.yml b/.github/workflows/build-artifact.yml
new file mode 100644
index 00000000..fc5b84bc
--- /dev/null
+++ b/.github/workflows/build-artifact.yml
@@ -0,0 +1,87 @@
+name: Build artifact
+
+on:
+  push:
+    branches:
+      - master
+  workflow_dispatch:
+
+jobs:
+  detect-file-change:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: 'true'
+      - name: Test file change
+        id: test-file-change
+        uses: tj-actions/changed-files@v45
+        with:
+          fetch_additional_submodule_history: 'true'
+          files: |
+            tests/ansibench/*
+            tests/rv8-bench/*
+            tests/*.c
+      - name: Set alias
+        id: has_changed_files
+        run: |
+          if [[ ${{ steps.test-file-change.outputs.any_modified }} == true ]]; then
+            echo "has_changed_files=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changed_files=false" >> $GITHUB_OUTPUT
+          fi
+    outputs:
+      has_changed_files: ${{ steps.has_changed_files.outputs.has_changed_files }}
+
+  build-artifact:
+    needs: [detect-file-change]
+    if: ${{ needs.detect-file-change.outputs.has_changed_files == 'true' || github.event_name == 'workflow_dispatch' }}
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: 'true'
+      - name: Install dependencies
+        run: |
+          sudo apt-get update -q -y
+          sudo apt-get upgrade -q -y
+          sudo apt-get install -q -y gcc-multilib g++-multilib
+          sudo apt-get install -q -y opam build-essential libgmp-dev z3 pkg-config zlib1g-dev
+          .ci/riscv-toolchain-install.sh
+          echo "$PWD/toolchain/bin" >> $GITHUB_PATH
+      - name: Build binaries
+        run: |
+          make artifact ENABLE_PREBUILT=0
+          mkdir -p /tmp/rv32emu-prebuilt
+          mv build/linux-x86-softfp build/riscv32 /tmp/rv32emu-prebuilt
+      - name: Build Sail model
+        run: |
+          cd /tmp
+          opam init -y --disable-sandboxing
+          opam switch create ocaml-base-compiler.4.06.1
+          opam install sail -y
+          eval $(opam config env)
+          git clone https://github.com/riscv/sail-riscv.git
+          cd sail-riscv
+          git checkout 9547a30bf84572c458476591b569a95f5232c1c7
+          ARCH=RV32 make -j
+          mkdir -p /tmp/rv32emu-prebuilt/sail_cSim
+          mv c_emulator/riscv_sim_RV32 /tmp/rv32emu-prebuilt/sail_cSim
+      - name: Create tarball
+        run: |
+          cd /tmp
+          tar -zcvf rv32emu-prebuilt.tar.gz rv32emu-prebuilt
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ secrets.RV32EMU_PREBUILT_TOKEN }}
+        run: |
+          RELEASE_TAG=$(date +'%Y.%m.%d')
+          cd /tmp
+          gh release create $RELEASE_TAG \
+            --repo sysprog21/rv32emu-prebuilt \
+            --title "$RELEASE_TAG""-nightly"
+          gh release upload $RELEASE_TAG \
+            rv32emu-prebuilt.tar.gz \
+            --repo sysprog21/rv32emu-prebuilt
diff --git a/.gitignore b/.gitignore
index 86dd5647..60dad509 100644
--- a/.gitignore
+++ b/.gitignore
@@ -16,9 +16,14 @@ build/softfloat
 build/cache/
 build/map/
 build/path/
+build/linux-x86-softfp/
+build/riscv32/
+build/sail_cSim/
+*.a
 *.o
 *.o.d
 tests/**/*.elf
 tests/arch-test-target/config.ini
+tests/arch-test-target/sail_cSim/riscv_sim_RV32
 __pycache__/
 src/rv32_jit.c
diff --git a/.gitmodules b/.gitmodules
index 8540dbfc..b9b99ffa 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -11,3 +11,15 @@
 	url = https://github.com/sysprog21/berkeley-softfloat-3
 	branch = rv32emu
 	shallow = true
+[submodule "tests/ansibench"]
+	path = tests/ansibench
+	url = https://github.com/sysprog21/ansibench
+	shallow = true
+[submodule "tests/rv8-bench"]
+	path = tests/rv8-bench
+	url = https://github.com/sysprog21/rv8-bench
+	shallow = true
+[submodule "src/ieeelib"]
+	path = src/ieeelib
+	url = https://github.com/sysprog21/ieeelib
+	shallow = true
diff --git a/Makefile b/Makefile
index d8359110..3c21b459 100644
--- a/Makefile
+++ b/Makefile
@@ -182,7 +182,7 @@ $(OUT)/emulate.o: CFLAGS += -foptimize-sibling-calls -fomit-frame-pointer -fno-s
 .DEFAULT_GOAL := all
 
 include mk/external.mk
-
+include mk/artifact.mk
 include mk/wasm.mk
 
 all: config $(BIN)
@@ -229,13 +229,13 @@ tool: $(TOOLS_BIN)
 include mk/riscv-arch-test.mk
 include mk/tests.mk
 
-CHECK_ELF_FILES := \
-	hello \
-	puzzle \
-	fcalc
+# the prebuilt executables are built for "rv32im"
+CHECK_ELF_FILES :=
 
 ifeq ($(call has, EXT_M), 1)
 CHECK_ELF_FILES += \
+	puzzle \
+	fcalc \
 	pi
 endif
 
@@ -244,10 +244,19 @@ EXPECTED_puzzle = success in 2005 trials
 EXPECTED_fcalc = Performed 12 tests, 0 failures, 100% success rate.
 EXPECTED_pi = 3.141592653589793238462643383279502884197169399375105820974944592307816406286208998628034825342117067982148086
 
-check: $(BIN)
+check-hello: $(BIN)
+	$(Q)$(PRINTF) "Running hello.elf ..."; \
+	    if [ "$(shell $(BIN) $(OUT)/hello.elf | uniq)" = "$(strip $(EXPECTED_hello)) inferior exit code 0" ]; then \
+	    $(call notice, [OK]); \
+	    else \
+	    $(PRINTF) "Failed.\n"; \
+	    exit 1; \
+	    fi;
+
+check: $(BIN) check-hello artifact
 	$(Q)$(foreach e,$(CHECK_ELF_FILES),\
-	    $(PRINTF) "Running $(e).elf ... "; \
-	    if [ "$(shell $(BIN) $(OUT)/$(e).elf | uniq)" = "$(strip $(EXPECTED_$(e))) inferior exit code 0" ]; then \
+	    $(PRINTF) "Running $(e) ... "; \
+	    if [ "$(shell $(BIN) $(OUT)/riscv32/$(e) | uniq)" = "$(strip $(EXPECTED_$(e))) inferior exit code 0" ]; then \
 	    $(call notice, [OK]); \
 	    else \
 	    $(PRINTF) "Failed.\n"; \
@@ -256,9 +265,9 @@ check: $(BIN)
 	)
 
 EXPECTED_aes_sha1 = 1242a6757c8aef23e50b5264f5941a2f4b4a347e  -
-misalign: $(BIN)
-	$(Q)$(PRINTF) "Running aes.elf ... ";
-	$(Q)if [ "$(shell $(BIN) -m $(OUT)/aes.elf | $(SHA1SUM))" = "$(EXPECTED_aes_sha1)" ]; then \
+misalign: $(BIN) artifact
+	$(Q)$(PRINTF) "Running uaes ... ";
+	$(Q)if [ "$(shell $(BIN) -m $(OUT)/riscv32/uaes | $(SHA1SUM))" = "$(EXPECTED_aes_sha1)" ]; then \
 	    $(call notice, [OK]); \
 	    else \
 	    $(PRINTF) "Failed.\n"; \
diff --git a/README.md b/README.md
index d5a926c2..808483cb 100644
--- a/README.md
+++ b/README.md
@@ -327,46 +327,8 @@ Use of this source code is governed by a MIT license that can be found in the [L
 
 ## External sources
 
-In `rv32emu` repository, there are some prebuilt ELF files for testing purpose.
-* `aes.elf` : See [tests/aes.c](tests/aes.c)
-* `captcha.elf` : See [tests/captcha.c](tests/captcha.c)
-* `cc.elf` : See [tests/cc](tests/cc)
-* `chacha20.elf` : See [tests/chacha20](tests/chacha20)
-* `coremark.elf` : See [eembc/coremark](https://github.com/eembc/coremark) [RV32M]
-* `dhrystone.elf` : See [rv8-bench](https://github.com/michaeljclark/rv8-bench)
-* `donut.elf` : See [donut.c](tests/donut.c)
-* `doom.elf` : See [sysprog21/doom_riscv](https://github.com/sysprog21/doom_riscv) [RV32M]
-* `fcalc.elf` : See [fcalc.c](tests/fcalc.c)
-* `hamilton.elf` : See [hamilton.c](tests/hamilton.c)
-* `ieee754.elf` : See [tests/ieee754.c](tests/ieee754.c) [RV32F]
-* `jit-bf.elf` : See [ezaki-k/xkon_beta](https://github.com/ezaki-k/xkon_beta)
-* `lena.elf`: See [tests/lena.c](tests/lena.c)
-* `line.elf` : See [tests/line.c](tests/line.c) [RV32M]
-* `maj2random.elf` : See [tests/maj2random.c](tests/maj2random.c) [RV32F]
-* `mandelbrot.elf` : See [tests/mandelbrot.c](tests/mandelbrot.c)
-* `nqueens.elf` : See [tests/nqueens.c](tests/nqueens.c)
-* `nyancat.elf` : See [tests/nyancat.c](tests/nyancat.c)
-* `pi.elf` : See [tests/pi.c](tests/pi.c) [RV32M]
-* `qrcode.elf` : See [tests/qrcode.c](tests/qrcode.c)
-* `quake.elf` : See [sysprog21/quake-embedded](https://github.com/sysprog21/quake-embedded) [RV32F]
-* `readelf.elf` : See [tests/readelf](tests/readelf)
-* `richards.elf` : See [tests/richards.c](tests/richards.c)
-* `rvsim.elf` : See [tests/rvsim.c](tests/rvsim.c)
-* `scimark2.elf` : See [tests/scimark2](tests/scimark2) [RV32MF]
-* `smolnes.elf` : See [tests/smolnes](tests/smolnes.c) [RV32M]
-* `spirograph.elf` : See [tests/spirograph.c](tests/spirograph.c)
-* `stream.elf` : See [tests/stream](tests/stream.c) [RV32MF]
-* `qsort.elf` : See [rv8-bench](https://github.com/michaeljclark/rv8-bench)
-* `miniz.elf` : See [rv8-bench](https://github.com/michaeljclark/rv8-bench)
-* `primes.elf` : See [rv8-bench](https://github.com/michaeljclark/rv8-bench)
-* `sha512.elf` : See [rv8-bench](https://github.com/michaeljclark/rv8-bench)
-* `numeric_sort.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench)
-* `FP_emulation.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench)
-* `bitfield.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench)
-* `idea.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench) 
-* `assignment.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench)
-* `string_sort.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench) 
-* `huffman.elf` : See [nbench](https://github.com/nfinit/ansibench/tree/master/nbench)
+See [docs/prebuilt.md](docs/prebuilt.md).
+
 ## Reference
 
 * [Writing a simple RISC-V emulator in plain C](https://fmash16.github.io/content/posts/riscv-emulator-in-c.html)
diff --git a/build/FP_emulation.elf b/build/FP_emulation.elf
deleted file mode 100644
index 8fd5e4aa..00000000
Binary files a/build/FP_emulation.elf and /dev/null differ
diff --git a/build/aes.elf b/build/aes.elf
deleted file mode 100644
index 7cbcd20f..00000000
Binary files a/build/aes.elf and /dev/null differ
diff --git a/build/assignment.elf b/build/assignment.elf
deleted file mode 100644
index a633e73d..00000000
Binary files a/build/assignment.elf and /dev/null differ
diff --git a/build/bitfield.elf b/build/bitfield.elf
deleted file mode 100644
index 456d691e..00000000
Binary files a/build/bitfield.elf and /dev/null differ
diff --git a/build/captcha.elf b/build/captcha.elf
deleted file mode 100644
index cad474b7..00000000
Binary files a/build/captcha.elf and /dev/null differ
diff --git a/build/coremark.elf b/build/coremark.elf
deleted file mode 100644
index 1da8631a..00000000
Binary files a/build/coremark.elf and /dev/null differ
diff --git a/build/dhrystone.elf b/build/dhrystone.elf
deleted file mode 100755
index 356ff0eb..00000000
Binary files a/build/dhrystone.elf and /dev/null differ
diff --git a/build/donut.elf b/build/donut.elf
deleted file mode 100644
index 71c54de7..00000000
Binary files a/build/donut.elf and /dev/null differ
diff --git a/build/fcalc.elf b/build/fcalc.elf
deleted file mode 100644
index a6e57552..00000000
Binary files a/build/fcalc.elf and /dev/null differ
diff --git a/build/hamilton.elf b/build/hamilton.elf
deleted file mode 100644
index 5f67e081..00000000
Binary files a/build/hamilton.elf and /dev/null differ
diff --git a/build/huffman.elf b/build/huffman.elf
deleted file mode 100644
index 483e937c..00000000
Binary files a/build/huffman.elf and /dev/null differ
diff --git a/build/idea.elf b/build/idea.elf
deleted file mode 100644
index 7609a5a5..00000000
Binary files a/build/idea.elf and /dev/null differ
diff --git a/build/lena.elf b/build/lena.elf
deleted file mode 100644
index e41e506e..00000000
Binary files a/build/lena.elf and /dev/null differ
diff --git a/build/line.elf b/build/line.elf
deleted file mode 100644
index 851b1376..00000000
Binary files a/build/line.elf and /dev/null differ
diff --git a/build/maj2random.elf b/build/maj2random.elf
deleted file mode 100644
index fae6c1aa..00000000
Binary files a/build/maj2random.elf and /dev/null differ
diff --git a/build/mandelbrot.elf b/build/mandelbrot.elf
deleted file mode 100644
index 6a847286..00000000
Binary files a/build/mandelbrot.elf and /dev/null differ
diff --git a/build/miniz.elf b/build/miniz.elf
deleted file mode 100644
index 2cc3e8df..00000000
Binary files a/build/miniz.elf and /dev/null differ
diff --git a/build/nqueens.elf b/build/nqueens.elf
deleted file mode 100644
index fdbfc31d..00000000
Binary files a/build/nqueens.elf and /dev/null differ
diff --git a/build/numeric_sort.elf b/build/numeric_sort.elf
deleted file mode 100644
index e6fda6ac..00000000
Binary files a/build/numeric_sort.elf and /dev/null differ
diff --git a/build/nyancat.elf b/build/nyancat.elf
deleted file mode 100644
index 5e4e346d..00000000
Binary files a/build/nyancat.elf and /dev/null differ
diff --git a/build/pi.elf b/build/pi.elf
deleted file mode 100644
index f1f29f7f..00000000
Binary files a/build/pi.elf and /dev/null differ
diff --git a/build/primes.elf b/build/primes.elf
deleted file mode 100644
index e474b49d..00000000
Binary files a/build/primes.elf and /dev/null differ
diff --git a/build/puzzle.elf b/build/puzzle.elf
deleted file mode 100644
index 1111f7a7..00000000
Binary files a/build/puzzle.elf and /dev/null differ
diff --git a/build/qrcode.elf b/build/qrcode.elf
deleted file mode 100644
index 4f80e504..00000000
Binary files a/build/qrcode.elf and /dev/null differ
diff --git a/build/qsort.elf b/build/qsort.elf
deleted file mode 100644
index 9432d445..00000000
Binary files a/build/qsort.elf and /dev/null differ
diff --git a/build/richards.elf b/build/richards.elf
deleted file mode 100644
index 3cdf4594..00000000
Binary files a/build/richards.elf and /dev/null differ
diff --git a/build/rvsim.elf b/build/rvsim.elf
deleted file mode 100644
index d2d0b837..00000000
Binary files a/build/rvsim.elf and /dev/null differ
diff --git a/build/sha512.elf b/build/sha512.elf
deleted file mode 100644
index a999f5ef..00000000
Binary files a/build/sha512.elf and /dev/null differ
diff --git a/build/spirograph.elf b/build/spirograph.elf
deleted file mode 100644
index 8dd7c915..00000000
Binary files a/build/spirograph.elf and /dev/null differ
diff --git a/build/stream.elf b/build/stream.elf
deleted file mode 100644
index a5915854..00000000
Binary files a/build/stream.elf and /dev/null differ
diff --git a/build/string_sort.elf b/build/string_sort.elf
deleted file mode 100644
index 6d551769..00000000
Binary files a/build/string_sort.elf and /dev/null differ
diff --git a/docs/prebuilt.md b/docs/prebuilt.md
new file mode 100644
index 00000000..f06e28ad
--- /dev/null
+++ b/docs/prebuilt.md
@@ -0,0 +1,67 @@
+# Prebuilt Binaries
+
+The prebuilt binaries for [rv32emu](https://github.com/sysprog21/rv32emu) are prepared primarily because the [RISC-V Sail Model](https://github.com/riscv/sail-riscv) executable is required for the [RISC-V Architecture Test](https://github.com/riscv-non-isa/riscv-arch-test), and selected RISC-V ELF files are useful for ISA simulation validation and testing.
+Some of these prebuilt binaries are stored in [rv32emu-prebuilt](https://github.com/sysprog21/rv32emu-prebuilt).
+During testing or benchmarking, these binaries are automatically downloaded into the `build/linux-x86-softfp/` and `build/riscv32/` directories by default.
+The RISC-V binaries are compiled using the [xPack RISC-V GCC toolchain](https://github.com/xpack-dev-tools/riscv-none-elf-gcc-xpack) with the options `-march=rv32im -mabi=ilp32`.
+The x86 binaries are compiled by GCC with `-m32 -mno-sse -mno-sse2 -msoft-float` options and use [ieeelib](https://github.com/sysprog21/ieeelib) as the soft-fp library.
+
+To fetch the prebuilt binaries manually, run:
+
+```shell
+$ make artifact
+```
+
+Or build the binaries from scratch (the RISC-V cross-compiler is required):
+
+```shell
+$ make artifact ENABLE_PREBUILT=0 [CROSS_COMPILE=<COMPILER_PREFIX>]
+```
+
+The compiler prefix varies according to the used toolchain, such as `riscv-none-elf-`, `riscv32-unknown-elf-`, etc.
+
+The prebuilt binaries in `rv32emu-prebuilt` are built from the following repositories and resources:
+
+- [ansibench](https://github.com/sysprog21/ansibench)
+    - coremark
+    - stream
+    - nbench
+- [rv8-bench](https://github.com/sysprog21/rv8-bench)
+    - aes
+    - dhrystone
+    - miniz
+    - norx
+    - primes
+    - qsort
+    - sha512
+- `captcha` : See [tests/captcha.c](/tests/captcha.c)
+- `donut` : See [tests/donut.c](/tests/donut.c)
+- `fcalc` : See [tests/fcalc.c](/tests/fcalc.c)
+- `hamilton` : See [tests/hamilton.c](/tests/hamilton.c)
+- `jit` : See [tests/jit.c](/tests/jit.c)
+- `lena`: See [tests/lena.c](/tests/lena.c)
+- `line` : See [tests/line.c](/tests/line.c)
+- `maj2random` : See [tests/maj2random.c](/tests/maj2random.c)
+- `mandelbrot` : See [tests/mandelbrot.c](/tests/mandelbrot.c)
+- `nqueens` : See [tests/nqueens.c](/tests/nqueens.c)
+- `nyancat` : See [tests/nyancat.c](/tests/nyancat.c)
+- `pi` : See [tests/pi.c](/tests/pi.c)
+- `puzzle` : See [tests/puzzle.c](/tests/puzzle.c)
+- `qrcode` : See [tests/qrcode.c](/tests/qrcode.c)
+- `richards` : See [tests/richards.c](/tests/richards.c)
+- `rvsim` : See [tests/rvsim.c](/tests/rvsim.c)
+- `spirograph` : See [tests/spirograph.c](/tests/spirograph.c)
+- `uaes` : See [tests/uaes.c](/tests/uaes.c)
+
+There are still some prebuilt standalone RISC-V binaries under `build/` directory only for testing purpose:
+
+- `hello.elf` : See [tests/asm-hello](/tests/asm-hello)
+- `cc.elf` : See [tests/cc](/tests/cc)
+- `chacha20.elf` : See [tests/chacha20](/tests/chacha20)
+- `doom.elf` : See [sysprog21/doom_riscv](https://github.com/sysprog21/doom_riscv) [RV32M]
+- `ieee754.elf` : See [tests/ieee754.c](/tests/ieee754.c) [RV32F]
+- `jit-bf.elf` : See [ezaki-k/xkon_beta](https://github.com/ezaki-k/xkon_beta)
+- `quake.elf` : See [sysprog21/quake-embedded](https://github.com/sysprog21/quake-embedded) [RV32F]
+- `readelf.elf` : See [tests/readelf](/tests/readelf)
+- `scimark2.elf` : See [tests/scimark2](/tests/scimark2) [RV32MF]
+- `smolnes.elf` : See [tests/smolnes](/tests/smolnes.c) [RV32M]
diff --git a/mk/artifact.mk b/mk/artifact.mk
new file mode 100644
index 00000000..543955af
--- /dev/null
+++ b/mk/artifact.mk
@@ -0,0 +1,70 @@
+ENABLE_PREBUILT ?= 1
+
+CC ?= gcc
+CROSS_COMPILE ?= riscv-none-elf-
+
+BIN_DIR := $(abspath $(OUT))
+
+TEST_SUITES += \
+	ansibench \
+	rv8-bench
+
+# "ieee754" needs F extension
+# "smolnes", "ticks" have inline assembly and only work in riscv
+TEST_BENCHES += \
+	captcha \
+	donut \
+	fcalc \
+	hamilton \
+	jit \
+	lena \
+	line \
+	maj2random \
+	mandelbrot \
+	nqueens \
+	nyancat \
+	pi \
+	puzzle \
+	qrcode \
+	richards \
+	rvsim \
+	spirograph \
+	uaes
+
+SHELL_HACK := $(shell mkdir -p $(BIN_DIR)/linux-x86-softfp $(BIN_DIR)/riscv32)
+
+ifeq ($(call has, PREBUILT), 1)
+  LATEST_RELEASE := $(shell wget -q https://api.github.com/repos/sysprog21/rv32emu-prebuilt/releases/latest -O- | grep '"tag_name"' | sed -E 's/.*"tag_name": "([^"]+)".*/\1/')
+else
+  # Since rv32emu only supports the dynamic binary translation of integer instruction in tiered compilation currently,
+  # we disable the hardware floating-point and the related SIMD operation of x86.
+  CFLAGS := -m32 -mno-sse -mno-sse2 -msoft-float -O2 -L$(BIN_DIR)
+  LDFLAGS := -lsoft-fp -lm
+
+  CFLAGS_CROSS := -march=rv32im -mabi=ilp32 -O2
+  LDFLAGS_CROSS := -lm -lsemihost
+endif
+
+.PHONY: artifact
+
+artifact:
+ifeq ($(call has, PREBUILT), 1)
+	$(Q)$(PRINTF) "Fetching prebuilt executables from \"rv32emu-prebuilt\" ...\n"
+	$(Q)wget -q --show-progress https://github.com/sysprog21/rv32emu-prebuilt/releases/download/$(LATEST_RELEASE)/rv32emu-prebuilt.tar.gz -O- | tar -C build --strip-components=1 -xz
+else
+	git submodule update --init ./src/ieeelib $(addprefix ./tests/,$(foreach tb,$(TEST_SUITES),$(tb)))
+	$(Q)$(MAKE) -C ./src/ieeelib CC=$(CC) CFLAGS="$(CFLAGS)" BINDIR=$(BIN_DIR)
+	$(Q)for tb in $(TEST_SUITES); do \
+	    CC=$(CC) CFLAGS="$(CFLAGS)" LDFLAGS="$(LDFLAGS)" BINDIR=$(BIN_DIR)/linux-x86-softfp $(MAKE) -C ./tests/$$tb; \
+	done
+	$(Q)for tb in $(TEST_SUITES); do \
+	    CC=$(CROSS_COMPILE)gcc CFLAGS="$(CFLAGS_CROSS)" LDFLAGS="$(LDFLAGS_CROSS)" BINDIR=$(BIN_DIR)/riscv32 $(MAKE) -C ./tests/$$tb; \
+	done
+	$(Q)$(PRINTF) "Building standalone testbenches ...\n"
+	$(Q)for tb in $(TEST_BENCHES); do \
+	    $(CC) $(CFLAGS) -Wno-unused-result -o $(BIN_DIR)/linux-x86-softfp/$$tb ./tests/$$tb.c $(LDFLAGS); \
+	done
+	$(Q)for tb in $(TEST_BENCHES); do \
+	    $(CROSS_COMPILE)gcc $(CFLAGS_CROSS) -o $(BIN_DIR)/riscv32/$$tb ./tests/$$tb.c $(LDFLAGS_CROSS); \
+	done
+endif
diff --git a/mk/external.mk b/mk/external.mk
index 704bbfda..202c2589 100644
--- a/mk/external.mk
+++ b/mk/external.mk
@@ -22,7 +22,7 @@ endef
 
 # $(1): compressed source URL
 define download
-    $(eval _ := $(shell curl --progress-bar -O -L -C - "$(strip $(1))"))
+    $(eval _ := $(shell wget -q --show-progress --continue "$(strip $(1))"))
 endef
 
 # $(1): compressed source(.zip or.gz)
diff --git a/mk/riscv-arch-test.mk b/mk/riscv-arch-test.mk
index ae00765e..bd117c2f 100644
--- a/mk/riscv-arch-test.mk
+++ b/mk/riscv-arch-test.mk
@@ -9,11 +9,12 @@ ifeq ($(RISCV_DEVICE),FCZicsr)
 ARCH_TEST_SUITE := tests/rv32fc-test-suite
 endif
 
-arch-test: $(BIN)
+arch-test: $(BIN) artifact
 ifeq ($(CROSS_COMPILE),)
 	$(error GNU Toolchain for RISC-V is required to build architecture tests. Please check package installation)
 endif
 	git submodule update --init $(dir $(ARCH_TEST_DIR))
+	$(Q)cp $(OUT)/sail_cSim/riscv_sim_RV32 tests/arch-test-target/sail_cSim/riscv_sim_RV32
 	$(Q)python3 -B $(RISCV_TARGET)/setup.py --riscv_device=$(RISCV_DEVICE)
 	$(Q)riscof run --work-dir=$(WORK) \
 			--config=$(RISCV_TARGET)/config.ini \
diff --git a/src/ieeelib b/src/ieeelib
new file mode 160000
index 00000000..8bd30447
--- /dev/null
+++ b/src/ieeelib
@@ -0,0 +1 @@
+Subproject commit 8bd3044791e12d196c2af6639312cfbf8b49677c
diff --git a/tests/ansibench b/tests/ansibench
new file mode 160000
index 00000000..676e97d4
--- /dev/null
+++ b/tests/ansibench
@@ -0,0 +1 @@
+Subproject commit 676e97d4e14ab1a390f32443691d789a80e48b79
diff --git a/tests/arch-test-target/sail_cSim/riscv_sim_RV32 b/tests/arch-test-target/sail_cSim/riscv_sim_RV32
deleted file mode 100755
index 0b9241ab..00000000
Binary files a/tests/arch-test-target/sail_cSim/riscv_sim_RV32 and /dev/null differ
diff --git a/tests/rv8-bench b/tests/rv8-bench
new file mode 160000
index 00000000..5bf50214
--- /dev/null
+++ b/tests/rv8-bench
@@ -0,0 +1 @@
+Subproject commit 5bf5021431f3946b3f8da89aad9635490c3078a0
diff --git a/tests/spirograph.c b/tests/spirograph.c
index e11d9cdd..2e409020 100644
--- a/tests/spirograph.c
+++ b/tests/spirograph.c
@@ -9,6 +9,7 @@
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <unistd.h>
 
 #ifndef GL_FPS
 #define GL_FPS 30
diff --git a/tests/stream.c b/tests/stream.c
deleted file mode 100644
index 54a28990..00000000
--- a/tests/stream.c
+++ /dev/null
@@ -1,488 +0,0 @@
-/* Program: STREAM                                                       */
-/*                                                                       */
-/* This program measures memory transfer rates in MB/s for simple        */
-/* computational kernels coded in C.                                     */
-/*-----------------------------------------------------------------------*/
-/* Copyright 1991-2013: John D. McCalpin                                 */
-/*-----------------------------------------------------------------------*/
-/* License:                                                              */
-/*  1. You are free to use this program and/or to redistribute           */
-/*     this program.                                                     */
-/*  2. You are free to modify this program for your own use,             */
-/*     including commercial use, subject to the publication              */
-/*     restrictions in item 3.                                           */
-/*  3. You are free to publish results obtained from running this        */
-/*     program, or from works that you derive from this program,         */
-/*     with the following limitations:                                   */
-/*     3a. In order to be referred to as "STREAM benchmark results",     */
-/*         published results must be in conformance to the STREAM        */
-/*         Run Rules, (briefly reviewed below) published at              */
-/*         https://www.cs.virginia.edu/stream/ref.html                   */
-/*         and incorporated herein by reference.                         */
-/*         As the copyright holder, John McCalpin retains the            */
-/*         right to determine conformity with the Run Rules.             */
-/*     3b. Results based on modified source code or on runs not in       */
-/*         accordance with the STREAM Run Rules must be clearly          */
-/*         labelled whenever they are published.  Examples of            */
-/*         proper labelling include:                                     */
-/*           "tuned STREAM benchmark results"                            */
-/*           "based on a variant of the STREAM benchmark code"           */
-/*         Other comparable, clear, and reasonable labelling is          */
-/*         acceptable.                                                   */
-/*     3c. Submission of results to the STREAM benchmark web site        */
-/*         is encouraged, but not required.                              */
-/*  4. Use of this program or creation of derived works based on this    */
-/*     program constitutes acceptance of these licensing restrictions.   */
-/*  5. Absolutely no warranty is expressed or implied.                   */
-/*-----------------------------------------------------------------------*/
-
-#include <float.h>
-#include <limits.h>
-#include <math.h>
-#include <stdio.h>
-#include <sys/time.h>
-#include <unistd.h>
-
-/*-----------------------------------------------------------------------
- * INSTRUCTIONS:
- *
- *	1) STREAM requires different amounts of memory to run on different
- *           systems, depending on both the system cache size(s) and the
- *           granularity of the system timer.
- *     You should adjust the value of 'STREAM_ARRAY_SIZE' (below)
- *           to meet *both* of the following criteria:
- *       (a) Each array must be at least 4 times the size of the
- *           available cache memory. I don't worry about the difference
- *           between 10^6 and 2^20, so in practice the minimum array size
- *           is about 3.8 times the cache size.
- *           Example: One Xeon E3 with 8 MB L3 cache
- *               STREAM_ARRAY_SIZE should be >= 4 million, giving
- *               an array size of 30.5 MB and a total memory requirement
- *               of 91.5 MB.
- *       (b) The size should be large enough so that the 'timing calibration'
- *           output by the program is at least 20 clock-ticks.
- *           Example: most versions of Windows have a 10 millisecond timer
- *               granularity.  20 "ticks" at 10 ms/tic is 200 milliseconds.
- *               If the chip is capable of 10 GB/s, it moves 2 GB in 200 msec.
- *               This means the each array must be at least 1 GB, or 128M
- *elements.
- *
- *      Version 5.10 increases the default array size from 2 million
- *          elements to 10 million elements in response to the increasing
- *          size of L3 caches.  The new default size is large enough for caches
- *          up to 20 MB.
- *      Version 5.10 changes the loop index variables from "register int"
- *          to "ssize_t", which allows array indices >2^32 (4 billion)
- *          on properly configured 64-bit systems.  Additional compiler options
- *          (such as "-mcmodel=medium") may be required for large memory runs.
- *
- *      Array size can be set at compile time without modifying the source
- *          code for the (many) compilers that support preprocessor definitions
- *          on the compile line.  E.g.,
- *                gcc -O -DSTREAM_ARRAY_SIZE=100000000 stream.c -o stream.100M
- *          will override the default size of 10M with a new size of 100M
- *elements per array.
- */
-#define STREAM_ARRAY_SIZE 10000000
-
-/*  2) STREAM runs each kernel "NTIMES" times and reports the *best* result
- *         for any iteration after the first, therefore the minimum value
- *         for NTIMES is 2.
- *      There are no rules on maximum allowable values for NTIMES, but
- *         values larger than the default are unlikely to noticeably
- *         increase the reported performance.
- *      NTIMES can also be set on the compile line without changing the source
- *         code using, for example, "-DNTIMES=7".
- */
-#if defined(NTIMES) && NTIMES <= 1
-#undef NTIMES
-#endif
-#ifndef NTIMES
-#define NTIMES 7
-#endif
-
-/*  Users are allowed to modify the "OFFSET" variable, which *may* change the
- *         relative alignment of the arrays (though compilers may change the
- *         effective offset by making the arrays non-contiguous on some
- * systems). Use of non-zero values for OFFSET can be especially helpful if the
- *         STREAM_ARRAY_SIZE is set to a value close to a large power of 2.
- *      OFFSET can also be set on the compile line without changing the source
- *         code using, for example, "-DOFFSET=56".
- */
-#ifndef OFFSET
-#define OFFSET 0
-#endif
-
-/*
- *	3) Compile the code with optimization.  Many compilers generate
- *       unreasonably bad code before the optimizer tightens things up.
- *     If the results are unreasonably good, on the other hand, the
- *       optimizer might be too smart for me!
- *
- *     For a simple single-core version, try compiling with:
- *            cc -O stream.c -o stream
- *     This is known to work on many, many systems....
- *
- *     To run with single-precision variables and arithmetic, simply add
- *         -DSTREAM_TYPE=float
- *     to the compile line.
- *     Note that this changes the minimum array sizes required --- see (1)
- *above.
- *
- *	4) Optional: Mail the results to mccalpin@cs.virginia.edu
- *	   Be sure to include info that will help me understand:
- *		a) the computer hardware configuration (e.g., processor model, memory
- *type) b) the compiler name/version and compilation flags c) any run-time
- *information (such as OMP_NUM_THREADS) d) all of the output from the test case.
- */
-
-#define HLINE "-------------------------------------------------------------\n"
-
-#ifndef MIN
-#define MIN(x, y) ((x) < (y) ? (x) : (y))
-#endif
-#ifndef MAX
-#define MAX(x, y) ((x) > (y) ? (x) : (y))
-#endif
-
-#ifndef STREAM_TYPE
-#define STREAM_TYPE double
-#endif
-#define ALIGNED_STREAM __attribute__((aligned(32)))
-
-static STREAM_TYPE a[STREAM_ARRAY_SIZE + OFFSET] ALIGNED_STREAM,
-    b[STREAM_ARRAY_SIZE + OFFSET] ALIGNED_STREAM,
-    c[STREAM_ARRAY_SIZE + OFFSET] ALIGNED_STREAM;
-
-static double avgtime[4] = {0}, maxtime[4] = {0},
-              mintime[4] = {FLT_MAX, FLT_MAX, FLT_MAX, FLT_MAX};
-
-static char *label[4] = {
-    "Copy:      ", "Scale:     ", "Add:       ", "Triad:     "};
-
-static double bytes[4] = {2 * sizeof(STREAM_TYPE) * STREAM_ARRAY_SIZE,
-                          2 * sizeof(STREAM_TYPE) * STREAM_ARRAY_SIZE,
-                          3 * sizeof(STREAM_TYPE) * STREAM_ARRAY_SIZE,
-                          3 * sizeof(STREAM_TYPE) * STREAM_ARRAY_SIZE};
-
-static double mysecond();
-static void checkSTREAMresults();
-
-int main()
-{
-    int quantum, checktick();
-    int BytesPerWord;
-    int k;
-    ssize_t j;
-    STREAM_TYPE scalar;
-    double t, times[4][NTIMES];
-
-    /* --- SETUP --- determine precision and check timing --- */
-
-    printf(HLINE);
-    printf("STREAM version $Revision: 5.10 $\n");
-    printf(HLINE);
-    BytesPerWord = sizeof(STREAM_TYPE);
-    printf("This system uses %d bytes per array element.\n", BytesPerWord);
-
-    printf(HLINE);
-#ifdef N
-    printf("*****  WARNING: ******\n");
-    printf(
-        "      It appears that you set the preprocessor variable N when "
-        "compiling this code.\n");
-    printf(
-        "      This version of the code uses the preprocesor variable "
-        "STREAM_ARRAY_SIZE to control the array size\n");
-    printf("      Reverting to default value of STREAM_ARRAY_SIZE=%llu\n",
-           (unsigned long long) STREAM_ARRAY_SIZE);
-    printf("*****  WARNING: ******\n");
-#endif
-
-    printf("Array size = %llu (elements), Offset = %d (elements)\n",
-           (unsigned long long) STREAM_ARRAY_SIZE, OFFSET);
-    printf(
-        "Memory per array = %.1f MiB (= %.1f GiB).\n",
-        BytesPerWord * ((double) STREAM_ARRAY_SIZE / 1024.0 / 1024.0),
-        BytesPerWord * ((double) STREAM_ARRAY_SIZE / 1024.0 / 1024.0 / 1024.0));
-    printf("Total memory required = %.1f MiB (= %.1f GiB).\n",
-           (3.0 * BytesPerWord) * ((double) STREAM_ARRAY_SIZE / 1024.0 / 1024.),
-           (3.0 * BytesPerWord) *
-               ((double) STREAM_ARRAY_SIZE / 1024.0 / 1024. / 1024.));
-    printf("Each kernel will be executed %d times.\n", NTIMES);
-    printf(
-        " The *best* time for each kernel (excluding the first iteration)\n");
-    printf(" will be used to compute the reported bandwidth.\n");
-
-    /* Get initial value for system clock. */
-    for (j = 0; j < STREAM_ARRAY_SIZE; j++) {
-        a[j] = 1.0;
-        b[j] = 2.0;
-        c[j] = 0.0;
-    }
-
-    printf(HLINE);
-
-    if ((quantum = checktick()) >= 1)
-        printf(
-            "Your clock granularity/precision appears to be "
-            "%d microseconds.\n",
-            quantum);
-    else {
-        printf(
-            "Your clock granularity appears to be "
-            "less than one microsecond.\n");
-        quantum = 1;
-    }
-
-    t = mysecond();
-    for (j = 0; j < STREAM_ARRAY_SIZE; j++)
-        a[j] = 2.0E0 * a[j];
-    t = 1.0E6 * (mysecond() - t);
-
-    printf(
-        "Each test below will take on the order"
-        " of %d microseconds.\n",
-        (int) t);
-    printf("   (= %d clock ticks)\n", (int) (t / quantum));
-    printf("Increase the size of the arrays if this shows that\n");
-    printf("you are not getting at least 20 clock ticks per test.\n");
-
-    printf(HLINE);
-
-    printf("WARNING -- The above is only a rough guideline.\n");
-    printf("For best results, please be sure you know the\n");
-    printf("precision of your system timer.\n");
-    printf(HLINE);
-
-    /*	--- MAIN LOOP --- repeat test cases NTIMES times --- */
-
-    scalar = 3.0;
-    for (k = 0; k < NTIMES; k++) {
-        times[0][k] = mysecond();
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++)
-            c[j] = a[j];
-        times[0][k] = mysecond() - times[0][k];
-
-        times[1][k] = mysecond();
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++)
-            b[j] = scalar * c[j];
-        times[1][k] = mysecond() - times[1][k];
-
-        times[2][k] = mysecond();
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++)
-            c[j] = a[j] + b[j];
-        times[2][k] = mysecond() - times[2][k];
-
-        times[3][k] = mysecond();
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++)
-            a[j] = b[j] + scalar * c[j];
-        times[3][k] = mysecond() - times[3][k];
-    }
-
-    /*	--- SUMMARY --- */
-
-    for (k = 1; k < NTIMES; k++) /* note -- skip first iteration */
-    {
-        for (j = 0; j < 4; j++) {
-            avgtime[j] = avgtime[j] + times[j][k];
-            mintime[j] = MIN(mintime[j], times[j][k]);
-            maxtime[j] = MAX(maxtime[j], times[j][k]);
-        }
-    }
-
-    printf("Function    Best Rate MB/s  Avg time     Min time     Max time\n");
-    for (j = 0; j < 4; j++) {
-        avgtime[j] = avgtime[j] / (double) (NTIMES - 1);
-
-        printf("%s%12.1f  %11.6f  %11.6f  %11.6f\n", label[j],
-               1.0E-06 * bytes[j] / mintime[j], avgtime[j], mintime[j],
-               maxtime[j]);
-    }
-    printf(HLINE);
-
-    /* --- Check Results --- */
-    checkSTREAMresults();
-    printf(HLINE);
-
-    return 0;
-}
-
-#define M 20
-
-int checktick()
-{
-    int i, minDelta, Delta;
-    double t1, t2, timesfound[M];
-
-    /*  Collect a sequence of M unique time values from the system. */
-
-    for (i = 0; i < M; i++) {
-        t1 = mysecond();
-        while (((t2 = mysecond()) - t1) < 1.0E-6)
-            ;
-        timesfound[i] = t1 = t2;
-    }
-
-    /*
-     * Determine the minimum difference between these M values.
-     * This result will be our estimate (in microseconds) for the
-     * clock granularity.
-     */
-
-    minDelta = 1000000;
-    for (i = 1; i < M; i++) {
-        Delta = (int) (1.0E6 * (timesfound[i] - timesfound[i - 1]));
-        minDelta = MIN(minDelta, MAX(Delta, 0));
-    }
-
-    return (minDelta);
-}
-
-/* A gettimeofday routine to give access to the wall clock timer on most
- * UNIX-like systems.
- */
-#include <sys/time.h>
-
-static double mysecond()
-{
-    struct timeval tp;
-    struct timezone tzp;
-
-    (void) gettimeofday(&tp, &tzp);
-    return ((double) tp.tv_sec + (double) tp.tv_usec * 1.e-6);
-}
-
-#ifndef abs
-#define abs(a) ((a) >= 0 ? (a) : -(a))
-#endif
-static void checkSTREAMresults()
-{
-    STREAM_TYPE aj, bj, cj, scalar;
-    STREAM_TYPE aSumErr, bSumErr, cSumErr;
-    STREAM_TYPE aAvgErr, bAvgErr, cAvgErr;
-    double epsilon;
-    ssize_t j;
-    int k, ierr, err;
-
-    /* reproduce initialization */
-    aj = 1.0;
-    bj = 2.0;
-    cj = 0.0;
-    /* a[] is modified during timing check */
-    aj = 2.0E0 * aj;
-    /* now execute timing loop */
-    scalar = 3.0;
-    for (k = 0; k < NTIMES; k++) {
-        cj = aj;
-        bj = scalar * cj;
-        cj = aj + bj;
-        aj = bj + scalar * cj;
-    }
-
-    /* accumulate deltas between observed and expected results */
-    aSumErr = 0.0;
-    bSumErr = 0.0;
-    cSumErr = 0.0;
-    for (j = 0; j < STREAM_ARRAY_SIZE; j++) {
-        aSumErr += abs(a[j] - aj);
-        bSumErr += abs(b[j] - bj);
-        cSumErr += abs(c[j] - cj);
-        // if (j == 417) printf("Index 417: c[j]: %f, cj: %f\n",c[j],cj);	//
-        // MCCALPIN
-    }
-    aAvgErr = aSumErr / (STREAM_TYPE) STREAM_ARRAY_SIZE;
-    bAvgErr = bSumErr / (STREAM_TYPE) STREAM_ARRAY_SIZE;
-    cAvgErr = cSumErr / (STREAM_TYPE) STREAM_ARRAY_SIZE;
-
-    if (sizeof(STREAM_TYPE) == 4) {
-        epsilon = 1.e-6;
-    } else if (sizeof(STREAM_TYPE) == 8) {
-        epsilon = 1.e-13;
-    } else {
-        printf("WEIRD: sizeof(STREAM_TYPE) = %u\n", sizeof(STREAM_TYPE));
-        epsilon = 1.e-6;
-    }
-
-    err = 0;
-    if (abs(aAvgErr / aj) > epsilon) {
-        err++;
-        printf("Failed Validation on array a[], AvgRelAbsErr > epsilon (%e)\n",
-               epsilon);
-        printf("     Expected Value: %e, AvgAbsErr: %e, AvgRelAbsErr: %e\n", aj,
-               aAvgErr, abs(aAvgErr) / aj);
-        ierr = 0;
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++) {
-            if (abs(a[j] / aj - 1.0) > epsilon) {
-                ierr++;
-#ifdef VERBOSE
-                if (ierr < 10) {
-                    printf(
-                        "         array a: index: %ld, expected: %e, observed: "
-                        "%e, relative error: %e\n",
-                        j, aj, a[j], abs((aj - a[j]) / aAvgErr));
-                }
-#endif
-            }
-        }
-        printf("     For array a[], %d errors were found.\n", ierr);
-    }
-    if (abs(bAvgErr / bj) > epsilon) {
-        err++;
-        printf("Failed Validation on array b[], AvgRelAbsErr > epsilon (%e)\n",
-               epsilon);
-        printf("     Expected Value: %e, AvgAbsErr: %e, AvgRelAbsErr: %e\n", bj,
-               bAvgErr, abs(bAvgErr) / bj);
-        printf("     AvgRelAbsErr > Epsilon (%e)\n", epsilon);
-        ierr = 0;
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++) {
-            if (abs(b[j] / bj - 1.0) > epsilon) {
-                ierr++;
-#ifdef VERBOSE
-                if (ierr < 10) {
-                    printf(
-                        "         array b: index: %ld, expected: %e, observed: "
-                        "%e, relative error: %e\n",
-                        j, bj, b[j], abs((bj - b[j]) / bAvgErr));
-                }
-#endif
-            }
-        }
-        printf("     For array b[], %d errors were found.\n", ierr);
-    }
-    if (abs(cAvgErr / cj) > epsilon) {
-        err++;
-        printf("Failed Validation on array c[], AvgRelAbsErr > epsilon (%e)\n",
-               epsilon);
-        printf("     Expected Value: %e, AvgAbsErr: %e, AvgRelAbsErr: %e\n", cj,
-               cAvgErr, abs(cAvgErr) / cj);
-        printf("     AvgRelAbsErr > Epsilon (%e)\n", epsilon);
-        ierr = 0;
-        for (j = 0; j < STREAM_ARRAY_SIZE; j++) {
-            if (abs(c[j] / cj - 1.0) > epsilon) {
-                ierr++;
-#ifdef VERBOSE
-                if (ierr < 10) {
-                    printf(
-                        "         array c: index: %ld, expected: %e, observed: "
-                        "%e, relative error: %e\n",
-                        j, cj, c[j], abs((cj - c[j]) / cAvgErr));
-                }
-#endif
-            }
-        }
-        printf("     For array c[], %d errors were found.\n", ierr);
-    }
-    if (err == 0) {
-        printf(
-            "Solution Validates: avg error less than %e on all three arrays\n",
-            epsilon);
-    }
-#ifdef VERBOSE
-    printf("Results Validation Verbose Results: \n");
-    printf("    Expected a(1), b(1), c(1): %f %f %f \n", aj, bj, cj);
-    printf("    Observed a(1), b(1), c(1): %f %f %f \n", a[1], b[1], c[1]);
-    printf("    Rel Errors on a, b, c:     %e %e %e \n", abs(aAvgErr / aj),
-           abs(bAvgErr / bj), abs(cAvgErr / cj));
-#endif
-}
diff --git a/tests/aes.c b/tests/uaes.c
similarity index 100%
rename from tests/aes.c
rename to tests/uaes.c