Implement the segue optimization for LLVM AOT/JIT (#2230)

Segue is an optimization technology which uses x86 segment register to store
the WebAssembly linear memory base address, so as to remove most of the cost
of SFI (Software-based Fault Isolation) base addition and free up a general
purpose register, by this way it may:
- Improve the performance of JIT/AOT
- Reduce the footprint of JIT/AOT, the JIT/AOT code generated is smaller
- Reduce the compilation time of JIT/AOT

This PR uses the x86-64 GS segment register to apply the optimization, currently
it supports linux and linux-sgx platforms on x86-64 target. By default it is disabled,
developer can use the option below to enable it for wamrc and iwasm(with LLVM
JIT enabled):
```bash
wamrc --enable-segue=[<flags>] -o output_file wasm_file
iwasm --enable-segue=[<flags>] wasm_file [args...]
```
`flags` can be:
    i32.load, i64.load, f32.load, f64.load, v128.load,
    i32.store, i64.store, f32.store, f64.store, v128.store
Use comma to separate them, e.g. `--enable-segue=i32.load,i64.store`,
and `--enable-segue` means all flags are added.

Acknowledgement:
Many thanks to Intel Labs, UC San Diego and UT Austin teams for introducing this
technology and the great support and guidance!

Signed-off-by: Wenyong Huang <wenyong.huang@intel.com>
Co-authored-by: Vahldiek-oberwagner, Anjo Lucas <anjo.lucas.vahldiek-oberwagner@intel.com>

tests/benchmarks/polybench/build.sh

@@ -3,6 +3,8 @@
 # Copyright (C) 2019 Intel Corporation.  All rights reserved.
 # SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
+PLATFORM=$(uname -s | tr A-Z a-z)
+
 OUT_DIR=$PWD/out
 WAMRC_CMD=$PWD/../../../wamr-compiler/build/wamrc
 POLYBENCH_CASES="datamining linear-algebra medley stencils"
@@ -40,6 +42,12 @@ do
         echo "Compile ${file_name%.*}.wasm into ${file_name%.*}.aot"
         ${WAMRC_CMD} -o ${OUT_DIR}/${file_name%.*}.aot \
                 ${OUT_DIR}/${file_name%.*}.wasm
+
+        if [[ ${PLATFORM} == "linux" ]]; then
+            echo "Compile ${file_name%.*}.wasm into ${file_name%.*}_segue.aot"
+            ${WAMRC_CMD} --enable-segue -o ${OUT_DIR}/${file_name%.*}_segue.aot \
+                    ${OUT_DIR}/${file_name%.*}.wasm
+        fi
     done
 done
 

tests/benchmarks/polybench/run_aot.sh

@@ -37,7 +37,11 @@ echo "Start to run cases, the result is written to report.txt"
 
 #run benchmarks
 cd $OUT_DIR
-echo -en "\t\t\t\t\t  native\tiwasm-aot\n" >> $REPORT
+if [[ ${PLATFORM} == "linux" ]]; then
+    echo -en "\t\t\t\t\t  native\tiwasm-aot\tiwasm-aot-segue\n" >> $REPORT
+else
+    echo -en "\t\t\t\t\t  native\tiwasm-aot\n" >> $REPORT
+fi
 
 for t in $POLYBENCH_CASES
 do
@@ -51,5 +55,11 @@ do
     echo -en "\t" >> $REPORT
     $TIME -f "real-%e-time" $IWASM_CMD ${t}.aot 2>&1 | grep "real-.*-time" | awk -F '-' '{ORS=""; print $2}' >> $REPORT
 
+    if [[ ${PLATFORM} == "linux" ]]; then
+        echo "run $t with iwasm aot segue .."
+        echo -en "\t" >> $REPORT
+        $TIME -f "real-%e-time" $IWASM_CMD ${t}_segue.aot 2>&1 | grep "real-.*-time" | awk -F '-' '{ORS=""; print $2}' >> $REPORT
+    fi
+
     echo -en "\n" >> $REPORT
 done

tests/benchmarks/polybench/run_interp.sh

@@ -37,7 +37,7 @@ echo "Start to run cases, the result is written to report.txt"
 
 #run benchmarks
 cd $OUT_DIR
-echo -en "\t\t\t\t\t  native\tiwasm-aot\n" >> $REPORT
+echo -en "\t\t\t\t\t  native\tiwasm-interp\n" >> $REPORT
 
 for t in $POLYBENCH_CASES
 do