solving conflicts

.vscode/launch.json

@@ -165,9 +165,7 @@
             "mode": "debug",
             "program": "${workspaceFolder}/samples/fir",
             "args": [
-                "-timing",
-                "-length=8192",
-                "-report-all",
+                "-parallel",
             ],
         },
         {

README.md

@@ -6,7 +6,7 @@
 [![MGPUSim Test](https://github.com/sarchlab/mgpusim/actions/workflows/mgpusim_test.yml/badge.svg)](https://github.com/sarchlab/mgpusim/actions/workflows/mgpusim_test.yml)
 
 [![Go Reference](https://pkg.go.dev/badge/github.com/sarchlab/mgpusim.svg)](https://pkg.go.dev/github.com/sarchlab/mgpusim)
-[![Go Report Card](https://goreportcard.com/badge/github.com/sarchlab/mgpusim/v3)](https://goreportcard.com/report/github.com/sarchlab/mgpusim/v3)
+[![Go Report Card](https://goreportcard.com/badge/github.com/sarchlab/mgpusim/v4)](https://goreportcard.com/report/github.com/sarchlab/mgpusim/v4)
 
 
 MGPUSim is a high-flexibility, high-performance, high-accuracy GPU simulator. It models GPUs that run the AMD GCN3 instruction sets. One main feature of MGPUSim is the support for multi-GPU simulation (you can still use it for single-GPU architecture research).
@@ -16,10 +16,20 @@ MGPUSim is a high-flexibility, high-performance, high-accuracy GPU simulator. It
 - Install the most recent version of Go from golang.org.
 - Clone this repository, assuming the path is `[mgpusim_home]`.
 - Change your current directory to `[mgpusim_home]/samples/fir`.
-- Compile the simulator with the benchmark with `go build`. The compiler will generate an executed called `fir` (on Linux or Mac OS) or `fir.exe` (on Windows) for you.
+- Compile the simulator with the benchmark with `go build`. The compiler will generate an executable file called `fir` (on Linux or Mac OS) or `fir.exe` (on Windows) for you.
 - Run the simulation with `./fir -timing --report-all` to run the simulation.
 - Check the generated `metrics.csv` file for high-level metrics output.
 
+## Develop with Modified Version of Akita (or other depending libraries)
+
+If a modification to Akita is required, you can clone Akita next to the MGPUSim directory in your system. Then, you can modify the `go.mod` file to include the following line. 
+
+```
+replace github.com/sarchlab/akita/v4 => ../akita
+```
+
+This line will direct the go compiler to use your local version of Akita rather than the official release of Akita. 
+
 ## Benchmark Support
 
 | AMD APP SDK           | DNN Mark   | HeteroMark | Polybench | Rodinia          | SHOC      |

accelsim_tracing/alu/alu.go

@@ -1,6 +1,6 @@
 package alu
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type ALU interface {
 	withParent(aluGroup *ALUGroup) ALU

accelsim_tracing/alu/builder.go

@@ -1,6 +1,6 @@
 package alu
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type ALUGroup struct {
 	meta *aluGroupMetaData

accelsim_tracing/alu/int32.go

@@ -1,6 +1,6 @@
 package alu
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type int32ALU struct {
 	parent *ALUGroup

accelsim_tracing/benchmark/build.go

@@ -3,8 +3,8 @@ package benchmark
 import (
 	"errors"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/trace"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/trace"
 )
 
 type BenchMark struct {

accelsim_tracing/gpc/builder.go

@@ -1,8 +1,8 @@
 package gpc
 
 import (
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/sm"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/sm"
 )
 
 type GPC struct {

accelsim_tracing/gpc/default.go

@@ -1,6 +1,6 @@
 package gpc
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type defaultDispatcher struct {
 	parent *GPC

accelsim_tracing/gpc/dispatcher.go

@@ -1,6 +1,6 @@
 package gpc
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type gpcDispatcher interface {
 	withParent(gpc *GPC) gpcDispatcher

accelsim_tracing/gpu/builder.go

@@ -1,8 +1,8 @@
 package gpu
 
 import (
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpc"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpc"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type GPU struct {

accelsim_tracing/gpu/default.go

@@ -1,7 +1,7 @@
 package gpu
 
 import (
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type defaultDispatcher struct {

accelsim_tracing/gpu/dispatcher.go

@@ -1,6 +1,6 @@
 package gpu
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type gpuDispatcher interface {
 	withParent(gpu *GPU) gpuDispatcher

accelsim_tracing/sm/builder.go

@@ -1,8 +1,8 @@
 package sm
 
 import (
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/smunit"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/smunit"
 )
 
 type SM struct {

accelsim_tracing/sm/default.go

@@ -1,6 +1,6 @@
 package sm
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type defaultDispatcher struct {
 	parent *SM

accelsim_tracing/sm/dispacther.go

@@ -1,6 +1,6 @@
 package sm
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type smDispatcher interface {
 	withParent(sm *SM) smDispatcher

accelsim_tracing/smunit/builder.go

@@ -1,8 +1,8 @@
 package smunit
 
 import (
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/alu"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/alu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type SMUnit struct {

accelsim_tracing/smunit/default.go

@@ -1,6 +1,6 @@
 package smunit
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type defaultDispatcher struct {
 	parent *SMUnit

accelsim_tracing/smunit/dispatcher.go

@@ -1,6 +1,6 @@
 package smunit
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 type smUnitDispatcher interface {
 	withParent(sm *SMUnit) smUnitDispatcher

accelsim_tracing/trace/convert.go

@@ -1,6 +1,6 @@
 package trace
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 
 func (tb *threadBlock) generateNVThreadBlock() *nvidia.ThreadBlock {
 	nvtb := &nvidia.ThreadBlock{

accelsim_tracing/trace/kernel.go

@@ -3,7 +3,7 @@ package trace
 import (
 	"path"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
 )
 
 type kernel struct { // trace execs interface

accelsim_tracing/trace/memory_copy.go

@@ -1,6 +1,6 @@
 package trace
 
-import "github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
+import "github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
 
 type memCopy struct { // trace execs interface
 	parent *Trace

accelsim_tracing/trace/thread_block.go

@@ -5,7 +5,7 @@ import (
 	"log"
 	"strings"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type threadBlock struct {

accelsim_tracing/trace/trace.go

@@ -6,7 +6,7 @@ import (
 	"os"
 	"path"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
 )
 
 type Trace struct {

accelsim_tracing/trace/trace_execs.go

@@ -5,7 +5,7 @@ import (
 	"log"
 	"strings"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
 )
 
 type traceExecs interface {

accelsim_tracing/trace/trace_group.go

@@ -7,7 +7,7 @@ import (
 	"os"
 	"strings"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
 )
 
 type traceGroup struct {

accelsim_tracing/trace/trace_header.go

@@ -5,7 +5,7 @@ import (
 	"log"
 	"strings"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type traceHeader struct {

accelsim_tracing/trace/warp.go

@@ -6,7 +6,7 @@ import (
 	"strconv"
 	"strings"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type warp struct {

accelsim_tracing/tracer.go

@@ -5,9 +5,9 @@ import (
 	"fmt"
 	"log"
 
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/benchmark"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/gpu"
-	"github.com/sarchlab/mgpusim/v3/accelsim_tracing/nvidia"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/benchmark"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/gpu"
+	"github.com/sarchlab/mgpusim/v4/accelsim_tracing/nvidia"
 )
 
 type inputArguments struct {

benchmarks/amdappsdk/bitonicsort/bitonicsort.go

@@ -11,9 +11,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 var doPerPassVerify = false

benchmarks/amdappsdk/fastwalshtransform/fastwalshtransform.go

@@ -10,9 +10,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // KernelArgs defines kernel arguments

benchmarks/amdappsdk/floydwarshall/floydwarshall.go

@@ -9,9 +9,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // KernelArgs defines kernel arguments

benchmarks/amdappsdk/matrixmultiplication/benchmark.go

@@ -7,7 +7,7 @@ import (
 	"math"
 	"math/rand"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
+	"github.com/sarchlab/mgpusim/v4/driver"
 )
 
 // Benchmark defines a benchmark

benchmarks/amdappsdk/matrixmultiplication/mm.go

@@ -6,9 +6,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // A MatrixMultiplier is a service type that can calculate the result of matrix

benchmarks/amdappsdk/matrixtranspose/matrixtranspose.go

@@ -8,9 +8,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // KernelArgs defines kernel arguments

benchmarks/amdappsdk/nbody/nbody.go

@@ -9,9 +9,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // KernelArgs defines kernel arguments

benchmarks/amdappsdk/simpleconvolution/simpleconvolution.go

@@ -8,9 +8,9 @@ import (
 	// embed hsaco files
 	_ "embed"
 
-	"github.com/sarchlab/mgpusim/v3/driver"
-	"github.com/sarchlab/mgpusim/v3/insts"
-	"github.com/sarchlab/mgpusim/v3/kernels"
+	"github.com/sarchlab/mgpusim/v4/driver"
+	"github.com/sarchlab/mgpusim/v4/insts"
+	"github.com/sarchlab/mgpusim/v4/kernels"
 )
 
 // KernelArgs defines kernel arguments

benchmarks/dnn/cpu_only_examples/lenet/main.go

@@ -5,13 +5,13 @@ import (
 	"math"
 	"math/rand"
 
-	"github.com/sarchlab/mgpusim/v3/benchmarks/dnn/tensor"
-	"github.com/sarchlab/mgpusim/v3/benchmarks/dnn/training/optimization"
+	"github.com/sarchlab/mgpusim/v4/benchmarks/dnn/tensor"
+	"github.com/sarchlab/mgpusim/v4/benchmarks/dnn/training/optimization"
 
-	"github.com/sarchlab/mgpusim/v3/benchmarks/dnn/dataset/mnist"
+	"github.com/sarchlab/mgpusim/v4/benchmarks/dnn/dataset/mnist"
 
-	"github.com/sarchlab/mgpusim/v3/benchmarks/dnn/layers"
-	"github.com/sarchlab/mgpusim/v3/benchmarks/dnn/training"
+	"github.com/sarchlab/mgpusim/v4/benchmarks/dnn/layers"
+	"github.com/sarchlab/mgpusim/v4/benchmarks/dnn/training"
 )
 
 func main() {