first timings

This commit is contained in:
antonl 2026-03-14 20:10:08 +01:00
parent d11d53c0a4
commit 5ee722a96b
4 changed files with 132 additions and 58 deletions

5
.gitignore vendored
View File

@ -285,3 +285,8 @@ ipython_config.py
# Remove previous ipynb_checkpoints # Remove previous ipynb_checkpoints
# git rm -r .ipynb_checkpoints/ # git rm -r .ipynb_checkpoints/
# We do not include any matrix data since it can be quite large.
# Instead there are urls to where to download the data in the repo
*.bin
*.mtx

47
go.sum
View File

@ -1,2 +1,49 @@
dmitri.shuralyov.com/gpu/mtl v0.0.0-20201218220906-28db891af037/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
github.com/ajstarks/svgo v0.0.0-20180226025133-644b8db467af/go.mod h1:K08gAheRH3/J6wwsYMMT4xOr94bZjxIelGM0+d/wbFw=
github.com/fogleman/gg v1.2.1-0.20190220221249-0403632d5b90/go.mod h1:R/bRT+9gY/C5z7JzPU0zXsXHKM4/ayA+zqcVNZzPa1k=
github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
github.com/james-bowman/sparse v0.0.0-20260216202247-495ee4f84d35 h1:J3GUCSQ+WW6iscT305u+4Zmq7KXaqm/Wk5h9ZQDtxic=
github.com/james-bowman/sparse v0.0.0-20260216202247-495ee4f84d35/go.mod h1:sWk/Vt2x04FG4nQrb1BdKP8QXTUFquT0mbtHw8LH+cE=
github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190125153040-c74c464bbbf2/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190731235908-ec7cb31e5a56/go.mod h1:JhuoJpWY28nO4Vef9tZUw9qufEGTyX1+7lmHxV5q5G4=
golang.org/x/exp v0.0.0-20210220032938-85be41e4509f/go.mod h1:I6l2HNBLBZEcrOoCpyKLdY2lHoRZ8lI4x60KMCQDft4=
golang.org/x/image v0.0.0-20180708004352-c73c2afc3b81/go.mod h1:ux5Hcp/YLpHSI86hEcLt0YII63i6oz57MZXIpbrjZUs=
golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
golang.org/x/mobile v0.0.0-20201217150744-e6ae53a27f4f/go.mod h1:skQtrUTUwhdJvXM/2KKJzY8pDgNr9I/FOMqDVRPBUS4=
golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
golang.org/x/mod v0.1.1-0.20191209134235-331c550502dd/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/mod v0.3.1-0.20200828183125-ce943fd02449/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20191001151750-bb3f8db39f24/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190206041539-40960b6deb8e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20190312151545-0bb0c0a6e846/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.0.0-20200117012304-6edc0a871e69/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
golang.org/x/tools v0.0.0-20200207183749-b753a1ba74fa/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gonum.org/v1/gonum v0.0.0-20180816165407-929014505bf4/go.mod h1:Y+Yx5eoAFn32cQvJDxZx5Dpnq+c3wtXuadVZAcxbbBo=
gonum.org/v1/gonum v0.8.2/go.mod h1:oe/vMfY3deqTw+1EZJhuvEW2iwGF1bW9wwu7XCu0+v0=
gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4= gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E= gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
gonum.org/v1/netlib v0.0.0-20190313105609-8cb42192e0e0/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
gonum.org/v1/plot v0.0.0-20190515093506-e2840ee46a6b/go.mod h1:Wt8AAjI+ypCyYX3nZBvf6cAIx93T+c/OS2HFAYskSZc=
rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

View File

@ -3,88 +3,104 @@ package main
import ( import (
"bufio" "bufio"
"fmt" "fmt"
"io"
"os" "os"
"strconv" "strconv"
"strings" "strings"
"time"
"github.com/james-bowman/sparse" "github.com/james-bowman/sparse"
"gonum.org/v1/gonum/mat"
) )
func matrix_read_market(path string) (*sparse.CSR, error) { // The "SuiteSparse" collection of matrices come in a format called
// "market matrix" and so we parse and load them to a sparse.COO format here.
func matrix_load_market(path string) *sparse.COO {
f, err := os.Open(path) f, err := os.Open(path)
if err != nil { if err != nil {
return nil, fmt.Errorf("open %q: %w", path, err) panic(err)
} }
defer f.Close() defer f.Close()
sc := bufio.NewScanner(f) scanner := bufio.NewScanner(f)
const maxCapacity = 1024 * 1024 // Long lines // skip header
buf := make([]byte, 64*1024) scanner.Scan()
sc.Buffer(buf, maxCapacity)
if !sc.Scan() { // skip comments
if err := sc.Err(); err != nil { for scanner.Scan() {
return nil, fmt.Errorf("read header: %w", err) line := scanner.Text()
if !strings.HasPrefix(line, "%") {
break
} }
return nil, fmt.Errorf("empty file!")
} }
header := strings.Fields(strings.TrimSpace(sc.Text())) fields := strings.Fields(scanner.Text())
if len(header) != 5 || header[0] != "%%MatrixMarket" {
return nil, fmt.Errorf("invalid matrix martket header: %q", sc.Text()) rows, _ := strconv.Atoi(fields[0])
cols, _ := strconv.Atoi(fields[1])
nnz, _ := strconv.Atoi(fields[2])
r := make([]int, nnz)
c := make([]int, nnz)
v := make([]float64, nnz)
i := 0
for scanner.Scan() {
f := strings.Fields(scanner.Text())
ri, _ := strconv.Atoi(f[0])
ci, _ := strconv.Atoi(f[1])
val, _ := strconv.ParseFloat(f[2], 64)
r[i] = ri - 1
c[i] = ci - 1
v[i] = val
i++
} }
object := strings.ToLower(header[1]) coo := sparse.NewCOO(rows, cols, r, c, v)
format := strings.ToLower(header[2])
field := strings.ToLower(header[3])
symmetry := strings.ToLower(header[4])
if object != "matrix" { return coo
return nil, fmt.Errorf("unsupported object: %q", object)
}
if format != "coordinate" {
return nil, fmt.Errorf("unsupported format %q (need coordinate)", format)
}
switch field {
case "real", "integer", "pattern":
default:
return nil, fmt.Errorf("unsupported field %q", field)
}
switch symmetry {
case "general", "symmetric":
default:
return nil, fmt.Errorf("unsupported symmetry %q", symmetry)
}
// Skip comments and then read the size line
var size_line string
for sc.Scan() {
line := strings.TrimSpace(sc.Text())
if line == "" || strings.HasPrefix(line, "%") {
continue // skip comment
}
sizeLine
} }
func main() { func main() {
A := mat.NewDense(2, 2, []float64{ // small_test_matrix_path := "suitesparse_test_matrices/1138_bus.mtx"
1, 2, big_8mill_nnz_matrix_path := "suitesparse_test_matrices/thermal2.mtx"
3, 4, m := matrix_load_market(big_8mill_nnz_matrix_path)
}) rows, cols := m.Dims()
fmt.Printf("matrix size: %d x %d \n", rows, cols)
B := mat.NewDense(2, 2, []float64{ if rows != cols {
5, 6, panic("sparse matmul benchmark assumes square matrix")
7, 8, }
})
var C mat.Dense // Convert to Compressed-Sparse-Row-storage
C.Mul(A, B) m_csr := m.ToCSR()
// Warm up caches to not include "first call" effects
var warm sparse.CSR
for i := 0; i < 3; i += 1 {
warm.Mul(m_csr, m_csr)
}
fmt.Printf("%v\n", mat.Formatted(&C)) // The CSR x CSR matrix multiplication is supposed to have a specific optimised
// path for matmuls
var out sparse.CSR
number_of_mults := 100
time_begin := time.Now()
for i := 0; i < number_of_mults; i += 1 {
out.Mul(m_csr, m_csr)
}
elapsed := time.Since(time_begin)
elapsed_ms := elapsed.Milliseconds()
time_per_matmul := float32(elapsed_ms) / float32(number_of_mults)
out_rows, out_cols := out.Dims()
if out_rows != rows || out_cols != cols {
panic("Output matrix dimensions not same as input. We are supposed to matmul square matrices")
}
fmt.Printf("Elapsed time per mat mul: %.4f ms\n", time_per_matmul)
} }

View File

@ -0,0 +1,6 @@
# This is just a small matrix for debugging / validating code
https://suitesparse-collection-website.herokuapp.com/MM/HB/1138_bus.tar.gz
# This is a real large (not really, but ok) sparse matrix with 8.5 million non-zero elements
https://suitesparse-collection-website.herokuapp.com/MM/Schmid/thermal2.tar.gz