[CUSPARSE] Interface generic mv! for SparseMatrixBSR #2929
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Your PR requires formatting changes to meet the project's style guidelines. Click here to view the suggested changes.diff --git a/lib/cusparse/generic.jl b/lib/cusparse/generic.jl
index eb7abad69..8bbb57ee7 100644
--- a/lib/cusparse/generic.jl
+++ b/lib/cusparse/generic.jl
@@ -152,7 +152,8 @@ function vv!(transx::SparseChar, X::CuSparseVector{T}, Y::DenseCuVector{T}, inde
return result[]
end
-function mv!(transa::SparseChar, alpha::Number, A::CuSparseMatrix{TA}, X::DenseCuVector{T},
+function mv!(
+ transa::SparseChar, alpha::Number, A::CuSparseMatrix{TA}, X::DenseCuVector{T},
beta::Number, Y::DenseCuVector{T}, index::SparseChar, algo::cusparseSpMVAlg_t=CUSPARSE_SPMV_ALG_DEFAULT) where {TA, T}
(A isa CuSparseMatrixBSR) && (CUSPARSE.version() < v"12.6.3") && throw(ErrorException("This operation is not supported by the current CUDA version."))
@@ -161,7 +162,7 @@ function mv!(transa::SparseChar, alpha::Number, A::CuSparseMatrix{TA}, X::DenseC
transa = T <: Real && transa == 'C' ? 'T' : transa
descA = CuSparseMatrixDescriptor(A, index)
- m,n = size(A)
+ m, n = size(A)
if transa == 'N'
chkmvdims(X,n,Y,m)
diff --git a/lib/cusparse/level2.jl b/lib/cusparse/level2.jl
index 37a9bd686..afccca8b6 100644
--- a/lib/cusparse/level2.jl
+++ b/lib/cusparse/level2.jl
@@ -8,13 +8,15 @@ for (fname,elty) in ((:cusparseSbsrmv, :Float32),
(:cusparseCbsrmv, :ComplexF32),
(:cusparseZbsrmv, :ComplexF64))
@eval begin
- function mv2!(transa::SparseChar,
- alpha::Number,
- A::CuSparseMatrixBSR{$elty},
- X::CuVector{$elty},
- beta::Number,
- Y::CuVector{$elty},
- index::SparseChar)
+ function mv2!(
+ transa::SparseChar,
+ alpha::Number,
+ A::CuSparseMatrixBSR{$elty},
+ X::CuVector{$elty},
+ beta::Number,
+ Y::CuVector{$elty},
+ index::SparseChar
+ )
# Support transa = 'C' for real matrices
transa = $elty <: Real && transa == 'C' ? 'T' : transa
diff --git a/test/libraries/cusparse.jl b/test/libraries/cusparse.jl
index e09a338a2..17e1c68ca 100644
--- a/test/libraries/cusparse.jl
+++ b/test/libraries/cusparse.jl
@@ -756,7 +756,8 @@ end
alpha = rand(elty)
beta = rand(elty)
@testset "$(typeof(d_A))" for d_A in [CuSparseMatrixCSR(A),
- CuSparseMatrixCSC(A)]
+ CuSparseMatrixCSC(A),
+ ]
d_x = CuArray(x)
d_y = CuArray(y)
@test_throws DimensionMismatch CUSPARSE.mv!('T',alpha,d_A,d_x,beta,d_y,'O')
@@ -769,9 +770,9 @@ end
@testset "$(typeof(d_A))" for d_A in [CuSparseMatrixBSR(A, blockdim)]
d_x = CuArray(x)
d_y = CuArray(y)
- @test_throws DimensionMismatch CUSPARSE.mv2!('T',alpha,d_A,d_x,beta,d_y,'O')
- @test_throws DimensionMismatch CUSPARSE.mv2!('N',alpha,d_A,d_y,beta,d_x,'O')
- CUSPARSE.mv2!('N',alpha,d_A,d_x,beta,d_y,'O')
+ @test_throws DimensionMismatch CUSPARSE.mv2!('T', alpha, d_A, d_x, beta, d_y, 'O')
+ @test_throws DimensionMismatch CUSPARSE.mv2!('N', alpha, d_A, d_y, beta, d_x, 'O')
+ CUSPARSE.mv2!('N', alpha, d_A, d_x, beta, d_y, 'O')
h_z = collect(d_y)
z = alpha * A * x + beta * y
@test z ≈ h_z
diff --git a/test/libraries/cusparse/generic.jl b/test/libraries/cusparse/generic.jl
index 7843fd40b..b729c92b9 100644
--- a/test/libraries/cusparse/generic.jl
+++ b/test/libraries/cusparse/generic.jl
@@ -32,7 +32,9 @@ SPMV_ALGOS = Dict(CuSparseMatrixCSC => [CUSPARSE.CUSPARSE_SPMV_ALG_DEFAULT],
CUSPARSE.CUSPARSE_SPMV_CSR_ALG1,
CUSPARSE.CUSPARSE_SPMV_CSR_ALG2],
CuSparseMatrixCOO => [CUSPARSE.CUSPARSE_SPMV_ALG_DEFAULT,
- CUSPARSE.CUSPARSE_SPMV_COO_ALG1])
+ CUSPARSE.CUSPARSE_SPMV_COO_ALG1,
+ ]
+)
SPMM_ALGOS = Dict(CuSparseMatrixCSC => [CUSPARSE.CUSPARSE_SPMM_ALG_DEFAULT],
CuSparseMatrixCSR => [CUSPARSE.CUSPARSE_SPMM_ALG_DEFAULT,
@@ -41,9 +43,11 @@ SPMM_ALGOS = Dict(CuSparseMatrixCSC => [CUSPARSE.CUSPARSE_SPMM_ALG_DEFAULT],
CUSPARSE.CUSPARSE_SPMM_CSR_ALG3],
CuSparseMatrixCOO => [CUSPARSE.CUSPARSE_SPMM_ALG_DEFAULT,
CUSPARSE.CUSPARSE_SPMM_COO_ALG1,
- CUSPARSE.CUSPARSE_SPMM_COO_ALG2,
+ CUSPARSE.CUSPARSE_SPMM_COO_ALG2,
CUSPARSE.CUSPARSE_SPMM_COO_ALG3,
- CUSPARSE.CUSPARSE_SPMM_COO_ALG4])
+ CUSPARSE.CUSPARSE_SPMM_COO_ALG4,
+ ]
+)
if CUSPARSE.version() >= v"12.1.3"
push!(SPMV_ALGOS[CuSparseMatrixCOO], CUSPARSE.CUSPARSE_SPMV_COO_ALG2)
@@ -55,8 +59,10 @@ if CUSPARSE.version() >= v"12.5.1"
end
if CUSPARSE.version() >= v"12.6.3"
- SPMV_ALGOS[CuSparseMatrixBSR] = [CUSPARSE.CUSPARSE_SPMV_ALG_DEFAULT,
- CUSPARSE.CUSPARSE_SPMV_BSR_ALG1]
+ SPMV_ALGOS[CuSparseMatrixBSR] = [
+ CUSPARSE.CUSPARSE_SPMV_ALG_DEFAULT,
+ CUSPARSE.CUSPARSE_SPMV_BSR_ALG1,
+ ]
end
for SparseMatrixType in keys(SPMV_ALGOS)
@@ -67,7 +73,7 @@ for SparseMatrixType in keys(SPMV_ALGOS)
A = sprand(T, 20, 10, 0.1)
B = transa == 'N' ? rand(T, 10) : rand(T, 20)
C = transa == 'N' ? rand(T, 20) : rand(T, 10)
- dA = SparseMatrixType == CuSparseMatrixBSR ? SparseMatrixType(A,1) : SparseMatrixType(A)
+ dA = SparseMatrixType == CuSparseMatrixBSR ? SparseMatrixType(A, 1) : SparseMatrixType(A)
dB = CuArray(B)
dC = CuArray(C)
@@ -313,14 +319,20 @@ end
@test Z ≈ collect(dY)
end
-SPGEMM_ALGOS = Dict(CuSparseMatrixCSR => [CUSPARSE.CUSPARSE_SPGEMM_DEFAULT,
- CUSPARSE.CUSPARSE_SPGEMM_ALG1,
- CUSPARSE.CUSPARSE_SPGEMM_ALG2,
- CUSPARSE.CUSPARSE_SPGEMM_ALG3],
- CuSparseMatrixCSC => [CUSPARSE.CUSPARSE_SPGEMM_DEFAULT,
- CUSPARSE.CUSPARSE_SPGEMM_ALG1,
- CUSPARSE.CUSPARSE_SPGEMM_ALG2,
- CUSPARSE.CUSPARSE_SPGEMM_ALG3])
+SPGEMM_ALGOS = Dict(
+ CuSparseMatrixCSR => [
+ CUSPARSE.CUSPARSE_SPGEMM_DEFAULT,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG1,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG2,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG3,
+ ],
+ CuSparseMatrixCSC => [
+ CUSPARSE.CUSPARSE_SPGEMM_DEFAULT,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG1,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG2,
+ CUSPARSE.CUSPARSE_SPGEMM_ALG3,
+ ]
+)
# Algorithms CUSPARSE.CUSPARSE_SPGEMM_CSR_ALG_DETERMINITIC and
# CUSPARSE.CUSPARSE_SPGEMM_CSR_ALG_NONDETERMINITIC are dedicated to the cusparseSpGEMMreuse routine.
@@ -406,9 +418,9 @@ for SparseMatrixType in keys(SDDMM_ALGOS)
mB = transb == 'N' ? 10 : 35
nB = transb == 'N' ? 35 : 10
- A = rand(T,mA,nA)
- B = rand(T,mB,nB)
- C = sprand(T,25,35,0.3)
+ A = rand(T, mA, nA)
+ B = rand(T, mB, nB)
+ C = sprand(T, 25, 35, 0.3)
spyC = copy(C)
spyC.nzval .= one(T) |
amontoison
force-pushed
the
am/cusparse_bsr_mv
branch
from
acabc12 to
4e9d911
Compare
|
CI failures are related |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
CuSparseMatrixBSRfor generic sparsemv!added with CUDA13.0.1.mv!andmm!because we don't have any high-level way to reuse the buffer / descriptor. We just do more work for nothing.