Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Remove weight properties and use time_estimate in LLT #87

Merged
merged 3 commits into from
Jun 27, 2023
Merged

Remove weight properties and use time_estimate in LLT #87

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c38a13d
Update submodule to after get_best_device revamp
abouteiller Jun 2, 2023
acccf72
Update dtd tester for the new get_best_device loads
abouteiller Jun 1, 2023
2e8e7b5
Remove weight properties and add time_estimate to LLT
abouteiller Jun 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion parsec
Open in desktop
Submodule parsec updated 42 files
+1 −0 .github/CI/github_runner.yaml
+4 −5 parsec/interfaces/dtd/insert_function.c
+2 −1 parsec/interfaces/ptg/ptg-compiler/jdf.c
+38 −18 parsec/interfaces/ptg/ptg-compiler/jdf2c.c
+28 −21 parsec/mca/device/cuda/device_cuda_module.c
+89 −89 parsec/mca/device/device.c
+21 −10 parsec/mca/device/device.h
+2 −2 parsec/mca/device/device_gpu.h
+5 −5 parsec/mca/device/template/device_template_module.c
+2 −3 parsec/parsec_comm_engine.c
+7 −0 parsec/parsec_internal.h
+3 −3 parsec/parsec_mpi_funnelled.c
+11 −1 parsec/scheduling.c
+1 −1 tests/api/CMakeLists.txt
+9 −7 tests/api/Testings.cmake
+0 −0 tests/api/init_fini.c
+0 −7 tests/api/taskpool_wait/CMakeLists.txt
+1 −0 tests/apps/Testings.cmake
+0 −5 tests/apps/stencil/CMakeLists.txt
+7 −0 tests/apps/stencil/Testings.cmake
+2 −1 tests/dsl/dtd/CMakeLists.txt
+2 −3 tests/dsl/dtd/Testings.cmake
+31 −0 tests/dsl/dtd/dtd_test_new_tile.c
+0 −1 tests/dsl/ptg/CMakeLists.txt
+1 −0 tests/runtime/CMakeLists.txt
+1 −0 tests/runtime/Testings.cmake
+1 −3 tests/runtime/cuda/CMakeLists.txt
+13 −0 tests/runtime/cuda/Testings.cmake
+0 −0 tests/runtime/cuda/cuda_test_internal.h
+21 −11 tests/runtime/cuda/get_best_device_check.jdf
+18 −7 tests/runtime/cuda/nvlink.jdf
+1 −1 tests/runtime/cuda/nvlink_main.c
+0 −0 tests/runtime/cuda/nvlink_wrapper.c
+0 −0 tests/runtime/cuda/nvlink_wrapper.h
+14 −3 tests/runtime/cuda/stage_custom.jdf
+0 −0 tests/runtime/cuda/stage_main.c
+16 −4 tests/runtime/cuda/stress.jdf
+0 −0 tests/runtime/cuda/stress_main.c
+0 −0 tests/runtime/cuda/stress_wrapper.c
+0 −0 tests/runtime/cuda/stress_wrapper.h
+0 −0 tests/runtime/cuda/testing_get_best_device.c
+1 −1 tests/runtime/scheduling/Testings.cmake
3 changes: 1 addition & 2 deletions src/zgemm_NN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,8 +165,7 @@ RW C <- (k == 0) ? ddescC(m, n) [ type = %{ return
CTL ctla -> (k < (descA->nt-lookQ)) ? ctla READ_A(m, k+lookQ)
CTL ctlb -> (k < (descA->nt-lookP)) ? ctlb READ_B(k+lookP, n)

BODY [type=CUDA
weight=(descA->nt-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex lalpha = make_cuDoubleComplex(creal(alpha), cimag(alpha));
Expand Down
3 changes: 1 addition & 2 deletions src/zgemm_NN_gpu.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,8 +362,7 @@ RW C <- k == 0 ? C READ_C(m, n)
CTL Z <- ( k > 0 ) & ((k % tD) == 0) ? Z LOCAL_BARRIER(x, y, z, u, v)
-> ((k == descB->mt-1) | (k == (z+1)*tD-1)) ? Z LOCAL_BARRIER(xn, yn, zn, u, v)

BODY [type=CUDA
weight=(descA->nt-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex lalpha = make_cuDoubleComplex(creal(alpha), cimag(alpha));
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_NN_summa.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,6 @@ CTL ctla -> (k < (descA->nt-lookQ)) ? ctla RING_A(m, k+lookQ, n%Q)
CTL ctlb -> (k < (descA->nt-lookP)) ? ctlb RING_B(k+lookP, n, m%P)

BODY [type=CUDA
weight=(descA->nt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_NT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,6 @@ CTL ctla -> (k < (descA->nt-lookQ)) ? ctla READ_A(m, k+lookQ)
CTL ctlb -> (k < (descA->nt-lookP)) ? ctlb READ_B(n, k+lookP)

BODY [type=CUDA
weight=(descA->nt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_NT_summa.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,6 @@ CTL ctla -> (k < (descA->nt-lookQ)) ? ctla RING_A(m, k+lookQ, n%Q)
CTL ctlb -> (k < (descA->nt-lookP)) ? ctlb RING_B(n, k+lookP, m%P)

BODY [type=CUDA
weight=(descA->nt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_TN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,6 @@ CTL ctla -> (k < (descA->mt-lookQ)) ? ctla READ_A(k+lookQ, m)
CTL ctlb -> (k < (descA->mt-lookP)) ? ctlb READ_B(k+lookP, n)

BODY [type=CUDA
weight=(descA->mt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_TN_summa.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,7 +206,6 @@ CTL ctla -> (k < (descA->mt-lookQ)) ? ctla RING_A(k+lookQ, m, n%Q)
CTL ctlb -> (k < (descA->mt-lookP)) ? ctlb RING_B(k+lookP, n, m%P)

BODY [type=CUDA
weight=(descA->mt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_TT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,6 @@ CTL ctla -> (k < (descA->mt-lookQ)) ? ctla READ_A(k+lookQ, m)
CTL ctlb -> (k < (descA->mt-lookP)) ? ctlb READ_B(n, k+lookP)

BODY [type=CUDA
weight=(descA->mt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgemm_TT_summa.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,7 +206,6 @@ CTL ctla -> (k < (descA->mt-lookQ)) ? ctla RING_A(k+lookQ, m, n%Q)
CTL ctlb -> (k < (descA->mt-lookP)) ? ctlb RING_B(n, k+lookP, m%P)

BODY [type=CUDA
weight=(descA->mt-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descB->mb*descB->nb*parsec_datadist_getsizeoftype(descB->mtype);%}
C.size=%{ return descC->mb*descC->nb*parsec_datadist_getsizeoftype(descC->mtype);%}
Expand Down
1 change: 0 additions & 1 deletion src/zgetrf_nopiv.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,7 +196,6 @@ loc_C = %{ return LOC(descA, m, n); %}
-> ((m > (k+1)) && (n > (k+1))) ? C zgemm(k+1, m, n) /* dep OUT: rely on datacopy dtt for sending */

BODY [type=CUDA
weight="dplasma_imin( m-k, n-k )"
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
C.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
Expand Down
44 changes: 35 additions & 9 deletions src/zpotrf_L.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,10 @@ static void zpotrf_L_update_INFO(parsec_taskpool_t* _tp, const parsec_recursive_
* WARNING: If mt is greater than 1200, we might get integer overflow.
*/

static int64_t zpotrf_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t ztrsm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t zherk_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t zgemm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
%}

/* Globals
Expand All @@ -80,7 +84,9 @@ POWorkspaceID [type = "int" hidden = on default = -1 ]
/**************************************************
* potrf_zpotrf *
**************************************************/
potrf_zpotrf(k) [high_priority = on flops = inline_c %{ return FLOPS_ZPOTRF( CLEAN_MB(descA, k) ); %}]
potrf_zpotrf(k) [high_priority = on
flops = inline_c %{ return FLOPS_ZPOTRF( CLEAN_MB(descA, k) ); %}
time_estimate = zpotrf_time_estimate]

// Execution space
k = 0 .. descA->mt-1
Expand Down Expand Up @@ -181,7 +187,9 @@ END
/**************************************************
* potrf_ztrsm *
**************************************************/
potrf_ztrsm(m, k) [high_priority = on flops = inline_c %{ return FLOPS_ZTRSM(PlasmaRight, CLEAN_MB(descA, m), descA->nb); %}]
potrf_ztrsm(m, k) [high_priority = on
flops = inline_c %{ return FLOPS_ZTRSM(PlasmaRight, CLEAN_MB(descA, m), descA->nb); %}
time_estimate = ztrsm_time_estimate]

// Execution space
m = 1 .. descA->mt-1
Expand All @@ -206,8 +214,7 @@ RW C <- (k == 0) ? ddescA(m, k) [ type = %{ return ADTT_

; (m >= (descA->mt - PRI_CHANGE)) ? (descA->mt - m) * (descA->mt - m) * (descA->mt - m) + 3 * ((2 * descA->mt) - k - m - 1) * (m - k) : PRI_MAX

BODY [type=CUDA
weight=(m+k)]
BODY [type=CUDA]
{
int tempmm = m == descA->mt-1 ? descA->m - m * descA->mb : descA->mb;
int ldak = LDA(ddescA, T);
Expand Down Expand Up @@ -293,7 +300,9 @@ END
/**************************************************
* potrf_zherk *
**************************************************/
potrf_zherk(k, m) [high_priority = on flops = inline_c %{ return FLOPS_ZHERK(CLEAN_MB(descA, m), descA->mb); %}]
potrf_zherk(k, m) [high_priority = on
flops = inline_c %{ return FLOPS_ZHERK(CLEAN_MB(descA, m), descA->mb); %}
time_estimate = zherk_time_estimate]

// Execution space
k = 0 .. descA->mt-2
Expand All @@ -314,8 +323,7 @@ RW T <- (k == 0) ? ddescA(m, m) [ type = %{ return ADTT_REA

; (m >= (descA->mt - PRI_CHANGE)) ? (descA->mt - m) * (descA->mt - m) * (descA->mt - m) + 3 * (m - k) : PRI_MAX

BODY [type=CUDA
weight=(m+k)]
BODY [type=CUDA]
{
int tempmm = m == descA->mt-1 ? descA->m - m*descA->mb : descA->mb;
int ldam_A = LDA(ddescA, A);
Expand Down Expand Up @@ -393,7 +401,8 @@ END
* potrf_zgemm *
**************************************************/
// Name
potrf_zgemm(m, n, k) [flops = inline_c %{ return FLOPS_ZGEMM(CLEAN_MB(descA, m), descA->mb, descA->mb); %}]
potrf_zgemm(m, n, k) [flops = inline_c %{ return FLOPS_ZGEMM(CLEAN_MB(descA, m), descA->mb, descA->mb); %}
time_estimate = zgemm_time_estimate]

// Execution space
k = 0 .. descA->mt-3
Expand All @@ -418,7 +427,6 @@ RW C <- (k == 0) ? ddescA(m, n) [ type = %{ return ADTT_
; (m >= (descA->mt - PRI_CHANGE)) ? (descA->mt - m) * (descA->mt - m) * (descA->mt - m) + 3 * ((2 * descA->mt) - m - n - 3) * (m - n) + 6 * (m - k) : PRI_MAX

BODY [type=CUDA
weight=(n+1-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
C.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
Expand Down Expand Up @@ -524,6 +532,24 @@ END

extern "C" %{

/* Compute the time estimates based on device capabilities and flops for the task */
static int64_t zpotrf_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_L_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZPOTRF(mb) / dev->gflops_fp64;
}
static int64_t ztrsm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_L_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZTRSM(PlasmaRight, mb, mb) / dev->gflops_fp64;
}
static int64_t zherk_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_L_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZHERK(mb, mb) / dev->gflops_fp64;
abouteiller marked this conversation as resolved.
Show resolved Hide resolved
}
static int64_t zgemm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_L_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZGEMM(mb, mb, mb) / dev->gflops_fp64;
}

abouteiller marked this conversation as resolved.
Show resolved Hide resolved
/*
* A function to recursively update the value of the INFO argument for
* recursive calls. We need a special function because the recursive calls being asynchronous
Expand Down
44 changes: 35 additions & 9 deletions src/zpotrf_U.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,10 @@ static void zpotrf_U_update_INFO(parsec_taskpool_t* _tp, const parsec_recursive_
* WARNING: If mt is greater than 1200, we might get integer overflow.
*/

static int64_t zpotrf_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t ztrsm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t zherk_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
static int64_t zgemm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev);
%}

/* Globals
Expand All @@ -80,7 +84,9 @@ POWorkspaceID [type = "int" hidden = on default = -1 ]
/**************************************************
* potrf_zpotrf *
**************************************************/
potrf_zpotrf(k) [high_priority = on flops = inline_c %{ return FLOPS_ZPOTRF( CLEAN_NB(descA, k) ); %}]
potrf_zpotrf(k) [high_priority = on
flops = inline_c %{ return FLOPS_ZPOTRF( CLEAN_NB(descA, k) ); %}
time_estimate = zpotrf_time_estimate]

// Execution space
k = 0 .. descA->nt-1
Expand Down Expand Up @@ -182,7 +188,9 @@ END
/**************************************************
* potrf_ztrsm *
**************************************************/
potrf_ztrsm(k, n) [high_priority = on flops = inline_c %{ return FLOPS_ZTRSM(PlasmaLeft, descA->mb, CLEAN_NB(descA, n)); %}]
potrf_ztrsm(k, n) [high_priority = on
flops = inline_c %{ return FLOPS_ZTRSM(PlasmaLeft, descA->mb, CLEAN_NB(descA, n)); %}
time_estimate = ztrsm_time_estimate]

// Execution space
k = 0 .. descA->nt-2
Expand All @@ -207,8 +215,7 @@ RW C <- (k == 0) ? ddescA(k, n) [ type = %{ return ADTT_

; (n >= (descA->nt - PRI_CHANGE)) ? (descA->nt - n) * (descA->nt - n) * (descA->nt - n) + 3 * ((2 * descA->nt) - k - n - 1) * (n - k) : PRI_MAX

BODY [type=CUDA
weight=(k+n)]
BODY [type=CUDA]
{
int tempnn = n == descA->nt - 1 ? descA->n - n * descA->nb : descA->nb;
int ldak_T = LDA(ddescA, T);
Expand Down Expand Up @@ -294,7 +301,9 @@ END
/**************************************************
* potrf_zherk *
**************************************************/
potrf_zherk(k, n) [high_priority = on flops = inline_c %{ return FLOPS_ZHERK(CLEAN_NB(descA, n), descA->mb); %}]
potrf_zherk(k, n) [high_priority = on
flops = inline_c %{ return FLOPS_ZHERK(CLEAN_NB(descA, n), descA->mb); %}
time_estimate = zherk_time_estimate]

// Execution space
k = 0 .. descA->nt-2
Expand All @@ -316,8 +325,7 @@ RW T <- (k == 0) ? ddescA(n, n) [ type = %{ return ADTT_REA

; (n >= (descA->nt - PRI_CHANGE)) ? (descA->nt - n) * (descA->nt - n) * (descA->nt - n) + 3 * (n - k) : PRI_MAX

BODY [type=CUDA
weight=(k+n)]
BODY [type=CUDA]
{
int tempnn = n == descA->nt-1 ? descA->n - n*descA->nb : descA->nb;
int ldak = LDA(ddescA, A);
Expand Down Expand Up @@ -396,7 +404,8 @@ END
* potrf_zgemm *
**************************************************/
// Name
potrf_zgemm(m, n, k) [ flops = inline_c %{ return FLOPS_ZGEMM(descA->mb, CLEAN_NB(descA, n), descA->nb); %}]
potrf_zgemm(m, n, k) [ flops = inline_c %{ return FLOPS_ZGEMM(descA->mb, CLEAN_NB(descA, n), descA->nb); %}
time_estimate = zgemm_time_estimate]

// Execution space
k = 0 .. descA->mt-3
Expand All @@ -421,7 +430,6 @@ RW C <- (k == 0) ? ddescA(m, n) [ type = %{ return ADTT_
; (n >= (descA->nt - PRI_CHANGE)) ? (descA->nt - n) * (descA->nt - n) * (descA->nt - n) + 3 * ((2 * descA->nt) - m - n - 3) * (n - m) + 6 * (n - k) : PRI_MAX

BODY [type=CUDA
weight=(m+1-k)
A.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
B.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
C.size=%{ return descA->mb*descA->nb*parsec_datadist_getsizeoftype(descA->mtype);%}
Expand Down Expand Up @@ -538,6 +546,24 @@ END

extern "C" %{

/* Compute the time estimates based on device capabilities and flops for the task */
static int64_t zpotrf_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_U_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZPOTRF(mb) / dev->gflops_fp64;
}
static int64_t ztrsm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_U_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZTRSM(PlasmaLeft, mb, mb) / dev->gflops_fp64;
}
static int64_t zherk_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_U_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZHERK(mb, mb) / dev->gflops_fp64;
}
static int64_t zgemm_time_estimate(const parsec_task_t *task, parsec_device_module_t *dev) {
int mb = ((parsec_zpotrf_U_taskpool_t*)task->taskpool)->_g_descA->mb;
return (int64_t)FLOPS_ZGEMM(mb, mb, mb) / dev->gflops_fp64;
}

/*
* A function to recursively update the value of the INFO argument for
* recursive calls. We need a special function because the recursive calls being asynchronous
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_LLN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), CLEAN_N
-> (m>=(k+2)) ? E zgemm(k+1, m, n)
-> ((k+1)==m) ? B ztrsm(m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_LLT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,8 +90,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(descB->mb, CLEAN_NB(descB,
-> ((1+k)==m) ? B ztrsm(m, n)
-> (m>=(k+2)) ? E zgemm(k+1, m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_LUN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(descB->mb, CLEAN_NB(descB,
-> ((1+k)==m) ? B ztrsm(m, n)
-> (m>=(k+2)) ? E zgemm(k+1, m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_LUT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), CLEAN_N
-> (m>=(k+2)) ? E zgemm(k+1, m, n)
-> ((k+1)==m) ? B ztrsm(m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_RLN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), descB->
-> (n>=(k+2)) ? E zgemm(k+1, m, n)
-> ((k+1)==n) ? B ztrsm(n, m)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_RLT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,8 +88,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), CLEAN_N
-> ((1+k)==n) ? B ztrsm(n, m)
-> (n>=(2+k)) ? E zgemm(k+1, m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex zone = make_cuDoubleComplex( 1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_RUN.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,8 +89,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), CLEAN_N
-> ((1+k)==n) ? B ztrsm(n, m)
-> (n>=(2+k)) ? E zgemm(k+1, m, n)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex mzone = make_cuDoubleComplex(-1., 0.);
Expand Down
3 changes: 1 addition & 2 deletions src/ztrsm_RUT.jdf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,8 +88,7 @@ zgemm(k,m,n) [ flops = inline_c%{ return FLOPS_ZGEMM(CLEAN_MB(descB, m), descB->
-> (n>=(k+2)) ? E zgemm(k+1, m, n)
-> ((k+1)==n) ? B ztrsm(n, m)

BODY [type=CUDA
weight=(n+1-k)]
BODY [type=CUDA]
{
#if defined(PRECISION_z) || defined(PRECISION_c)
cuDoubleComplex zone = make_cuDoubleComplex( 1., 0.);
Expand Down
Loading