| /dports/science/qmcpack/qmcpack-3.11.0/src/AFQMC/Numerics/detail/CUDA/Kernels/ |
| H A D | adiagApy.cu | 52 int block_dim = 256; in adiagApy() local
53 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
54 kernel_adiagApy<<<grid_dim, block_dim>>>(N, alpha, A, lda, y, incy); in adiagApy()
66 int block_dim = 256; in adiagApy() local
67 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
68 kernel_adiagApy<<<grid_dim, block_dim>>>(N, static_cast<thrust::complex<double> const>(alpha), in adiagApy()
77 int block_dim = 256; in adiagApy() local
78 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
79 kernel_adiagApy<<<grid_dim, block_dim>>>(N, alpha, A, lda, y, incy); in adiagApy()
91 int block_dim = 128; in adiagApy() local
[all …]
|
| H A D | zero_complex_part.cu | 35 int block_dim = 256; in zero_complex_part() local
36 int grid_dim = (n + block_dim - 1) / block_dim; in zero_complex_part()
37 …kernel_zero_complex_part<<<grid_dim, block_dim>>>(n, reinterpret_cast<thrust::complex<double>*>(x)… in zero_complex_part()
44 int block_dim = 256; in zero_complex_part() local
45 int grid_dim = (n + block_dim - 1) / block_dim; in zero_complex_part()
46 …kernel_zero_complex_part<<<grid_dim, block_dim>>>(n, reinterpret_cast<thrust::complex<float>*>(x)); in zero_complex_part()
|
| H A D | setIdentity.cu | 94 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
96 kernel_setIdentity<<<grid_dim, block_dim>>>(m, n, A, lda); in set_identity()
106 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
108 kernel_setIdentity<<<grid_dim, block_dim>>>(m, n, A, lda); in set_identity()
118 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
130 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
142 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
154 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
166 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
168 kernel_setIdentity_strided<<<grid_dim, block_dim>>>(nbatch, stride, m, n, in set_identity_strided()
[all …]
|
| H A D | term_by_term_matrix_vec.cu | 133 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_plus() local
134 …kernel_tbt_mv_plus<<<1, block_dim>>>(dim, nrow, ncol, reinterpret_cast<thrust::complex<double>*>(A… in term_by_term_mat_vec_plus()
150 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_minus() local
167 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_mult() local
168 …kernel_tbt_mv_mult<<<1, block_dim>>>(dim, nrow, ncol, reinterpret_cast<thrust::complex<double>*>(A… in term_by_term_mat_vec_mult()
184 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_div() local
185 …kernel_tbt_mv_div<<<1, block_dim>>>(dim, nrow, ncol, reinterpret_cast<thrust::complex<double>*>(A)… in term_by_term_mat_vec_div()
195 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_plus() local
205 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_minus() local
215 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_mult() local
[all …]
|
| H A D | inplace_product.cu | 42 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
43 …kernel_inplace_product<<<grid_dim, block_dim>>>(nbatch, n, m, B, ldb, reinterpret_cast<thrust::com… in inplace_product()
53 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
54 …kernel_inplace_product<<<grid_dim, block_dim>>>(nbatch, n, m, reinterpret_cast<thrust::complex<dou… in inplace_product()
64 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
65 …kernel_inplace_product<<<grid_dim, block_dim>>>(nbatch, n, m, B, ldb, reinterpret_cast<thrust::com… in inplace_product()
75 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
76 …kernel_inplace_product<<<grid_dim, block_dim>>>(nbatch, n, m, reinterpret_cast<thrust::complex<flo… in inplace_product()
|
| H A D | KaKjw_to_QKajw.cu | 129 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
131 …kernel_KaKjw_to_QKajw<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_QKajw()
153 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
155 …kernel_KaKjw_to_QKajw<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_QKajw()
177 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
179 …kernel_KaKjw_to_QKajw<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_QKajw()
201 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
203 …kernel_KaKjw_to_QKajw<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_QKajw()
226 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
228 …kernel_KaKjw_to_QKajw<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_QKajw()
[all …]
|
| H A D | KaKjw_to_KKwaj.cu | 121 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
123 …kernel_KaKjw_to_KKwaj<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_KKwaj()
144 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
146 …kernel_KaKjw_to_KKwaj<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_KKwaj()
167 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
169 …kernel_KaKjw_to_KKwaj<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_KKwaj()
190 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
192 …kernel_KaKjw_to_KKwaj<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_KKwaj()
214 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
216 …kernel_KaKjw_to_KKwaj<<<grid_dim, block_dim>>>(nwalk, nkpts, npol, nmo_max, nmo_tot, nocc_max, nmo… in KaKjw_to_KKwaj()
[all …]
|
| H A D | construct_X.cu | 151 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
154 kernel_construct_X_free_projection<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, in construct_X()
159 kernel_construct_X<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, vbound, in construct_X()
180 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
183 kernel_construct_X_free_projection<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, in construct_X()
188 kernel_construct_X<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, vbound, in construct_X()
209 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
212 kernel_construct_X_free_projection<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, in construct_X()
217 kernel_construct_X<<<grid_dim, block_dim>>>(nCV, nsteps, nwalk, sqrtdt, vbound, in construct_X()
238 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
[all …]
|
| H A D | vKKwij_to_vwKiKj.cu | 190 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
192 …kernel_vKKwij_to_vwKiKj<<<grid_dim, block_dim>>>(nwalk, nkpts, nmo_max, nmo_tot, kk, nmo, nmo0, A,… in vKKwij_to_vwKiKj()
209 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
211 …kernel_vKKwij_to_vwKiKj<<<grid_dim, block_dim>>>(nwalk, nkpts, nmo_max, nmo_tot, kk, nmo, nmo0, A,… in vKKwij_to_vwKiKj()
228 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
247 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
249 kernel_vKKwij_to_vwKiKj<<<grid_dim, block_dim>>>(nwalk, nkpts, nmo_max, nmo_tot, kk, nmo, nmo0, in vKKwij_to_vwKiKj()
268 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
270 kernel_vKKwij_to_vwKiKj<<<grid_dim, block_dim>>>(nwalk, nkpts, nmo_max, nmo_tot, kk, nmo, nmo0, in vKKwij_to_vwKiKj()
289 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
[all …]
|
| H A D | acAxpbB.cu | 76 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
78 kernel_acAxpbB<<<grid_dim, block_dim>>>(m, n, alpha, A, lda, x, incx, beta, B, ldb); in acAxpbB()
98 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
100 kernel_acAxpbB<<<grid_dim, block_dim>>>(m, n, alpha, A, lda, x, incx, beta, B, ldb); in acAxpbB()
120 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
122 kernel_acAxpbB<<<grid_dim, block_dim>>>(m, n, static_cast<thrust::complex<double> const>(alpha), in acAxpbB()
146 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
148 kernel_acAxpbB<<<grid_dim, block_dim>>>(m, n, static_cast<thrust::complex<float> const>(alpha), in acAxpbB()
|
| H A D | Auwn_Bun_Cuw.cu | 283 dim3 block_dim(nthr, nw, 1); in Auwn_Bun_Cuw() local
306 dim3 block_dim(nthr, nw, 1); in Auwn_Bun_Cuw() local
331 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
355 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
378 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
403 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
661 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
687 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
688 kernel_element_wise_Aij_Bjk_Ckji<<<grid_dim, block_dim>>>(ni, nj, nk, in element_wise_Aij_Bjk_Ckji()
713 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
[all …]
|
| /dports/science/qmcpack/qmcpack-3.11.0/src/AFQMC/Numerics/detail/HIP/Kernels/ |
| H A D | adiagApy.hip.cpp | 49 int block_dim = 256; in adiagApy() local
50 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
51 …hipLaunchKernelGGL(kernel_adiagApy, dim3(grid_dim), dim3(block_dim), 0, 0, N, alpha, A, lda, y, in… in adiagApy()
63 int block_dim = 256; in adiagApy() local
64 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
65 hipLaunchKernelGGL(kernel_adiagApy, dim3(grid_dim), dim3(block_dim), 0, 0, N, in adiagApy()
75 int block_dim = 256; in adiagApy() local
76 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
89 int block_dim = 128; in adiagApy() local
90 int grid_dim = (N + block_dim - 1) / block_dim; in adiagApy()
[all …]
|
| H A D | zero_complex_part.hip.cpp | 32 int block_dim = 256; in zero_complex_part() local
33 int grid_dim = (n + block_dim - 1) / block_dim; in zero_complex_part()
34 hipLaunchKernelGGL(kernel_zero_complex_part, dim3(grid_dim), dim3(block_dim), 0, 0, n, in zero_complex_part()
42 int block_dim = 256; in zero_complex_part() local
43 int grid_dim = (n + block_dim - 1) / block_dim; in zero_complex_part()
44 hipLaunchKernelGGL(kernel_zero_complex_part, dim3(grid_dim), dim3(block_dim), 0, 0, n, in zero_complex_part()
|
| H A D | setIdentity.hip.cpp | 98 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
100 hipLaunchKernelGGL(kernel_setIdentity, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, A, lda); in set_identity()
110 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
122 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
124 hipLaunchKernelGGL(kernel_setIdentity, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, in set_identity()
135 dim3 block_dim(xblock_dim, xblock_dim); in set_identity() local
137 hipLaunchKernelGGL(kernel_setIdentity, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, in set_identity()
148 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
160 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
172 dim3 block_dim(xblock_dim, xblock_dim); in set_identity_strided() local
[all …]
|
| H A D | term_by_term_matrix_vec.hip.cpp | 130 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_plus() local
131 hipLaunchKernelGGL(kernel_tbt_mv_plus, dim3(1), dim3(block_dim), 0, 0, dim, nrow, ncol, in term_by_term_mat_vec_plus()
148 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_minus() local
166 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_mult() local
167 hipLaunchKernelGGL(kernel_tbt_mv_mult, dim3(1), dim3(block_dim), 0, 0, dim, nrow, ncol, in term_by_term_mat_vec_mult()
184 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_div() local
185 hipLaunchKernelGGL(kernel_tbt_mv_div, dim3(1), dim3(block_dim), 0, 0, dim, nrow, ncol, in term_by_term_mat_vec_div()
196 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_plus() local
207 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_minus() local
218 dim3 block_dim(xblock_dim, yblock_dim, 1); in term_by_term_mat_vec_mult() local
[all …]
|
| H A D | inplace_product.hip.cpp | 38 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
39 …hipLaunchKernelGGL(kernel_inplace_product, dim3(grid_dim), dim3(block_dim), 0, 0, nbatch, n, m, B,… in inplace_product()
49 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
50 hipLaunchKernelGGL(kernel_inplace_product, dim3(grid_dim), dim3(block_dim), 0, 0, nbatch, n, m, in inplace_product()
61 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
62 …hipLaunchKernelGGL(kernel_inplace_product, dim3(grid_dim), dim3(block_dim), 0, 0, nbatch, n, m, B,… in inplace_product()
72 dim3 block_dim(1, MAX_THREADS_PER_DIM, 1); in inplace_product() local
73 hipLaunchKernelGGL(kernel_inplace_product, dim3(grid_dim), dim3(block_dim), 0, 0, nbatch, n, m, in inplace_product()
|
| H A D | KaKjw_to_KKwaj.hip.cpp | 117 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
119 …hipLaunchKernelGGL(kernel_KaKjw_to_KKwaj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_KKwaj()
140 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
142 …hipLaunchKernelGGL(kernel_KaKjw_to_KKwaj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_KKwaj()
163 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
165 …hipLaunchKernelGGL(kernel_KaKjw_to_KKwaj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_KKwaj()
186 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
188 …hipLaunchKernelGGL(kernel_KaKjw_to_KKwaj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_KKwaj()
210 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_KKwaj() local
212 …hipLaunchKernelGGL(kernel_KaKjw_to_KKwaj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_KKwaj()
[all …]
|
| H A D | KaKjw_to_QKajw.hip.cpp | 126 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
128 …hipLaunchKernelGGL(kernel_KaKjw_to_QKajw, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_QKajw()
150 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
152 …hipLaunchKernelGGL(kernel_KaKjw_to_QKajw, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_QKajw()
174 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
176 …hipLaunchKernelGGL(kernel_KaKjw_to_QKajw, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_QKajw()
198 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
200 …hipLaunchKernelGGL(kernel_KaKjw_to_QKajw, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_QKajw()
223 dim3 block_dim(xblock_dim, yblock_dim, 1); in KaKjw_to_QKajw() local
225 …hipLaunchKernelGGL(kernel_KaKjw_to_QKajw, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, npo… in KaKjw_to_QKajw()
[all …]
|
| H A D | vKKwij_to_vwKiKj.hip.cpp | 187 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
189 …hipLaunchKernelGGL(kernel_vKKwij_to_vwKiKj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, n… in vKKwij_to_vwKiKj()
207 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
209 …hipLaunchKernelGGL(kernel_vKKwij_to_vwKiKj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, n… in vKKwij_to_vwKiKj()
227 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
229 …hipLaunchKernelGGL(kernel_vKKwij_to_vwKiKj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, n… in vKKwij_to_vwKiKj()
247 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
249 …hipLaunchKernelGGL(kernel_vKKwij_to_vwKiKj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, n… in vKKwij_to_vwKiKj()
268 dim3 block_dim(xblock_dim, yblock_dim, 1); in vKKwij_to_vwKiKj() local
270 …hipLaunchKernelGGL(kernel_vKKwij_to_vwKiKj, dim3(grid_dim), dim3(block_dim), 0, 0, nwalk, nkpts, n… in vKKwij_to_vwKiKj()
[all …]
|
| H A D | construct_X.hip.cpp | 147 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
150 …hipLaunchKernelGGL(kernel_construct_X_free_projection, dim3(grid_dim), dim3(block_dim), 0, 0, nCV,… in construct_X()
154 …hipLaunchKernelGGL(kernel_construct_X, dim3(grid_dim), dim3(block_dim), 0, 0, nCV, nsteps, nwalk, … in construct_X()
174 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
177 …hipLaunchKernelGGL(kernel_construct_X_free_projection, dim3(grid_dim), dim3(block_dim), 0, 0, nCV,… in construct_X()
181 …hipLaunchKernelGGL(kernel_construct_X, dim3(grid_dim), dim3(block_dim), 0, 0, nCV, nsteps, nwalk, … in construct_X()
201 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
204 …hipLaunchKernelGGL(kernel_construct_X_free_projection, dim3(grid_dim), dim3(block_dim), 0, 0, nCV,… in construct_X()
208 …hipLaunchKernelGGL(kernel_construct_X, dim3(grid_dim), dim3(block_dim), 0, 0, nCV, nsteps, nwalk, … in construct_X()
228 dim3 block_dim(REDUCE_BLOCK_SIZE, 1, 1); in construct_X() local
[all …]
|
| H A D | acAxpbB.hip.cpp | 73 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
75 …hipLaunchKernelGGL(kernel_acAxpbB, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, alpha, A, lda, x, … in acAxpbB()
95 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
97 …hipLaunchKernelGGL(kernel_acAxpbB, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, alpha, A, lda, x, … in acAxpbB()
117 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
119 hipLaunchKernelGGL(kernel_acAxpbB, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, in acAxpbB()
144 dim3 block_dim(xblock_dim, yblock_dim); in acAxpbB() local
146 hipLaunchKernelGGL(kernel_acAxpbB, dim3(grid_dim), dim3(block_dim), 0, 0, m, n, in acAxpbB()
|
| H A D | Auwn_Bun_Cuw.hip.cpp | 278 dim3 block_dim(nthr, nw, 1); in Auwn_Bun_Cuw() local
279 hipLaunchKernelGGL(kernel_Auwn_Bun_Cuw, dim3(grid_dim), dim3(block_dim), 0, 0, nu, nw, na, in Auwn_Bun_Cuw()
302 dim3 block_dim(nthr, nw, 1); in Auwn_Bun_Cuw() local
327 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
352 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
376 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
402 dim3 block_dim(nthr, nw, 1); in Awiu_Biu_Cuw() local
648 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
674 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
700 dim3 block_dim(nthr, nthrj, 1); in element_wise_Aij_Bjk_Ckji() local
[all …]
|
| /dports/devel/libflatarray/libflatarray-0.3.0/src/detail/ |
| H A D | generate_cuda_launch_config.hpp | 29 void operator()(dim3 *grid_dim, dim3 *block_dim, int x, int y, int z) in operator ()() argument
32 *block_dim = dim3(128, 4, 1); in operator ()()
34 *block_dim = dim3(512, 1, 1); in operator ()()
37 grid_dim->x = divide_and_round_up(x, block_dim->x); in operator ()()
38 grid_dim->y = divide_and_round_up(y, block_dim->y); in operator ()()
39 grid_dim->z = divide_and_round_up(z, block_dim->z); in operator ()()
|
| /dports/science/quantum-espresso/q-e-qe-6.7.0/PP/src/ |
| H A D | write_hamiltonians.f90 | 185 INTEGER :: nblocks, block_dim(nwannierblocksmax), block_l(nwannierblocksmax), & local
189 … SUBROUTINE split_basis_into_blocks(nblocks,block_dim,block_l,block_atom,block_wannier,block_start)
190 …INTEGER, INTENT(OUT) :: nblocks, block_dim(:), block_atom(:), block_l(:), block_wannier(:,:), bloc… local
232 CALL split_basis_into_blocks(nblocks,block_dim,block_l,block_atom,block_wannier,block_start)
240 … block_dim(i), block_start(i), ( orbitals(wan_in(j,1)%ing(1)%m,block_l(i)+1), &
241 j=block_wannier(i,1), block_wannier(i,block_dim(i)) )
256 …INTEGER, INTENT(OUT) :: nblocks, block_dim(:), block_atom(:), block_l(:), block_wannier(:,:), bloc… local
259 block_dim = 0
273 block_dim(iblock) = i - block_start(iblock) + 1
283 block_dim(iblock) = nwan - block_start(iblock) + 1
|
| /dports/devel/py-numba/numba-0.51.2/numba/cuda/simulator/ |
| H A D | kernel.py | 58 self.block_dim = None
68 grid_dim, block_dim = normalize_kernel_dimensions(self.grid_dim,
69 self.block_dim)
71 fake_cuda_module = FakeCUDAModule(grid_dim, block_dim,
105 bm = BlockManager(self.fn, grid_dim, block_dim)
112 self.grid_dim, self.block_dim = \
236 def __init__(self, f, grid_dim, block_dim): argument
238 self._block_dim = block_dim
240 self.block_state = np.zeros(block_dim, dtype=np.bool)
|