Skip to content
This repository was archived by the owner on Jan 12, 2024. It is now read-only.

Merging Linux simulator update from dbwz8/simDbg #281

Merged
swernli merged 2 commits into from
Jun 23, 2020
Merged

Merging Linux simulator update from dbwz8/simDbg #281

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
394bdb1
Merging Linux simulator update from dbwz8/simDbg
swernli Jun 23, 2020
2f1c62b
Remove extra semicolon
swernli Jun 23, 2020
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 src/Simulation/Native/codegen/codegen_fma.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ def generate_kernel(n, blocks, only_one_matrix, unroll_loops, avx_len):
kernelarray.append("#ifndef _MSC_VER\n")
kernelarray.append("\t"*indent + "if (ctrlmask == 0){\n")
indent += 1
kernelarray.append("\t"*indent + "#pragma omp parallel for collapse(LOOP_COLLAPSE"+str(n)+") schedule(static)\n" + "\t"*indent + "for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){\n")
kernelarray.append("\t"*indent + "#pragma omp parallel for collapse(LOOP_COLLAPSE"+str(n)+") schedule(static) proc_bind(spread)\n" + "\t"*indent + "for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){\n")
indent = indent + 1
for i in range(1,nc+1):
kernelarray.append("\t"*indent + "for (std::size_t i"+str(i)+" = 0; i"+str(i)+" < dsorted["+str(i-1) + "]; i"+str(i)+" += 2 * dsorted["+str(i)+"]){\n")
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel1.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ void kernel(V& psi, unsigned id0, M const& matrix, std::size_t ctrlmask)

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; ++i1){
kernel_core(psi, i0 + i1, dsorted[0], mm, mmt);
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel2.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ void kernel(V& psi, unsigned id1, unsigned id0, M const& matrix, std::size_t ctr

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; ++i2){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel3.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ void kernel(V& psi, unsigned id2, unsigned id1, unsigned id0, M const& matrix, s

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel4.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@ void kernel(V& psi, unsigned id3, unsigned id2, unsigned id1, unsigned id0, M co

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel5.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,7 +380,7 @@ void kernel(V& psi, unsigned id4, unsigned id3, unsigned id2, unsigned id1, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel6.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ void kernel(V& psi, unsigned id5, unsigned id4, unsigned id3, unsigned id2, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx/kernel7.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,7 +389,7 @@ void kernel(V& psi, unsigned id6, unsigned id5, unsigned id4, unsigned id3, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel1.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ void kernel(V& psi, unsigned id0, M const& matrix, std::size_t ctrlmask)

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; ++i1){
kernel_core(psi, i0 + i1, dsorted[0], mm, mmt);
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel2.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ void kernel(V& psi, unsigned id1, unsigned id0, M const& matrix, std::size_t ctr

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; ++i2){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel3.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ void kernel(V& psi, unsigned id2, unsigned id1, unsigned id0, M const& matrix, s

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel4.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@ void kernel(V& psi, unsigned id3, unsigned id2, unsigned id1, unsigned id0, M co

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel5.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,7 +380,7 @@ void kernel(V& psi, unsigned id4, unsigned id3, unsigned id2, unsigned id1, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel6.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ void kernel(V& psi, unsigned id5, unsigned id4, unsigned id3, unsigned id2, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/avx2/kernel7.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -389,7 +389,7 @@ void kernel(V& psi, unsigned id6, unsigned id5, unsigned id4, unsigned id3, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel1.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, M const& m, M const& mt)
Expand Down Expand Up @@ -49,7 +49,7 @@ void kernel(V& psi, unsigned id0, M const& matrix, std::size_t ctrlmask)

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; ++i1){
kernel_core(psi, i0 + i1, dsorted[0], mm, mmt);
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel2.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, M const& m, M const& mt)
Expand Down Expand Up @@ -58,7 +58,7 @@ void kernel(V& psi, unsigned id1, unsigned id0, M const& matrix, std::size_t ctr

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; ++i2){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel3.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, std::size_t d2, M const& m, M const& mt)
Expand Down Expand Up @@ -84,7 +84,7 @@ void kernel(V& psi, unsigned id2, unsigned id1, unsigned id0, M const& matrix, s

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel4.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, std::size_t d2, std::size_t d3, M const& m, M const& mt)
Expand Down Expand Up @@ -159,7 +159,7 @@ void kernel(V& psi, unsigned id3, unsigned id2, unsigned id1, unsigned id0, M co

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel5.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, std::size_t d2, std::size_t d3, std::size_t d4, M const& m, M const& mt)
Expand Down Expand Up @@ -244,7 +244,7 @@ void kernel(V& psi, unsigned id4, unsigned id3, unsigned id2, unsigned id1, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel6.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, std::size_t d2, std::size_t d3, std::size_t d4, std::size_t d5, M const& m)
Expand Down Expand Up @@ -196,7 +196,7 @@ void kernel(V& psi, unsigned id5, unsigned id4, unsigned id3, unsigned id2, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
4 changes: 2 additions & 2 deletions src/Simulation/Native/src/external/avx512/kernel7.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
// (C) 2018 ETH Zurich, ITP, Thomas H�ner and Damian Steiger
// (C) 2018 ETH Zurich, ITP, Thomas Häner and Damian Steiger

template <class V, class M>
inline void kernel_core(V& psi, std::size_t I, std::size_t d0, std::size_t d1, std::size_t d2, std::size_t d3, std::size_t d4, std::size_t d5, std::size_t d6, M const& m)
Expand Down Expand Up @@ -357,7 +357,7 @@ void kernel(V& psi, unsigned id6, unsigned id5, unsigned id4, unsigned id3, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel1.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ void kernel(V& psi, unsigned id0, M const& matrix, std::size_t ctrlmask)

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE1) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; ++i1){
kernel_core(psi, i0 + i1, dsorted[0], mm);
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel2.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ void kernel(V& psi, unsigned id1, unsigned id0, M const& matrix, std::size_t ctr

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE2) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; ++i2){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel3.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@ void kernel(V& psi, unsigned id2, unsigned id1, unsigned id0, M const& matrix, s

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE3) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel4.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -354,7 +354,7 @@ void kernel(V& psi, unsigned id3, unsigned id2, unsigned id1, unsigned id0, M co

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE4) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel5.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -643,7 +643,7 @@ void kernel(V& psi, unsigned id4, unsigned id3, unsigned id2, unsigned id1, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE5) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel6.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,7 +244,7 @@ void kernel(V& psi, unsigned id5, unsigned id4, unsigned id3, unsigned id2, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE6) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down
2 changes: 1 addition & 1 deletion src/Simulation/Native/src/external/nointrin/kernel7.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -453,7 +453,7 @@ void kernel(V& psi, unsigned id6, unsigned id5, unsigned id4, unsigned id3, unsi

#ifndef _MSC_VER
if (ctrlmask == 0){
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static)
#pragma omp parallel for collapse(LOOP_COLLAPSE7) schedule(static) proc_bind(spread)
for (std::size_t i0 = 0; i0 < n; i0 += 2 * dsorted[0]){
for (std::size_t i1 = 0; i1 < dsorted[0]; i1 += 2 * dsorted[1]){
for (std::size_t i2 = 0; i2 < dsorted[1]; i2 += 2 * dsorted[2]){
Expand Down