| Message ID | patch-18149-tamar@arm.com |
|---|---|
| State | New |
| Headers | show |
| Series | middle-end: fill in reduction PHI for all alt exits [PR113144] | expand |
On Thu, 11 Jan 2024, Tamar Christina wrote: > Hi All, > > When we have a loop with more than 2 exits and a reduction I forgot to fill in > the PHI value for all alternate exits. > > All alternate exits use the same PHI value so we should loop over the new > PHI elements and copy the value across since we call the reduction calculation > code only once for all exits. This was normally covered up by earlier parts of > the compiler rejecting loops incorrectly (which has been fixed now). > > Note that while I can use the loop in all cases, the reason I separated out the > main and alt exit is so that if you pass the wrong edge the macro will assert. > > Bootstrapped Regtested on aarch64-none-linux-gnu, x86_64-pc-linux-gnu > and no issues. > > Ok for master? OK > Thanks, > Tamar > > gcc/ChangeLog: > > PR tree-optimization/113178 > * tree-vect-loop.cc (vect_create_epilog_for_reduction): Fill in all > alternate exits. > > gcc/testsuite/ChangeLog: > > PR tree-optimization/113178 > * g++.dg/vect/vect-early-break_6-pr113178.cc: New test. > * gcc.dg/vect/vect-early-break_101-pr113178.c: New test. > * gcc.dg/vect/vect-early-break_102-pr113178.c: New test. > > --- inline copy of patch -- > diff --git a/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc > new file mode 100644 > index 0000000000000000000000000000000000000000..da008759a72dd563bf4930decd74470ae35cb98e > --- /dev/null > +++ b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc > @@ -0,0 +1,34 @@ > +/* { dg-do compile } */ > +/* { dg-add-options vect_early_break } */ > +/* { dg-require-effective-target vect_early_break } */ > +/* { dg-require-effective-target vect_int } */ > + > +struct PixelWeight { > + int m_SrcStart; > + int m_Weights[]; > +}; > +struct CWeightTable { > + int *GetValueFromPixelWeight(PixelWeight *, int) const; > +}; > +char ContinueStretchHorz_dest_scan; > +struct CStretchEngine { > + bool ContinueStretchHorz(); > + CWeightTable m_WeightTable; > +}; > +int *CWeightTable::GetValueFromPixelWeight(PixelWeight *pWeight, > + int index) const { > + long __trans_tmp_1; > + if (index < pWeight->m_SrcStart) > + return __trans_tmp_1 ? &pWeight->m_Weights[pWeight->m_SrcStart] : nullptr; > +} > +bool CStretchEngine::ContinueStretchHorz() { > + { > + PixelWeight pPixelWeights; > + int dest_g_m; > + for (int j; j; j++) { > + int pWeight = *m_WeightTable.GetValueFromPixelWeight(&pPixelWeights, j); > + dest_g_m += pWeight; > + } > + ContinueStretchHorz_dest_scan = dest_g_m; > + } > +} > diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c > new file mode 100644 > index 0000000000000000000000000000000000000000..8b91112133f0522270bb4d92664355838a405aaf > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c > @@ -0,0 +1,22 @@ > +/* { dg-do compile } */ > +/* { dg-add-options vect_early_break } */ > +/* { dg-require-effective-target vect_early_break } */ > +/* { dg-require-effective-target vect_int } */ > + > +struct PixelWeight { > + int m_SrcStart; > + int m_Weights[16]; > +}; > +char h; > +void f(struct PixelWeight *pPixelWeights) { > + int dest_g_m; > + long tt; > + for (int j = 0; j < 16; j++) { > + int *p = 0; > + if (j < pPixelWeights->m_SrcStart) > + p = tt ? &pPixelWeights->m_Weights[0] : 0; > + int pWeight = *p; > + dest_g_m += pWeight; > + } > + h = dest_g_m; > +} > diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c > new file mode 100644 > index 0000000000000000000000000000000000000000..ad7582e440720e50a2769239c88b1e07517e4c10 > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c > @@ -0,0 +1,19 @@ > +/* { dg-do compile } */ > +/* { dg-add-options vect_early_break } */ > +/* { dg-require-effective-target vect_early_break } */ > +/* { dg-require-effective-target vect_int } */ > +/* { dg-additional-options "-std=gnu99 -fpermissive -fgnu89-inline -Ofast -fprofile-generate -w" } */ > + > +extern int replace_reg_with_saved_mem_i, replace_reg_with_saved_mem_nregs, > + replace_reg_with_saved_mem_mem_1; > +replace_reg_with_saved_mem_mode() { > + if (replace_reg_with_saved_mem_i) > + return; > + while (++replace_reg_with_saved_mem_i < replace_reg_with_saved_mem_nregs) > + if (replace_reg_with_saved_mem_i) > + break; > + if (replace_reg_with_saved_mem_i) > + if (replace_reg_with_saved_mem_mem_1) > + adjust_address_1(); > + replace_reg_with_saved_mem_mem_1 ? fancy_abort() : 0; > +} > diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc > index 27bb28365936978013a576b64b72d9e92375f361..da2dfa176ecd457ebc11d1131302ca15d77d779d 100644 > --- a/gcc/tree-vect-loop.cc > +++ b/gcc/tree-vect-loop.cc > @@ -6223,7 +6223,13 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo, > phi = create_phi_node (new_def, exit_bb); > if (j) > def = gimple_get_lhs (vec_stmts[j]); > - SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); > + if (LOOP_VINFO_IV_EXIT (loop_vinfo) == loop_exit) > + SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); > + else > + { > + for (unsigned k = 0; k < gimple_phi_num_args (phi); k++) > + SET_PHI_ARG_DEF (phi, k, def); > + } > new_def = gimple_convert (&stmts, vectype, new_def); > reduc_inputs.quick_push (new_def); > } > > > > >
--- /dev/null +++ b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc @@ -0,0 +1,34 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ + +struct PixelWeight { + int m_SrcStart; + int m_Weights[]; +}; +struct CWeightTable { + int *GetValueFromPixelWeight(PixelWeight *, int) const; +}; +char ContinueStretchHorz_dest_scan; +struct CStretchEngine { + bool ContinueStretchHorz(); + CWeightTable m_WeightTable; +}; +int *CWeightTable::GetValueFromPixelWeight(PixelWeight *pWeight, + int index) const { + long __trans_tmp_1; + if (index < pWeight->m_SrcStart) + return __trans_tmp_1 ? &pWeight->m_Weights[pWeight->m_SrcStart] : nullptr; +} +bool CStretchEngine::ContinueStretchHorz() { + { + PixelWeight pPixelWeights; + int dest_g_m; + for (int j; j; j++) { + int pWeight = *m_WeightTable.GetValueFromPixelWeight(&pPixelWeights, j); + dest_g_m += pWeight; + } + ContinueStretchHorz_dest_scan = dest_g_m; + } +} diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c new file mode 100644 index 0000000000000000000000000000000000000000..8b91112133f0522270bb4d92664355838a405aaf --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c @@ -0,0 +1,22 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ + +struct PixelWeight { + int m_SrcStart; + int m_Weights[16]; +}; +char h; +void f(struct PixelWeight *pPixelWeights) { + int dest_g_m; + long tt; + for (int j = 0; j < 16; j++) { + int *p = 0; + if (j < pPixelWeights->m_SrcStart) + p = tt ? &pPixelWeights->m_Weights[0] : 0; + int pWeight = *p; + dest_g_m += pWeight; + } + h = dest_g_m; +} diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c new file mode 100644 index 0000000000000000000000000000000000000000..ad7582e440720e50a2769239c88b1e07517e4c10 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c @@ -0,0 +1,19 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ +/* { dg-additional-options "-std=gnu99 -fpermissive -fgnu89-inline -Ofast -fprofile-generate -w" } */ + +extern int replace_reg_with_saved_mem_i, replace_reg_with_saved_mem_nregs, + replace_reg_with_saved_mem_mem_1; +replace_reg_with_saved_mem_mode() { + if (replace_reg_with_saved_mem_i) + return; + while (++replace_reg_with_saved_mem_i < replace_reg_with_saved_mem_nregs) + if (replace_reg_with_saved_mem_i) + break; + if (replace_reg_with_saved_mem_i) + if (replace_reg_with_saved_mem_mem_1) + adjust_address_1(); + replace_reg_with_saved_mem_mem_1 ? fancy_abort() : 0; +} diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 27bb28365936978013a576b64b72d9e92375f361..da2dfa176ecd457ebc11d1131302ca15d77d779d 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -6223,7 +6223,13 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo, phi = create_phi_node (new_def, exit_bb); if (j) def = gimple_get_lhs (vec_stmts[j]); - SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); + if (LOOP_VINFO_IV_EXIT (loop_vinfo) == loop_exit) + SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); + else + { + for (unsigned k = 0; k < gimple_phi_num_args (phi); k++) + SET_PHI_ARG_DEF (phi, k, def); + } new_def = gimple_convert (&stmts, vectype, new_def); reduc_inputs.quick_push (new_def); }
Hi All, When we have a loop with more than 2 exits and a reduction I forgot to fill in the PHI value for all alternate exits. All alternate exits use the same PHI value so we should loop over the new PHI elements and copy the value across since we call the reduction calculation code only once for all exits. This was normally covered up by earlier parts of the compiler rejecting loops incorrectly (which has been fixed now). Note that while I can use the loop in all cases, the reason I separated out the main and alt exit is so that if you pass the wrong edge the macro will assert. Bootstrapped Regtested on aarch64-none-linux-gnu, x86_64-pc-linux-gnu and no issues. Ok for master? Thanks, Tamar gcc/ChangeLog: PR tree-optimization/113178 * tree-vect-loop.cc (vect_create_epilog_for_reduction): Fill in all alternate exits. gcc/testsuite/ChangeLog: PR tree-optimization/113178 * g++.dg/vect/vect-early-break_6-pr113178.cc: New test. * gcc.dg/vect/vect-early-break_101-pr113178.c: New test. * gcc.dg/vect/vect-early-break_102-pr113178.c: New test. --- inline copy of patch -- diff --git a/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc new file mode 100644 index 0000000000000000000000000000000000000000..da008759a72dd563bf4930decd74470ae35cb98e -- diff --git a/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc new file mode 100644 index 0000000000000000000000000000000000000000..da008759a72dd563bf4930decd74470ae35cb98e --- /dev/null +++ b/gcc/testsuite/g++.dg/vect/vect-early-break_6-pr113178.cc @@ -0,0 +1,34 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ + +struct PixelWeight { + int m_SrcStart; + int m_Weights[]; +}; +struct CWeightTable { + int *GetValueFromPixelWeight(PixelWeight *, int) const; +}; +char ContinueStretchHorz_dest_scan; +struct CStretchEngine { + bool ContinueStretchHorz(); + CWeightTable m_WeightTable; +}; +int *CWeightTable::GetValueFromPixelWeight(PixelWeight *pWeight, + int index) const { + long __trans_tmp_1; + if (index < pWeight->m_SrcStart) + return __trans_tmp_1 ? &pWeight->m_Weights[pWeight->m_SrcStart] : nullptr; +} +bool CStretchEngine::ContinueStretchHorz() { + { + PixelWeight pPixelWeights; + int dest_g_m; + for (int j; j; j++) { + int pWeight = *m_WeightTable.GetValueFromPixelWeight(&pPixelWeights, j); + dest_g_m += pWeight; + } + ContinueStretchHorz_dest_scan = dest_g_m; + } +} diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c new file mode 100644 index 0000000000000000000000000000000000000000..8b91112133f0522270bb4d92664355838a405aaf --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_101-pr113178.c @@ -0,0 +1,22 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ + +struct PixelWeight { + int m_SrcStart; + int m_Weights[16]; +}; +char h; +void f(struct PixelWeight *pPixelWeights) { + int dest_g_m; + long tt; + for (int j = 0; j < 16; j++) { + int *p = 0; + if (j < pPixelWeights->m_SrcStart) + p = tt ? &pPixelWeights->m_Weights[0] : 0; + int pWeight = *p; + dest_g_m += pWeight; + } + h = dest_g_m; +} diff --git a/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c new file mode 100644 index 0000000000000000000000000000000000000000..ad7582e440720e50a2769239c88b1e07517e4c10 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-early-break_102-pr113178.c @@ -0,0 +1,19 @@ +/* { dg-do compile } */ +/* { dg-add-options vect_early_break } */ +/* { dg-require-effective-target vect_early_break } */ +/* { dg-require-effective-target vect_int } */ +/* { dg-additional-options "-std=gnu99 -fpermissive -fgnu89-inline -Ofast -fprofile-generate -w" } */ + +extern int replace_reg_with_saved_mem_i, replace_reg_with_saved_mem_nregs, + replace_reg_with_saved_mem_mem_1; +replace_reg_with_saved_mem_mode() { + if (replace_reg_with_saved_mem_i) + return; + while (++replace_reg_with_saved_mem_i < replace_reg_with_saved_mem_nregs) + if (replace_reg_with_saved_mem_i) + break; + if (replace_reg_with_saved_mem_i) + if (replace_reg_with_saved_mem_mem_1) + adjust_address_1(); + replace_reg_with_saved_mem_mem_1 ? fancy_abort() : 0; +} diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 27bb28365936978013a576b64b72d9e92375f361..da2dfa176ecd457ebc11d1131302ca15d77d779d 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -6223,7 +6223,13 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo, phi = create_phi_node (new_def, exit_bb); if (j) def = gimple_get_lhs (vec_stmts[j]); - SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); + if (LOOP_VINFO_IV_EXIT (loop_vinfo) == loop_exit) + SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def); + else + { + for (unsigned k = 0; k < gimple_phi_num_args (phi); k++) + SET_PHI_ARG_DEF (phi, k, def); + } new_def = gimple_convert (&stmts, vectype, new_def); reduc_inputs.quick_push (new_def); }