| # RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32 -run-pass=si-optimize-exec-masking -verify-machineinstrs %s -o - | FileCheck --check-prefixes=GCN,WAVE32 %s |
| # RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -run-pass=si-optimize-exec-masking -verify-machineinstrs %s -o - | FileCheck --check-prefixes=GCN,WAVE64 %s |
| |
| --- |
| |
| # After the Optimize exec masking (post-RA) pass, codegen can end up with the following sequence: |
| # s_or_saveexec_b32 s0, s0 |
| # s_xor_b32 exec_lo, exec_lo, s0 |
| # |
| # This can be combined into one instruction: |
| # s_andn2_saveexec_b32 s0, s0 |
| |
| # Ensure the transformation gets applied in the b32 case. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32 |
| # WAVE32: S_ANDN2_SAVEEXEC_B32 |
| name: s_or_saveexec_xor_combine_b32 |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |
| $exec_lo = S_XOR_B32 $exec_lo, renamable $sgpr0, implicit-def $scc |
| ... |
| |
| --- |
| |
| # Ensure the transformation gets applied in the b64 case. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b64 |
| # WAVE64: S_ANDN2_SAVEEXEC_B64 |
| name: s_or_saveexec_xor_combine_b64 |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0_sgpr1 |
| renamable $sgpr0_sgpr1 = S_OR_SAVEEXEC_B64 killed renamable $sgpr0_sgpr1, implicit-def $exec, implicit-def $scc, implicit $exec |
| $exec = S_XOR_B64 $exec, renamable $sgpr0_sgpr1, implicit-def $scc |
| ... |
| |
| --- |
| |
| # Ensure the transformation does get applied even if the operands are swapped. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_swap |
| # WAVE32: S_ANDN2_SAVEEXEC_B32 |
| name: s_or_saveexec_xor_combine_b32_swap |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |
| $exec_lo = S_XOR_B32 renamable $sgpr0, $exec_lo, implicit-def $scc |
| ... |
| |
| --- |
| |
| # Ensure the transformation does get applied if source and dest operand for s_or_saveeexec are not equal. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_inequal_operands |
| # WAVE32: S_ANDN2_SAVEEXEC |
| name: s_or_saveexec_xor_combine_b32_inequal_operands |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0, $sgpr1 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr1, implicit-def $exec, implicit-def $scc, implicit $exec |
| $exec_lo = S_XOR_B32 $exec_lo, renamable $sgpr0, implicit-def $scc |
| ... |
| |
| --- |
| |
| # Ensure the transformation does not get applied if s_xor does not use the dest as input operand. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_wrong_input |
| # WAVE32: S_OR_SAVEEXEC |
| # WAVE32: S_XOR_B32 |
| name: s_or_saveexec_xor_combine_b32_wrong_input |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0, $sgpr1 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |
| $exec_lo = S_XOR_B32 $exec_lo, renamable $sgpr1, implicit-def $scc |
| ... |
| |
| --- |
| |
| |
| # Ensure the transformation does not get applied if the instructions don't appear sequentially. |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_non_sequence |
| # WAVE32: S_OR_SAVEEXEC |
| # WAVE32: S_MOV_B32 |
| # WAVE32: S_XOR_B32 |
| name: s_or_saveexec_xor_combine_b32_non_sequence |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0, $sgpr1 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |
| renamable $sgpr1 = S_MOV_B32 renamable $sgpr0 |
| $exec_lo = S_XOR_B32 $exec_lo, renamable $sgpr1, implicit-def $scc |
| ... |
| |
| --- |
| |
| # Don't apply the transformation if the basic block only has a single instruction. |
| |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_last_inst |
| # WAVE32: S_OR_SAVEEXEC |
| name: s_or_saveexec_xor_combine_b32_last_inst |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |
| ... |
| |
| --- |
| |
| # Don't apply the transformation if the basic block ends with an S_OR_SAVEEXEC_B32 instruction. |
| |
| # GCN-LABEL: name: s_or_saveexec_xor_combine_b32_or_saveexec_terminator |
| # WAVE32: S_MOV_B32 |
| # WAVE32: S_OR_SAVEEXEC |
| name: s_or_saveexec_xor_combine_b32_or_saveexec_terminator |
| tracksRegLiveness: true |
| body: | |
| bb.0: |
| liveins: $sgpr0, $sgpr1 |
| renamable $sgpr1 = S_MOV_B32 renamable $sgpr0 |
| renamable $sgpr0 = S_OR_SAVEEXEC_B32 killed renamable $sgpr0, implicit-def $exec, implicit-def $scc, implicit $exec |