diff options
| author | Daniel Schürmann <daniel@schuermann.dev> | 2020-05-07 18:19:54 +0100 |
|---|---|---|
| committer | Marge Bot <eric+marge@anholt.net> | 2020-05-12 15:59:31 +0000 |
| commit | a5fc96b533418dc2d68f17f3f19ac5f82d59b978 (patch) | |
| tree | c2aa4c70444bfac0f1e5a273cb3276aa73d8439d | |
| parent | 38cc649fcb54baf87a974ca2dc29d92b50c86cfa (diff) | |
aco: coalesce parallelcopies during register allocation
These are the result of lowering to CSSA, and should be removed if possible
Totals from affected shaders: (VEGA)
SGPRS: 544544 -> 544544 (0.00 %)
VGPRS: 418224 -> 418224 (0.00 %)
Spilled SGPRs: 141826 -> 141826 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 65853740 -> 64703380 (-1.75 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 13669 -> 13669 (0.00 %)
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4952>
| -rw-r--r-- | src/amd/compiler/aco_register_allocation.cpp | 9 |
1 files changed, 3 insertions, 6 deletions
diff --git a/src/amd/compiler/aco_register_allocation.cpp b/src/amd/compiler/aco_register_allocation.cpp index 8d6971e1c4d..318e29b9cf3 100644 --- a/src/amd/compiler/aco_register_allocation.cpp +++ b/src/amd/compiler/aco_register_allocation.cpp @@ -1837,13 +1837,10 @@ void register_allocation(Program *program, std::vector<TempSet>& live_out_per_bl reg.reg_b += instr->definitions[j].bytes(); if (get_reg_specified(ctx, register_file, definition.regClass(), parallelcopy, instr, reg)) definition.setFixed(reg); - } else if (instr->opcode == aco_opcode::p_wqm) { - PhysReg reg; - if (instr->operands[0].isKillBeforeDef() && instr->operands[0].getTemp().type() == definition.getTemp().type()) { - reg = instr->operands[0].physReg(); + } else if (instr->opcode == aco_opcode::p_wqm || instr->opcode == aco_opcode::p_parallelcopy) { + PhysReg reg = instr->operands[i].physReg(); + if (get_reg_specified(ctx, register_file, definition.regClass(), parallelcopy, instr, reg)) definition.setFixed(reg); - assert(register_file[reg.reg()] == 0); - } } else if (instr->opcode == aco_opcode::p_extract_vector) { PhysReg reg; if (instr->operands[0].isKillBeforeDef() && |