From 8902c42db4fd72568cfa071987cfa10e7a366c2e Mon Sep 17 00:00:00 2001 From: José Fonseca Date: Thu, 17 Feb 2011 09:48:17 +0000 Subject: mesa: Do copy propagation across if-else-endif. Addresses excessive TEMP allocation in vertex shaders where all CONSTs are stored into TEMPS at the start, but copy propagation was failing due to the presence of IFs. We could do something about loops, but ifs are easy enough. --- src/mesa/program/ir_to_mesa.cpp | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/src/mesa/program/ir_to_mesa.cpp b/src/mesa/program/ir_to_mesa.cpp index 7f905ae5ce..33c262f8ca 100644 --- a/src/mesa/program/ir_to_mesa.cpp +++ b/src/mesa/program/ir_to_mesa.cpp @@ -2670,6 +2670,8 @@ ir_to_mesa_visitor::copy_propagate(void) ir_to_mesa_instruction **acp = rzalloc_array(mem_ctx, ir_to_mesa_instruction *, this->next_temp * 4); + int *acp_level = rzalloc_array(mem_ctx, int, this->next_temp * 4); + int level = 0; foreach_iter(exec_list_iterator, iter, this->instructions) { ir_to_mesa_instruction *inst = (ir_to_mesa_instruction *)iter.get(); @@ -2700,6 +2702,8 @@ ir_to_mesa_visitor::copy_propagate(void) break; } + assert(acp_level[acp_base + src_chan] <= level); + if (!first) { first = copy_chan; } else { @@ -2732,12 +2736,32 @@ ir_to_mesa_visitor::copy_propagate(void) switch (inst->op) { case OPCODE_BGNLOOP: case OPCODE_ENDLOOP: - case OPCODE_ELSE: - case OPCODE_ENDIF: /* End of a basic block, clear the ACP entirely. */ memset(acp, 0, sizeof(*acp) * this->next_temp * 4); break; + case OPCODE_IF: + ++level; + break; + + case OPCODE_ENDIF: + case OPCODE_ELSE: + /* Clear all channels written inside the block from the ACP, but + * leaving those that were not touched. + */ + for (int r = 0; r < this->next_temp; r++) { + for (int c = 0; c < 4; c++) { + if (!acp[4 * r + c]) + continue; + + if (acp_level[4 * r + c] >= level) + acp[4 * r + c] = NULL; + } + } + if (inst->op == OPCODE_ENDIF) + --level; + break; + default: /* Continuing the block, clear any written channels from * the ACP. @@ -2802,11 +2826,13 @@ ir_to_mesa_visitor::copy_propagate(void) for (int i = 0; i < 4; i++) { if (inst->dst_reg.writemask & (1 << i)) { acp[4 * inst->dst_reg.index + i] = inst; + acp_level[4 * inst->dst_reg.index + i] = level; } } } } + ralloc_free(acp_level); ralloc_free(acp); } -- cgit v1.2.3