From 4c3ed795662974a1c2ad2326fc74bef608a34f31 Mon Sep 17 00:00:00 2001 From: Martin Andersson Date: Tue, 16 Apr 2013 18:02:00 +0400 Subject: r600g: Workaround for a harware bug with nested loops on Cayman There is a hardware bug on Cayman where a BREAK/CONTINUE followed by LOOP_STARTxxx for nested loops may put the branch stack into a state such that ALU_PUSH_BEFORE doesn't work as expected. Workaround this by replacing the ALU_PUSH_BEFORE with a PUSH + ALU Fixes piglit tests EXT_transform_feedback/order* v2: Use existing loop count and improve comment v3: [Vadim Girlin] Set jump address for PUSH instructions NOTE: This is a candidate for the 9.1 branch Signed-off-by: Vadim Girlin --- src/gallium/drivers/r600/r600_shader.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'src/gallium/drivers') diff --git a/src/gallium/drivers/r600/r600_shader.c b/src/gallium/drivers/r600/r600_shader.c index 6dbca505cbe..f3e21874653 100644 --- a/src/gallium/drivers/r600/r600_shader.c +++ b/src/gallium/drivers/r600/r600_shader.c @@ -5490,7 +5490,7 @@ static int tgsi_opdst(struct r600_shader_ctx *ctx) return 0; } -static int emit_logic_pred(struct r600_shader_ctx *ctx, int opcode) +static int emit_logic_pred(struct r600_shader_ctx *ctx, int opcode, int alu_type) { struct r600_bytecode_alu alu; int r; @@ -5510,7 +5510,7 @@ static int emit_logic_pred(struct r600_shader_ctx *ctx, int opcode) alu.last = 1; - r = r600_bytecode_add_alu_type(ctx->bc, &alu, CF_OP_ALU_PUSH_BEFORE); + r = r600_bytecode_add_alu_type(ctx->bc, &alu, alu_type); if (r) return r; return 0; @@ -5730,7 +5730,19 @@ static void break_loop_on_flag(struct r600_shader_ctx *ctx, unsigned fc_sp) static int tgsi_if(struct r600_shader_ctx *ctx) { - emit_logic_pred(ctx, ALU_OP2_PRED_SETNE_INT); + int alu_type = CF_OP_ALU_PUSH_BEFORE; + + /* There is a hardware bug on Cayman where a BREAK/CONTINUE followed by + * LOOP_STARTxxx for nested loops may put the branch stack into a state + * such that ALU_PUSH_BEFORE doesn't work as expected. Workaround this + * by replacing the ALU_PUSH_BEFORE with a PUSH + ALU */ + if (ctx->bc->chip_class == CAYMAN && ctx->bc->stack.loop > 1) { + r600_bytecode_add_cfinst(ctx->bc, CF_OP_PUSH); + ctx->bc->cf_last->cf_addr = ctx->bc->cf_last->id + 2; + alu_type = CF_OP_ALU; + } + + emit_logic_pred(ctx, ALU_OP2_PRED_SETNE_INT, alu_type); r600_bytecode_add_cfinst(ctx->bc, CF_OP_JUMP); -- cgit v1.2.3