From: Kenneth Graunke Date: Fri, 25 Sep 2015 06:47:29 +0000 (-0700) Subject: i965/gs: Allow src0 immediates in GS_OPCODE_SET_WRITE_OFFSET. X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=08fe5799e61e9251dec163d000709ff33434216d;p=mesa.git i965/gs: Allow src0 immediates in GS_OPCODE_SET_WRITE_OFFSET. GS_OPCODE_SET_WRITE_OFFSET is a MUL with a constant src[1] and special strides. We can easily make the generator handle constant src[0] arguments by instead generating a MOV with the product of both operands. This isn't necessarily a win in and of itself - instead of a MUL, we generate a MOV, which should be basically the same cost. However, we can probably avoid the earlier MOV to put src[0] into a register. shader-db statistics for geometry shaders only: total instructions in shared programs: 3207 -> 3173 (-1.06%) instructions in affected programs: 3207 -> 3173 (-1.06%) helped: 11 Signed-off-by: Kenneth Graunke Reviewed-by: Matt Turner --- diff --git a/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp index 5b6444e3210..610caef7dce 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp @@ -202,6 +202,13 @@ try_constant_propagate(const struct brw_device_info *devinfo, return true; } break; + case GS_OPCODE_SET_WRITE_OFFSET: + /* This is just a multiply by a constant with special strides. + * The generator will handle immediates in both arguments (generating + * a single MOV of the product). So feel free to propagate in src0. + */ + inst->src[arg] = value; + return true; case BRW_OPCODE_CMP: if (arg == 1) { diff --git a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp index 50f96632f7f..dcacc900540 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_generator.cpp @@ -541,8 +541,13 @@ vec4_generator::generate_gs_set_write_offset(struct brw_reg dst, src1.file == BRW_IMMEDIATE_VALUE && src1.type == BRW_REGISTER_TYPE_UD && src1.dw1.ud <= USHRT_MAX); - brw_MUL(p, suboffset(stride(dst, 2, 2, 1), 3), stride(src0, 8, 2, 4), - retype(src1, BRW_REGISTER_TYPE_UW)); + if (src0.file == IMM) { + brw_MOV(p, suboffset(stride(dst, 2, 2, 1), 3), + brw_imm_ud(src0.dw1.ud * src1.dw1.ud)); + } else { + brw_MUL(p, suboffset(stride(dst, 2, 2, 1), 3), stride(src0, 8, 2, 4), + retype(src1, BRW_REGISTER_TYPE_UW)); + } brw_set_default_access_mode(p, BRW_ALIGN_16); brw_pop_insn_state(p); }