From 81deefc45ba7b7d3b2b5e7ccf9e1680df6e31e3a Mon Sep 17 00:00:00 2001 From: Matt Turner Date: Thu, 14 May 2015 22:23:22 -0700 Subject: [PATCH] i965/fs: Unrestrict constant propagation into integer multiply. Gen8+'s MUL instruction doesn't ignore the high 16-bits of one source like on earlier platforms, so we can constant propagate into it without worry. Integer multiplies (not into the accumulator, which is done for imul_high) are lowered in lower_integer_multiplication(), so it's safe there as well. On Broadwell, fragment shaders only: total instructions in shared programs: 4377769 -> 4377451 (-0.01%) instructions in affected programs: 48064 -> 47746 (-0.66%) helped: 156 On Broadwell, vertex shaders only: total instructions in shared programs: 2858885 -> 2856313 (-0.09%) instructions in affected programs: 26380 -> 23808 (-9.75%) helped: 134 On Broadwell, vertex shaders only (with INTEL_USE_NIR=1): total instructions in shared programs: 2911688 -> 2865984 (-1.57%) instructions in affected programs: 1421715 -> 1376011 (-3.21%) helped: 6186 Reviewed-by: Jason Ekstrand --- src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp index 52bfa921dc3..c92aae4b1d6 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp @@ -541,8 +541,16 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry) /* Fit this constant in by commuting the operands. * Exception: we can't do this for 32-bit integer MUL/MACH * because it's asymmetric. + * + * The BSpec says for Broadwell that + * + * "When multiplying DW x DW, the dst cannot be accumulator." + * + * Integer MUL with a non-accumulator destination will be lowered + * by lower_integer_multiplication(), so don't restrict it. */ - if ((inst->opcode == BRW_OPCODE_MUL || + if (((inst->opcode == BRW_OPCODE_MUL && + inst->dst.is_accumulator()) || inst->opcode == BRW_OPCODE_MACH) && (inst->src[1].type == BRW_REGISTER_TYPE_D || inst->src[1].type == BRW_REGISTER_TYPE_UD)) -- 2.30.2