From 8620f7ebbc763dc1bbbc825d31cacfdd84433e05 Mon Sep 17 00:00:00 2001 From: Iago Toral Quiroga Date: Wed, 29 Nov 2017 10:50:42 +0100 Subject: [PATCH] i965/vec4: use a temp register to compute offsets for pull loads 64-bit pull loads are implemented by emitting 2 separate 32-bit pull load messages, where the second message loads from an offset at +16B. That addition of 16B to the original offset should not alter the original offset register used as source for the pull load instruction though, since the compiler might use that same offset register in other instructions (for example, for other pull loads in the shader code that take that same offset as reference). If the pull load is 32-bit then we only need to emit one message and we don't need to do offset calculations, but in that case the optimizer should be able to drop the redundant MOV. Fixes the following test on Haswell: KHR-GL45.gpu_shader_fp64.fp64.max_uniform_components Reviewed-by: Matt Turner Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103007 --- src/intel/compiler/brw_vec4_nir.cpp | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/intel/compiler/brw_vec4_nir.cpp b/src/intel/compiler/brw_vec4_nir.cpp index c4ea24b8db7..4ff3ef9927e 100644 --- a/src/intel/compiler/brw_vec4_nir.cpp +++ b/src/intel/compiler/brw_vec4_nir.cpp @@ -842,7 +842,9 @@ vec4_visitor::nir_emit_intrinsic(nir_intrinsic_instr *instr) if (const_offset) { offset_reg = brw_imm_ud(const_offset->u32[0] & ~15); } else { - offset_reg = get_nir_src(instr->src[1], nir_type_uint32, 1); + offset_reg = src_reg(this, glsl_type::uint_type); + emit(MOV(dst_reg(offset_reg), + get_nir_src(instr->src[1], nir_type_uint32, 1))); } src_reg packed_consts; -- 2.30.2