From: Jason Ekstrand Date: Wed, 3 Oct 2018 17:14:20 +0000 (-0500) Subject: nir/alu_to_scalar: Use ssa_for_alu_src in hand-rolled expansions X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=dd553bc67f8ab1513fd196b6ffb7c4a76723adfd;p=mesa.git nir/alu_to_scalar: Use ssa_for_alu_src in hand-rolled expansions The ssa_for_alu_src helper will correctly handle swizzles and other source modifiers for you. The expansions for unpack_half_2x16, pack_uvec2_to_uint, and pack_uvec4_to_uint were all broken with regards to swizzles. The brokenness of unpack_half_2x16 was causing rendering errors in Rise of the Tomb Raider on Intel ever since c11833ab24dcba26 which added an extra copy propagation to the optimization pipeline and caused us to start seeing swizzles where we hadn't seen any before. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107926 Fixes: 9ce901058f3d "nir: Add lowering of nir_op_unpack_half_2x16." Fixes: 9b8786eba955 "nir: Add lowering support for packing opcodes." Tested-by: Alex Smith Tested-by: Józef Kucia Reviewed-by: Matt Turner --- diff --git a/src/compiler/nir/nir_lower_alu_to_scalar.c b/src/compiler/nir/nir_lower_alu_to_scalar.c index 742c8d8ee66..0be3aba9456 100644 --- a/src/compiler/nir/nir_lower_alu_to_scalar.c +++ b/src/compiler/nir/nir_lower_alu_to_scalar.c @@ -107,11 +107,11 @@ lower_alu_instr_scalar(nir_alu_instr *instr, nir_builder *b) if (!b->shader->options->lower_pack_half_2x16) return false; + nir_ssa_def *src_vec2 = nir_ssa_for_alu_src(b, instr, 0); + nir_ssa_def *val = - nir_pack_half_2x16_split(b, nir_channel(b, instr->src[0].src.ssa, - instr->src[0].swizzle[0]), - nir_channel(b, instr->src[0].src.ssa, - instr->src[0].swizzle[1])); + nir_pack_half_2x16_split(b, nir_channel(b, src_vec2, 0), + nir_channel(b, src_vec2, 1)); nir_ssa_def_rewrite_uses(&instr->dest.dest.ssa, nir_src_for_ssa(val)); nir_instr_remove(&instr->instr); @@ -130,9 +130,11 @@ lower_alu_instr_scalar(nir_alu_instr *instr, nir_builder *b) if (!b->shader->options->lower_unpack_half_2x16) return false; + nir_ssa_def *packed = nir_ssa_for_alu_src(b, instr, 0); + nir_ssa_def *comps[2]; - comps[0] = nir_unpack_half_2x16_split_x(b, instr->src[0].src.ssa); - comps[1] = nir_unpack_half_2x16_split_y(b, instr->src[0].src.ssa); + comps[0] = nir_unpack_half_2x16_split_x(b, packed); + comps[1] = nir_unpack_half_2x16_split_y(b, packed); nir_ssa_def *vec = nir_vec(b, comps, 2); nir_ssa_def_rewrite_uses(&instr->dest.dest.ssa, nir_src_for_ssa(vec)); @@ -144,8 +146,8 @@ lower_alu_instr_scalar(nir_alu_instr *instr, nir_builder *b) assert(b->shader->options->lower_pack_snorm_2x16 || b->shader->options->lower_pack_unorm_2x16); - nir_ssa_def *word = - nir_extract_u16(b, instr->src[0].src.ssa, nir_imm_int(b, 0)); + nir_ssa_def *word = nir_extract_u16(b, nir_ssa_for_alu_src(b, instr, 0), + nir_imm_int(b, 0)); nir_ssa_def *val = nir_ior(b, nir_ishl(b, nir_channel(b, word, 1), nir_imm_int(b, 16)), nir_channel(b, word, 0)); @@ -159,8 +161,8 @@ lower_alu_instr_scalar(nir_alu_instr *instr, nir_builder *b) assert(b->shader->options->lower_pack_snorm_4x8 || b->shader->options->lower_pack_unorm_4x8); - nir_ssa_def *byte = - nir_extract_u8(b, instr->src[0].src.ssa, nir_imm_int(b, 0)); + nir_ssa_def *byte = nir_extract_u8(b, nir_ssa_for_alu_src(b, instr, 0), + nir_imm_int(b, 0)); nir_ssa_def *val = nir_ior(b, nir_ior(b, nir_ishl(b, nir_channel(b, byte, 3), nir_imm_int(b, 24)), nir_ishl(b, nir_channel(b, byte, 2), nir_imm_int(b, 16))), @@ -173,14 +175,15 @@ lower_alu_instr_scalar(nir_alu_instr *instr, nir_builder *b) } case nir_op_fdph: { + nir_ssa_def *src0_vec = nir_ssa_for_alu_src(b, instr, 0); + nir_ssa_def *src1_vec = nir_ssa_for_alu_src(b, instr, 1); + nir_ssa_def *sum[4]; for (unsigned i = 0; i < 3; i++) { - sum[i] = nir_fmul(b, nir_channel(b, instr->src[0].src.ssa, - instr->src[0].swizzle[i]), - nir_channel(b, instr->src[1].src.ssa, - instr->src[1].swizzle[i])); + sum[i] = nir_fmul(b, nir_channel(b, src0_vec, i), + nir_channel(b, src1_vec, i)); } - sum[3] = nir_channel(b, instr->src[1].src.ssa, instr->src[1].swizzle[3]); + sum[3] = nir_channel(b, src1_vec, 3); nir_ssa_def *val = nir_fadd(b, nir_fadd(b, sum[0], sum[1]), nir_fadd(b, sum[2], sum[3]));