It can do 32-bit packing too now.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
progress = false;
NIR_PASS_V(shader, nir_lower_vars_to_ssa);
- NIR_PASS_V(shader, nir_lower_64bit_pack);
+ NIR_PASS_V(shader, nir_lower_pack);
NIR_PASS_V(shader, nir_lower_alu_to_scalar);
NIR_PASS_V(shader, nir_lower_phis_to_scalar);
nir/nir_liveness.c \
nir/nir_loop_analyze.c \
nir/nir_loop_analyze.h \
- nir/nir_lower_64bit_packing.c \
nir/nir_lower_alpha_test.c \
nir/nir_lower_alu_to_scalar.c \
nir/nir_lower_atomics_to_ssbo.c \
nir/nir_lower_io_to_temporaries.c \
nir/nir_lower_io_to_scalar.c \
nir/nir_lower_io_types.c \
+ nir/nir_lower_packing.c \
nir/nir_lower_passthrough_edgeflags.c \
nir/nir_lower_patch_vertices.c \
nir/nir_lower_phis_to_scalar.c \
'nir_liveness.c',
'nir_loop_analyze.c',
'nir_loop_analyze.h',
- 'nir_lower_64bit_packing.c',
'nir_lower_alu_to_scalar.c',
'nir_lower_alpha_test.c',
'nir_lower_atomics_to_ssbo.c',
'nir_lower_io_to_temporaries.c',
'nir_lower_io_to_scalar.c',
'nir_lower_io_types.c',
+ 'nir_lower_packing.c',
'nir_lower_passthrough_edgeflags.c',
'nir_lower_patch_vertices.c',
'nir_lower_phis_to_scalar.c',
} nir_lower_doubles_options;
bool nir_lower_doubles(nir_shader *shader, nir_lower_doubles_options options);
-bool nir_lower_64bit_pack(nir_shader *shader);
+bool nir_lower_pack(nir_shader *shader);
bool nir_normalize_cubemap_coords(nir_shader *shader);
+++ /dev/null
-/*
- * Copyright © 2015 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- */
-
-#include "nir.h"
-#include "nir_builder.h"
-
-/*
- * lowers:
- *
- * packDouble2x32(foo) -> packDouble2x32Split(foo.x, foo.y)
- * unpackDouble2x32(foo) -> vec2(unpackDouble2x32_x(foo), unpackDouble2x32_y(foo))
- * packInt2x32(foo) -> packInt2x32Split(foo.x, foo.y)
- * unpackInt2x32(foo) -> vec2(unpackInt2x32_x(foo), unpackInt2x32_y(foo))
- */
-
-static nir_ssa_def *
-lower_pack_64_from_32(nir_builder *b, nir_ssa_def *src)
-{
- return nir_pack_64_2x32_split(b, nir_channel(b, src, 0),
- nir_channel(b, src, 1));
-}
-
-static nir_ssa_def *
-lower_unpack_64_to_32(nir_builder *b, nir_ssa_def *src)
-{
- return nir_vec2(b, nir_unpack_64_2x32_split_x(b, src),
- nir_unpack_64_2x32_split_y(b, src));
-}
-
-static nir_ssa_def *
-lower_pack_32_from_16(nir_builder *b, nir_ssa_def *src)
-{
- return nir_pack_32_2x16_split(b, nir_channel(b, src, 0),
- nir_channel(b, src, 1));
-}
-
-static nir_ssa_def *
-lower_unpack_32_to_16(nir_builder *b, nir_ssa_def *src)
-{
- return nir_vec2(b, nir_unpack_32_2x16_split_x(b, src),
- nir_unpack_32_2x16_split_y(b, src));
-}
-
-static nir_ssa_def *
-lower_pack_64_from_16(nir_builder *b, nir_ssa_def *src)
-{
- nir_ssa_def *xy = nir_pack_32_2x16_split(b, nir_channel(b, src, 0),
- nir_channel(b, src, 1));
-
- nir_ssa_def *zw = nir_pack_32_2x16_split(b, nir_channel(b, src, 2),
- nir_channel(b, src, 3));
-
- return nir_pack_64_2x32_split(b, xy, zw);
-}
-
-static nir_ssa_def *
-lower_unpack_64_to_16(nir_builder *b, nir_ssa_def *src)
-{
- nir_ssa_def *xy = nir_unpack_64_2x32_split_x(b, src);
- nir_ssa_def *zw = nir_unpack_64_2x32_split_y(b, src);
-
- return nir_vec4(b, nir_unpack_32_2x16_split_x(b, xy),
- nir_unpack_32_2x16_split_y(b, xy),
- nir_unpack_32_2x16_split_x(b, zw),
- nir_unpack_32_2x16_split_y(b, zw));
-}
-
-static bool
-lower_64bit_pack_impl(nir_function_impl *impl)
-{
- nir_builder b;
- nir_builder_init(&b, impl);
- bool progress = false;
-
- nir_foreach_block(block, impl) {
- nir_foreach_instr_safe(instr, block) {
- if (instr->type != nir_instr_type_alu)
- continue;
-
- nir_alu_instr *alu_instr = (nir_alu_instr *) instr;
-
- if (alu_instr->op != nir_op_pack_64_2x32 &&
- alu_instr->op != nir_op_unpack_64_2x32 &&
- alu_instr->op != nir_op_pack_64_4x16 &&
- alu_instr->op != nir_op_unpack_64_4x16 &&
- alu_instr->op != nir_op_pack_32_2x16 &&
- alu_instr->op != nir_op_unpack_32_2x16)
- continue;
-
- b.cursor = nir_before_instr(&alu_instr->instr);
-
- nir_ssa_def *src = nir_ssa_for_alu_src(&b, alu_instr, 0);
- nir_ssa_def *dest;
-
- switch (alu_instr->op) {
- case nir_op_pack_64_2x32:
- dest = lower_pack_64_from_32(&b, src);
- break;
- case nir_op_unpack_64_2x32:
- dest = lower_unpack_64_to_32(&b, src);
- break;
- case nir_op_pack_64_4x16:
- dest = lower_pack_64_from_16(&b, src);
- break;
- case nir_op_unpack_64_4x16:
- dest = lower_unpack_64_to_16(&b, src);
- break;
- case nir_op_pack_32_2x16:
- dest = lower_pack_32_from_16(&b, src);
- break;
- case nir_op_unpack_32_2x16:
- dest = lower_unpack_32_to_16(&b, src);
- break;
- default:
- unreachable("Impossible opcode");
- }
-
- nir_ssa_def_rewrite_uses(&alu_instr->dest.dest.ssa, nir_src_for_ssa(dest));
- nir_instr_remove(&alu_instr->instr);
- nir_metadata_preserve(impl, nir_metadata_block_index |
- nir_metadata_dominance);
- progress = true;
- }
- }
-
- return progress;
-}
-
-bool
-nir_lower_64bit_pack(nir_shader *shader)
-{
- bool progress = false;
-
- nir_foreach_function(function, shader) {
- if (function->impl)
- progress |= lower_64bit_pack_impl(function->impl);
- }
-
- return false;
-}
--- /dev/null
+/*
+ * Copyright © 2015 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include "nir.h"
+#include "nir_builder.h"
+
+/*
+ * lowers:
+ *
+ * packDouble2x32(foo) -> packDouble2x32Split(foo.x, foo.y)
+ * unpackDouble2x32(foo) -> vec2(unpackDouble2x32_x(foo), unpackDouble2x32_y(foo))
+ * packInt2x32(foo) -> packInt2x32Split(foo.x, foo.y)
+ * unpackInt2x32(foo) -> vec2(unpackInt2x32_x(foo), unpackInt2x32_y(foo))
+ */
+
+static nir_ssa_def *
+lower_pack_64_from_32(nir_builder *b, nir_ssa_def *src)
+{
+ return nir_pack_64_2x32_split(b, nir_channel(b, src, 0),
+ nir_channel(b, src, 1));
+}
+
+static nir_ssa_def *
+lower_unpack_64_to_32(nir_builder *b, nir_ssa_def *src)
+{
+ return nir_vec2(b, nir_unpack_64_2x32_split_x(b, src),
+ nir_unpack_64_2x32_split_y(b, src));
+}
+
+static nir_ssa_def *
+lower_pack_32_from_16(nir_builder *b, nir_ssa_def *src)
+{
+ return nir_pack_32_2x16_split(b, nir_channel(b, src, 0),
+ nir_channel(b, src, 1));
+}
+
+static nir_ssa_def *
+lower_unpack_32_to_16(nir_builder *b, nir_ssa_def *src)
+{
+ return nir_vec2(b, nir_unpack_32_2x16_split_x(b, src),
+ nir_unpack_32_2x16_split_y(b, src));
+}
+
+static nir_ssa_def *
+lower_pack_64_from_16(nir_builder *b, nir_ssa_def *src)
+{
+ nir_ssa_def *xy = nir_pack_32_2x16_split(b, nir_channel(b, src, 0),
+ nir_channel(b, src, 1));
+
+ nir_ssa_def *zw = nir_pack_32_2x16_split(b, nir_channel(b, src, 2),
+ nir_channel(b, src, 3));
+
+ return nir_pack_64_2x32_split(b, xy, zw);
+}
+
+static nir_ssa_def *
+lower_unpack_64_to_16(nir_builder *b, nir_ssa_def *src)
+{
+ nir_ssa_def *xy = nir_unpack_64_2x32_split_x(b, src);
+ nir_ssa_def *zw = nir_unpack_64_2x32_split_y(b, src);
+
+ return nir_vec4(b, nir_unpack_32_2x16_split_x(b, xy),
+ nir_unpack_32_2x16_split_y(b, xy),
+ nir_unpack_32_2x16_split_x(b, zw),
+ nir_unpack_32_2x16_split_y(b, zw));
+}
+
+static bool
+lower_pack_impl(nir_function_impl *impl)
+{
+ nir_builder b;
+ nir_builder_init(&b, impl);
+ bool progress = false;
+
+ nir_foreach_block(block, impl) {
+ nir_foreach_instr_safe(instr, block) {
+ if (instr->type != nir_instr_type_alu)
+ continue;
+
+ nir_alu_instr *alu_instr = (nir_alu_instr *) instr;
+
+ if (alu_instr->op != nir_op_pack_64_2x32 &&
+ alu_instr->op != nir_op_unpack_64_2x32 &&
+ alu_instr->op != nir_op_pack_64_4x16 &&
+ alu_instr->op != nir_op_unpack_64_4x16 &&
+ alu_instr->op != nir_op_pack_32_2x16 &&
+ alu_instr->op != nir_op_unpack_32_2x16)
+ continue;
+
+ b.cursor = nir_before_instr(&alu_instr->instr);
+
+ nir_ssa_def *src = nir_ssa_for_alu_src(&b, alu_instr, 0);
+ nir_ssa_def *dest;
+
+ switch (alu_instr->op) {
+ case nir_op_pack_64_2x32:
+ dest = lower_pack_64_from_32(&b, src);
+ break;
+ case nir_op_unpack_64_2x32:
+ dest = lower_unpack_64_to_32(&b, src);
+ break;
+ case nir_op_pack_64_4x16:
+ dest = lower_pack_64_from_16(&b, src);
+ break;
+ case nir_op_unpack_64_4x16:
+ dest = lower_unpack_64_to_16(&b, src);
+ break;
+ case nir_op_pack_32_2x16:
+ dest = lower_pack_32_from_16(&b, src);
+ break;
+ case nir_op_unpack_32_2x16:
+ dest = lower_unpack_32_to_16(&b, src);
+ break;
+ default:
+ unreachable("Impossible opcode");
+ }
+
+ nir_ssa_def_rewrite_uses(&alu_instr->dest.dest.ssa, nir_src_for_ssa(dest));
+ nir_instr_remove(&alu_instr->instr);
+ nir_metadata_preserve(impl, nir_metadata_block_index |
+ nir_metadata_dominance);
+ progress = true;
+ }
+ }
+
+ return progress;
+}
+
+bool
+nir_lower_pack(nir_shader *shader)
+{
+ bool progress = false;
+
+ nir_foreach_function(function, shader) {
+ if (function->impl)
+ progress |= lower_pack_impl(function->impl);
+ }
+
+ return false;
+}
nir_lower_dfract |
nir_lower_dround_even |
nir_lower_dmod);
- OPT(nir_lower_64bit_pack);
+ OPT(nir_lower_pack);
} while (progress);
return nir;
NIR_PASS_V(nir, nir_lower_alu_to_scalar);
NIR_PASS_V(nir, nir_lower_phis_to_scalar);
- NIR_PASS_V(nir, nir_lower_64bit_pack);
+ NIR_PASS_V(nir, nir_lower_pack);
NIR_PASS(progress, nir, nir_copy_prop);
NIR_PASS(progress, nir, nir_opt_remove_phis);
NIR_PASS(progress, nir, nir_opt_dce);
projects / mesa.git / commitdiff