From f1a9936ee1c7d2abe641eb785786c908c5ed799c Mon Sep 17 00:00:00 2001 From: Jose Maria Casanova Crespo Date: Sat, 1 Jul 2017 08:16:01 +0200 Subject: i965/fs: Add byte scattered write message and fs support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit v2: (Jason Ekstrand) - Enable bit_size parameter to scattered messages to enable different bitsizes byte/word/dword. - Remove use of brw_send_indirect_scattered_message in favor of brw_send_indirect_surface_message. - Move scattered messages to surface messages namespace. - Assert align1 for scattered messages and assume Gen8+. - Inline brw_set_dp_byte_scattered_write. v3: - Remove leftover newline (Topi Pohjolainen) - Rename brw_data_size to brw_scattered_data_element and use defines instead of an enum (Jason Ekstrand) - Assert scattered write for Gen8+ and Haswell (Jason Ekstrand) Signed-off-by: Jose Maria Casanova Crespo Signed-off-by: Alejandro Piñeiro Reviewed-by: Jason Ekstrand --- src/intel/compiler/brw_eu.h | 7 ++++ src/intel/compiler/brw_eu_defines.h | 20 ++++++++++++ src/intel/compiler/brw_eu_emit.c | 44 ++++++++++++++++++++++++++ src/intel/compiler/brw_fs.cpp | 14 ++++++++ src/intel/compiler/brw_fs_copy_propagation.cpp | 2 ++ src/intel/compiler/brw_fs_generator.cpp | 6 ++++ src/intel/compiler/brw_fs_surface_builder.cpp | 11 +++++++ src/intel/compiler/brw_fs_surface_builder.h | 7 ++++ src/intel/compiler/brw_shader.cpp | 7 ++++ 9 files changed, 118 insertions(+) (limited to 'src/intel/compiler') diff --git a/src/intel/compiler/brw_eu.h b/src/intel/compiler/brw_eu.h index 343dcd867db..3ac3b4342a9 100644 --- a/src/intel/compiler/brw_eu.h +++ b/src/intel/compiler/brw_eu.h @@ -485,6 +485,13 @@ brw_typed_surface_write(struct brw_codegen *p, unsigned msg_length, unsigned num_channels); +void +brw_byte_scattered_write(struct brw_codegen *p, + struct brw_reg payload, + struct brw_reg surface, + unsigned msg_length, + unsigned bit_size); + void brw_memory_fence(struct brw_codegen *p, struct brw_reg dst); diff --git a/src/intel/compiler/brw_eu_defines.h b/src/intel/compiler/brw_eu_defines.h index 9d5cf05c86e..14401982cd9 100644 --- a/src/intel/compiler/brw_eu_defines.h +++ b/src/intel/compiler/brw_eu_defines.h @@ -402,6 +402,16 @@ enum opcode { SHADER_OPCODE_RND_MODE, + /** + * Byte scattered write/read opcodes. + * + * LOGICAL opcodes are eventually translated to the matching non-LOGICAL + * opcode, but instead of taking a single payload blog they expect their + * arguments separately as individual sources, like untyped write/read. + */ + SHADER_OPCODE_BYTE_SCATTERED_WRITE, + SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL, + SHADER_OPCODE_MEMORY_FENCE, SHADER_OPCODE_GEN4_SCRATCH_READ, @@ -1255,4 +1265,14 @@ enum PACKED brw_rnd_mode { BRW_RND_MODE_UNSPECIFIED, /* Unspecified rounding mode */ }; +/* MDC_DS - Data Size Message Descriptor Control Field + * Skylake PRM, Volume 2d, page 129 + * + * Specifies the number of Bytes to be read or written per Dword used at + * byte_scattered read/write and byte_scaled read/write messages. + */ +#define GEN7_BYTE_SCATTERED_DATA_ELEMENT_BYTE 0 +#define GEN7_BYTE_SCATTERED_DATA_ELEMENT_WORD 1 +#define GEN7_BYTE_SCATTERED_DATA_ELEMENT_DWORD 2 + #endif /* BRW_EU_DEFINES_H */ diff --git a/src/intel/compiler/brw_eu_emit.c b/src/intel/compiler/brw_eu_emit.c index ca97ff7325e..bf9d3c945a9 100644 --- a/src/intel/compiler/brw_eu_emit.c +++ b/src/intel/compiler/brw_eu_emit.c @@ -2983,6 +2983,50 @@ brw_untyped_surface_write(struct brw_codegen *p, p, insn, num_channels); } +static unsigned +brw_byte_scattered_data_element_from_bit_size(unsigned bit_size) +{ + switch (bit_size) { + case 8: + return GEN7_BYTE_SCATTERED_DATA_ELEMENT_BYTE; + case 16: + return GEN7_BYTE_SCATTERED_DATA_ELEMENT_WORD; + case 32: + return GEN7_BYTE_SCATTERED_DATA_ELEMENT_DWORD; + default: + unreachable("Unsupported bit_size for byte scattered messages"); + } +} + +void +brw_byte_scattered_write(struct brw_codegen *p, + struct brw_reg payload, + struct brw_reg surface, + unsigned msg_length, + unsigned bit_size) +{ + const struct gen_device_info *devinfo = p->devinfo; + assert(devinfo->gen > 7 || devinfo->is_haswell); + assert(brw_inst_access_mode(devinfo, p->current) == BRW_ALIGN_1); + const unsigned sfid = GEN7_SFID_DATAPORT_DATA_CACHE; + + struct brw_inst *insn = brw_send_indirect_surface_message( + p, sfid, brw_writemask(brw_null_reg(), WRITEMASK_XYZW), + payload, surface, msg_length, 0, true); + + unsigned msg_control = + brw_byte_scattered_data_element_from_bit_size(bit_size) << 2; + + if (brw_inst_exec_size(devinfo, p->current) == BRW_EXECUTE_16) + msg_control |= 1; + else + msg_control |= 0; + + brw_inst_set_dp_msg_type(devinfo, insn, + HSW_DATAPORT_DC_PORT0_BYTE_SCATTERED_WRITE); + brw_inst_set_dp_msg_control(devinfo, insn, msg_control); +} + static void brw_set_dp_typed_atomic_message(struct brw_codegen *p, struct brw_inst *insn, diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp index 36fb337c620..32f1d757f0c 100644 --- a/src/intel/compiler/brw_fs.cpp +++ b/src/intel/compiler/brw_fs.cpp @@ -250,6 +250,7 @@ fs_inst::is_send_from_grf() const case SHADER_OPCODE_UNTYPED_ATOMIC: case SHADER_OPCODE_UNTYPED_SURFACE_READ: case SHADER_OPCODE_UNTYPED_SURFACE_WRITE: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: case SHADER_OPCODE_TYPED_ATOMIC: case SHADER_OPCODE_TYPED_SURFACE_READ: case SHADER_OPCODE_TYPED_SURFACE_WRITE: @@ -749,6 +750,11 @@ fs_inst::components_read(unsigned i) const else return 1; + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: + assert(src[3].file == IMM && + src[4].file == IMM); + return 1; + case SHADER_OPCODE_UNTYPED_ATOMIC_LOGICAL: case SHADER_OPCODE_TYPED_ATOMIC_LOGICAL: { assert(src[3].file == IMM && @@ -791,6 +797,7 @@ fs_inst::size_read(int arg) const case SHADER_OPCODE_TYPED_SURFACE_READ: case SHADER_OPCODE_TYPED_SURFACE_WRITE: case FS_OPCODE_INTERPOLATE_AT_PER_SLOT_OFFSET: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: if (arg == 0) return mlen * REG_SIZE; break; @@ -4538,6 +4545,12 @@ fs_visitor::lower_logical_sends() ibld.sample_mask_reg()); break; + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: + lower_surface_logical_send(ibld, inst, + SHADER_OPCODE_BYTE_SCATTERED_WRITE, + ibld.sample_mask_reg()); + break; + case SHADER_OPCODE_UNTYPED_ATOMIC_LOGICAL: lower_surface_logical_send(ibld, inst, SHADER_OPCODE_UNTYPED_ATOMIC, @@ -5022,6 +5035,7 @@ get_lowered_simd_width(const struct gen_device_info *devinfo, case SHADER_OPCODE_UNTYPED_ATOMIC_LOGICAL: case SHADER_OPCODE_UNTYPED_SURFACE_READ_LOGICAL: case SHADER_OPCODE_UNTYPED_SURFACE_WRITE_LOGICAL: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: return MIN2(16, inst->exec_size); case SHADER_OPCODE_URB_READ_SIMD8: diff --git a/src/intel/compiler/brw_fs_copy_propagation.cpp b/src/intel/compiler/brw_fs_copy_propagation.cpp index cb117396089..fcf4706b7ab 100644 --- a/src/intel/compiler/brw_fs_copy_propagation.cpp +++ b/src/intel/compiler/brw_fs_copy_propagation.cpp @@ -655,6 +655,7 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry) case SHADER_OPCODE_TYPED_ATOMIC: case SHADER_OPCODE_TYPED_SURFACE_READ: case SHADER_OPCODE_TYPED_SURFACE_WRITE: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: /* We only propagate into the surface argument of the * instruction. Everything else goes through LOAD_PAYLOAD. */ @@ -694,6 +695,7 @@ fs_visitor::try_constant_propagate(fs_inst *inst, acp_entry *entry) case SHADER_OPCODE_TYPED_ATOMIC_LOGICAL: case SHADER_OPCODE_TYPED_SURFACE_READ_LOGICAL: case SHADER_OPCODE_TYPED_SURFACE_WRITE_LOGICAL: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: inst->src[i] = val; progress = true; break; diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp index a5c39cc956b..92d1805f70d 100644 --- a/src/intel/compiler/brw_fs_generator.cpp +++ b/src/intel/compiler/brw_fs_generator.cpp @@ -2086,6 +2086,12 @@ fs_generator::generate_code(const cfg_t *cfg, int dispatch_width) inst->mlen, src[2].ud); break; + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: + assert(src[2].file == BRW_IMMEDIATE_VALUE); + brw_byte_scattered_write(p, src[0], src[1], + inst->mlen, src[2].ud); + break; + case SHADER_OPCODE_TYPED_ATOMIC: assert(src[2].file == BRW_IMMEDIATE_VALUE); brw_typed_atomic(p, dst, src[0], src[1], diff --git a/src/intel/compiler/brw_fs_surface_builder.cpp b/src/intel/compiler/brw_fs_surface_builder.cpp index d00d8920b2b..37cc29e361d 100644 --- a/src/intel/compiler/brw_fs_surface_builder.cpp +++ b/src/intel/compiler/brw_fs_surface_builder.cpp @@ -160,6 +160,16 @@ namespace brw { return emit_send(bld, SHADER_OPCODE_TYPED_ATOMIC_LOGICAL, addr, tmp, surface, dims, op, rsize); } + + void + emit_byte_scattered_write(const fs_builder &bld, const fs_reg &surface, + const fs_reg &addr, const fs_reg &src, + unsigned dims, unsigned size, + unsigned bit_size, brw_predicate pred) + { + emit_send(bld, SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL, + addr, src, surface, dims, bit_size, 0, pred); + } } } @@ -1192,3 +1202,4 @@ namespace brw { } } } + diff --git a/src/intel/compiler/brw_fs_surface_builder.h b/src/intel/compiler/brw_fs_surface_builder.h index 32b56d387f6..bf9a8c68c8d 100644 --- a/src/intel/compiler/brw_fs_surface_builder.h +++ b/src/intel/compiler/brw_fs_surface_builder.h @@ -63,6 +63,13 @@ namespace brw { const fs_reg &src0, const fs_reg &src1, unsigned dims, unsigned rsize, unsigned op, brw_predicate pred = BRW_PREDICATE_NONE); + + void + emit_byte_scattered_write(const fs_builder &bld, const fs_reg &surface, + const fs_reg &addr, const fs_reg &src, + unsigned dims, unsigned size, + unsigned bit_size, + brw_predicate pred = BRW_PREDICATE_NONE); } namespace image_access { diff --git a/src/intel/compiler/brw_shader.cpp b/src/intel/compiler/brw_shader.cpp index d7d7616cf4f..209552e1b29 100644 --- a/src/intel/compiler/brw_shader.cpp +++ b/src/intel/compiler/brw_shader.cpp @@ -293,6 +293,11 @@ brw_instruction_name(const struct gen_device_info *devinfo, enum opcode op) case SHADER_OPCODE_MEMORY_FENCE: return "memory_fence"; + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: + return "byte_scattered_write"; + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: + return "byte_scattered_write_logical"; + case SHADER_OPCODE_LOAD_PAYLOAD: return "load_payload"; case FS_OPCODE_PACK: @@ -963,6 +968,8 @@ backend_instruction::has_side_effects() const case SHADER_OPCODE_GEN4_SCRATCH_WRITE: case SHADER_OPCODE_UNTYPED_SURFACE_WRITE: case SHADER_OPCODE_UNTYPED_SURFACE_WRITE_LOGICAL: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE: + case SHADER_OPCODE_BYTE_SCATTERED_WRITE_LOGICAL: case SHADER_OPCODE_TYPED_ATOMIC: case SHADER_OPCODE_TYPED_ATOMIC_LOGICAL: case SHADER_OPCODE_TYPED_SURFACE_WRITE: -- cgit v1.2.3