--- src/gallium/auxiliary/Makefile | 1 + src/gallium/auxiliary/util/u_linkage.c | 119 ++++++++++++++++++++++++++++++++ src/gallium/auxiliary/util/u_linkage.h | 38 ++++++++++ 3 files changed, 158 insertions(+), 0 deletions(-) create mode 100644 src/gallium/auxiliary/util/u_linkage.c create mode 100644 src/gallium/auxiliary/util/u_linkage.h
diff --git a/src/gallium/auxiliary/Makefile b/src/gallium/auxiliary/Makefile index c4d6b52..44c2f8b 100644 --- a/src/gallium/auxiliary/Makefile +++ b/src/gallium/auxiliary/Makefile @@ -120,6 +120,7 @@ C_SOURCES = \ util/u_hash.c \ util/u_keymap.c \ util/u_linear.c \ + util/u_linkage.c \ util/u_network.c \ util/u_math.c \ util/u_mm.c \ diff --git a/src/gallium/auxiliary/util/u_linkage.c b/src/gallium/auxiliary/util/u_linkage.c new file mode 100644 index 0000000..8a76378 --- /dev/null +++ b/src/gallium/auxiliary/util/u_linkage.c @@ -0,0 +1,119 @@ +#include "util/u_debug.h" +#include "pipe/p_shader_tokens.h" +#include "tgsi/tgsi_parse.h" +#include "tgsi/tgsi_scan.h" +#include "util/u_linkage.h" + +/* we must only record the registers that are actually used, not just declared */ +static INLINE boolean +util_semantic_set_test_and_set(struct util_semantic_set *set, unsigned value) +{ + unsigned mask = 1 << (value % (sizeof(long) * 8)); + unsigned long *p = &set->masks[value / (sizeof(long) * 8)]; + unsigned long v = *p & mask; + *p |= mask; + return !!v; +} + +unsigned +util_semantic_set_from_program_file(struct util_semantic_set *set, const struct tgsi_token *tokens, enum tgsi_file_type file) +{ + struct tgsi_shader_info info; + struct tgsi_parse_context parse; + unsigned count = 0; + ubyte *semantic_name; + ubyte *semantic_index; + + tgsi_scan_shader(tokens, &info); + + if(file == TGSI_FILE_INPUT) + { + semantic_name = info.input_semantic_name; + semantic_index = info.input_semantic_index; + } + else if(file == TGSI_FILE_OUTPUT) + { + semantic_name = info.output_semantic_name; + semantic_index = info.output_semantic_index; + } + else + assert(0); + + tgsi_parse_init(&parse, tokens); + + memset(set->masks, 0, sizeof(set->masks)); + while(!tgsi_parse_end_of_tokens(&parse)) + { + tgsi_parse_token(&parse); + + if(parse.FullToken.Token.Type == TGSI_TOKEN_TYPE_INSTRUCTION) + { + const struct tgsi_full_instruction *finst = &parse.FullToken.FullInstruction; + unsigned i; + for(i = 0; i < finst->Instruction.NumDstRegs; ++i) + { + if(finst->Dst[i].Register.File == file) + { + unsigned idx = finst->Dst[i].Register.Index; + if(semantic_name[idx] == TGSI_SEMANTIC_GENERIC) + { + if(!util_semantic_set_test_and_set(set, semantic_index[idx])) + ++count; + } + } + } + + for(i = 0; i < finst->Instruction.NumSrcRegs; ++i) + { + if(finst->Src[i].Register.File == file) + { + unsigned idx = finst->Src[i].Register.Index; + if(semantic_name[idx] == TGSI_SEMANTIC_GENERIC) + { + if(!util_semantic_set_test_and_set(set, semantic_index[idx])) + ++count; + } + } + } + } + } + tgsi_parse_free(&parse); + + return count; +} + +#define UTIL_SEMANTIC_SET_FOR_EACH(i, set) for(i = 0; i < 256; ++i) if(set->masks[i / (sizeof(long) * 8)] & (1 << (i % (sizeof(long) * 8)))) + +void +util_semantic_layout_from_set(unsigned char *layout, const struct util_semantic_set *set, unsigned efficient_slots, unsigned num_slots) +{ + int first = -1; + int last = -1; + unsigned i; + + memset(layout, 0xff, num_slots); + + UTIL_SEMANTIC_SET_FOR_EACH(i, set) + { + if(first < 0) + first = i; + last = i; + } + + if(last < efficient_slots) + { + UTIL_SEMANTIC_SET_FOR_EACH(i, set) + layout[i] = i; + } + else if((last - first) < efficient_slots) + { + UTIL_SEMANTIC_SET_FOR_EACH(i, set) + layout[i - first] = i; + } + else + { + unsigned idx = 0; + UTIL_SEMANTIC_SET_FOR_EACH(i, set) + layout[idx++] = i; + } +} diff --git a/src/gallium/auxiliary/util/u_linkage.h b/src/gallium/auxiliary/util/u_linkage.h new file mode 100644 index 0000000..e73e0fd --- /dev/null +++ b/src/gallium/auxiliary/util/u_linkage.h @@ -0,0 +1,38 @@ +#ifndef U_LINKAGE_H_ +#define U_LINKAGE_H_ + +#include "pipe/p_compiler.h" + +struct util_semantic_set +{ + unsigned long masks[256 / 8 / sizeof(unsigned long)]; +}; + +static INLINE bool +util_semantic_set_contains(struct util_semantic_set *set, unsigned char value) +{ + return !!(set->masks[value / (sizeof(long) * 8)] & (1 << (value / (sizeof(long) * 8)))); +} + +unsigned util_semantic_set_from_program_file(struct util_semantic_set *set, const struct tgsi_token *tokens, enum tgsi_file_type file); + +/* efficient_slots is the number of slots such that hardware performance is + * the same for using that amount, with holes, or less slots but with less + * holes. + * + * num_slots is the size of the layout array and hardware limit instead. + * + * efficient_slots == 0 or efficient_solts == num_slots are typical settings. + */ +void util_semantic_layout_from_set(unsigned char *layout, const struct util_semantic_set *set, unsigned efficient_slots, unsigned num_slots); + +static INLINE void +util_semantic_table_from_layout(unsigned char *table, unsigned char *layout, unsigned char first_slot_value, unsigned char num_slots) +{ + memset(table, 0xff, sizeof(table)); + + for(int i = 0; i < num_slots; ++i) + table[layout[i]] = first_slot_value + i; +} + +#endif /* U_LINKAGE_H_ */ -- 1.7.0.1.147.g6d84b ------------------------------------------------------------------------------ Download Intel® Parallel Studio Eval Try the new software tools for yourself. Speed compiling, find bugs proactively, and fine-tune applications for parallel performance. See why Intel Parallel Studio got high marks during beta. http://p.sf.net/sfu/intel-sw-dev _______________________________________________ Mesa3d-dev mailing list Mesa3d-dev@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/mesa3d-dev