search for: file_immedi

...nv50.cpp index 2077388..b1e7409 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp @@ -939,9 +939,20 @@ CodeEmitterNV50::emitFMAD(const Instruction *i) code[0] = 0xe0000000; + if (i->src(1).getFile() == FILE_IMMEDIATE) { + code[1] = 0; + emitForm_IMM(i); + code[0] |= neg_mul << 15; + code[0] |= neg_add << 22; + if (i->saturate) + code[0] |= 1 << 8; + } else if (i->encSize == 4) { emitForm_MUL(i); - assert(!neg_mul && !neg_add);...

...nv50.cpp index 2077388..b1e7409 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp @@ -939,9 +939,20 @@ CodeEmitterNV50::emitFMAD(const Instruction *i) code[0] = 0xe0000000; + if (i->src(1).getFile() == FILE_IMMEDIATE) { + code[1] = 0; + emitForm_IMM(i); + code[0] |= neg_mul << 15; + code[0] |= neg_add << 22; + if (i->saturate) + code[0] |= 1 << 8; + } else if (i->encSize == 4) { emitForm_MUL(i); - assert(!neg_mul && !neg_add);...

V2: clarify code, commit msgs, add comments. Drop code to was supposed to make register assignment prefer SDST == SRC2 (patch 2) for now, because it didn't quite do what I intended.

Add emission rules for negative and saturate flags for MAD 4-byte opcodes, and get rid of some of the constraints. Obviously tested with a wide variety of shaders. V2: Document MAD as supported short form V3: Split up IMM from short-form modifiers Signed-off-by: Roy Spliet <rspliet at eclipso.eu> --- src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp | 10 ++++------

On using builtin functions we have to move the input to registers $0 and $1, if one of the input value is an immediate, we fail to propagate the immediate: ... mov u32 $r477 0x00000003 (0) ... mov u32 $r0 %r473 (0) mov u32 $r1 $r477 (0) call abs BUILTIN:0 (0) mov u32 %r495 $r1 (0) ... With this patch the immediate is propagated, potentially causing the first MOV to be superfluous, which we'd

...Instruction *ld = i->getSrc(s)->getInsn(); + assert(ld->getSrc(0) != NULL); + // check if we are moving an immediate, propagate it in that case + if (!ld || ld->fixed || (ld->op != OP_LOAD && ld->op != OP_MOV) || + !(ld->src(0).getFile() == FILE_IMMEDIATE)) + bld.mkMovToReg(s, i->getSrc(s)); + else { + bld.mkMovToReg(s, ld->getSrc(0)); + // Clear the src, to make code elimination possible here before we + // delete the instruction i later + i->setSrc(s, NULL); + if (ld->isDead()) +...

...llium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp >> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp >> @@ -939,9 +939,20 @@ CodeEmitterNV50::emitFMAD(const Instruction *i) >> >> code[0] = 0xe0000000; >> >> + if (i->src(1).getFile() == FILE_IMMEDIATE) { >> + code[1] = 0; >> + emitForm_IMM(i); >> + code[0] |= neg_mul << 15; >> + code[0] |= neg_add << 22; >> + if (i->saturate) >> + code[0] |= 1 << 8; >> + } else >> if (i->encSize ==...

was "nv50/ir: PostRaConstantFolding improvements" before. nothing really changed from the last version, just minor things. Karol Herbst (5): nv50/ir: restructure and rename postraconstantfolding pass nv50/ir: implement mad post ra folding for nvc0+ gk110/ir: add LIMM form of mad gm107/ir: add LIMM form of mad nv50/ir: also do PostRaLoadPropagation for FMA

Hi All, This series implements using double immediates in the nouveau codegen code. This turns the following (nvc0) code: 1: mov u32 $r2 0x00000000 (8) 2: mov u32 $r3 0x3fe00000 (8) 3: add f64 $r0d $r0d $r2d (8) Into: 1: add f64 $r0d $r0d 0.500000 (8) This has been tested with the 2 double shader tests which I just send to the piglet list. On a gk208 (gk110 / SM35)

...e30..7ae0cb2 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp @@ -373,7 +373,7 @@ static nv50_ir::DataFile translateFile(uint file) case TGSI_FILE_PREDICATE: return nv50_ir::FILE_PREDICATE; case TGSI_FILE_IMMEDIATE: return nv50_ir::FILE_IMMEDIATE; case TGSI_FILE_SYSTEM_VALUE: return nv50_ir::FILE_SYSTEM_VALUE; - case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_GLOBAL; + case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_BUFFER; case TGSI_FILE_MEMORY: return...

...odegen/nv50_ir_target_nv50.cpp @@ -275,9 +275,10 @@ TargetNV50::insnCanLoad(const Instruction *i, int s, return false; // NOTE: don't rely on flagsDef - for (int d = 0; i->defExists(d); ++d) - if (i->def(d).getFile() == FILE_FLAGS) - return false; + if (sf == FILE_IMMEDIATE) + for (int d = 0; i->defExists(d); ++d) + if (i->def(d).getFile() == FILE_FLAGS) + return false; unsigned mode = 0; -- 1.8.3.2

....getFile() == FILE_GPR && + i->getDef(0)->reg.data.id == i->getSrc(2)->reg.data.id) { + for (int s = 1; s >= 0; s--) { + def = i->getSrc(1)->getInsn(); + if (def->op == OP_MOV && def->src(0).getFile() == FILE_IMMEDIATE) { + vtmp = i->getSrc(1); + i->setSrc(1, def->getSrc(0)); + if (vtmp->refCount() == 0) + delete_Instruction(bb->getProgram(), def); + break; + } + + vtmp = i->get...

...100644 > --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp > +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp > @@ -939,9 +939,20 @@ CodeEmitterNV50::emitFMAD(const Instruction *i) > > code[0] = 0xe0000000; > > + if (i->src(1).getFile() == FILE_IMMEDIATE) { > + code[1] = 0; > + emitForm_IMM(i); > + code[0] |= neg_mul << 15; > + code[0] |= neg_add << 22; > + if (i->saturate) > + code[0] |= 1 << 8; > + } else > if (i->encSize == 4) { > emitForm_MUL(i);...

...).getFile() != FILE_GPR || + i->getDef(0)->reg.data.id != i->getSrc(2)->reg.data.id) + break; + + for (int s = 0; s < 2; s++) { + def = i->getSrc(1)->getInsn(); + if (def->op == OP_MOV && def->src(0).getFile() == FILE_IMMEDIATE) { + vtmp = i->getSrc(1); + i->setSrc(1, def->getSrc(0)); + + /* There's no post-RA dead code elimination, so do it here + * XXX: if we add more code-removing post-RA passes, we might + * want to create a p...

...tFile() != FILE_GPR || + i->src(2).getFile() != FILE_GPR || + i->getDef(0)->reg.data.id != i->getSrc(2)->reg.data.id) + break; + + def = i->getSrc(1)->getInsn(); + if (def->op == OP_MOV && def->src(0).getFile() == FILE_IMMEDIATE) { + vtmp = i->getSrc(1); + i->setSrc(1, def->getSrc(0)); + + /* There's no post-RA dead code elimination, so do it here + * XXX: if we add more code-removing post-RA passes, we might + * want to create a post-RA dead-cod...

...tFile() != FILE_GPR || + i->src(2).getFile() != FILE_GPR || + i->getDef(0)->reg.data.id != i->getSrc(2)->reg.data.id) + break; + + def = i->getSrc(1)->getInsn(); + if (def->op == OP_MOV && def->src(0).getFile() == FILE_IMMEDIATE) { + vtmp = i->getSrc(1); + i->setSrc(1, def->getSrc(0)); + + /* There's no post-RA dead code elimination, so do it here + * XXX: if we add more code-removing post-RA passes, we might + * want to create a post-RA dead-cod...

...ng an immediate, propagate it in that case > + if (!ld || ld->fixed || (ld->op != OP_LOAD && ld->op != OP_MOV) || > + !ld->src(0).getImmediate(imm)) At this point you don't even have to use getImmediate - you can just look at ld->src(0).getFile() == FILE_IMMEDIATE. Normally you'd just do i->src(s).getImmediate(imm) and moved on with life. But you kinda need the ld here, which is annoying. Perhaps you can just drop the manual deletion of the op here... which would let you do the much simpler thing. Can you see if there's any effect from that?...

...drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp >> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp >> @@ -373,7 +373,7 @@ static nv50_ir::DataFile translateFile(uint file) >> case TGSI_FILE_PREDICATE: return nv50_ir::FILE_PREDICATE; >> case TGSI_FILE_IMMEDIATE: return nv50_ir::FILE_IMMEDIATE; >> case TGSI_FILE_SYSTEM_VALUE: return nv50_ir::FILE_SYSTEM_VALUE; >> - case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_GLOBAL; >> + case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_BUFFER; >>...

...- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp > +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp > @@ -373,7 +373,7 @@ static nv50_ir::DataFile translateFile(uint file) > case TGSI_FILE_PREDICATE: return nv50_ir::FILE_PREDICATE; > case TGSI_FILE_IMMEDIATE: return nv50_ir::FILE_IMMEDIATE; > case TGSI_FILE_SYSTEM_VALUE: return nv50_ir::FILE_SYSTEM_VALUE; > - case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_GLOBAL; > + case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_BUFFER; > case TGSI_FILE_M...

...from_tgsi.cpp >>>> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp >>>> @@ -373,7 +373,7 @@ static nv50_ir::DataFile translateFile(uint file) >>>> case TGSI_FILE_PREDICATE: return nv50_ir::FILE_PREDICATE; >>>> case TGSI_FILE_IMMEDIATE: return nv50_ir::FILE_IMMEDIATE; >>>> case TGSI_FILE_SYSTEM_VALUE: return nv50_ir::FILE_SYSTEM_VALUE; >>>> - case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_GLOBAL; >>>> + case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMOR...