This approach leads to the emitters needing to know about both global and buffer, even though at that point, they are identical. I was thinking that in the lowering logic, buffer would just get rewritten as global (with the offset added), thus not needing any change to the emitters. What do you think about such an approach? <div class="gmail_quote">On Mar 16, 2016 2:24 AM, "Hans de Goede" <<a href="mailto:hdegoede@redhat.com">hdegoede@redhat.com</a>> wrote: <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">FILE_MEMORY_GLOBAL is currently only used for buffer handling, as we do not yet have (opencl) global memory support. Global memory support actually requires some different handling during lowering, so rename FILE_MEMORY_GLOBAL to FILE_MEMORY_BUFFER to reflect that the current code is for buffer handling, this will allow the later (re-)addition of FILE_MEMORY_GLOBAL for regular global memory. Signed-off-by: Hans de Goede <<a href="mailto:hdegoede@redhat.com">hdegoede@redhat.com</a>> --- src/gallium/drivers/nouveau/codegen/nv50_ir.h | 2 +- src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp | 10 +++++----- src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp | 6 +++--- src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp | 10 +++++----- src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp | 12 ++++++------ src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 8 ++++---- .../drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp | 10 +++++----- src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 8 ++++---- src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp | 2 +- src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp | 6 +++--- src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp | 2 +- 11 files changed, 38 insertions(+), 38 deletions(-) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir.h b/src/gallium/drivers/nouveau/codegen/nv50_ir.h index 7b0eb2f..fdc2195 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir.h +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir.h @@ -332,7 +332,7 @@ enum DataFile FILE_MEMORY_CONST, FILE_SHADER_INPUT, FILE_SHADER_OUTPUT, - FILE_MEMORY_GLOBAL, + FILE_MEMORY_BUFFER, FILE_MEMORY_SHARED, FILE_MEMORY_LOCAL, FILE_SYSTEM_VALUE, diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp index 70f3c3f..02a1101 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp @@ -1641,7 +1641,7 @@ CodeEmitterGK110::emitSTORE(const Instruction *i) int32_t offset = SDATA(i->src(0)).offset; switch (i->src(0).getFile()) { - case FILE_MEMORY_GLOBAL: code[1] = 0xe0000000; code[0] = 0x00000000; break; + case FILE_MEMORY_BUFFER: code[1] = 0xe0000000; code[0] = 0x00000000; break; case FILE_MEMORY_LOCAL: code[1] = 0x7a800000; code[0] = 0x00000002; break; case FILE_MEMORY_SHARED: code[0] = 0x00000002; @@ -1678,7 +1678,7 @@ CodeEmitterGK110::emitSTORE(const Instruction *i) srcId(i->src(1), 2); srcId(i->src(0).getIndirect(0), 10); - if (i->src(0).getFile() == FILE_MEMORY_GLOBAL && + if (i->src(0).getFile() == FILE_MEMORY_BUFFER && i->src(0).isIndirect(0) && i->getIndirect(0, 0)->reg.size == 8) code[1] |= 1 << 23; @@ -1690,7 +1690,7 @@ CodeEmitterGK110::emitLOAD(const Instruction *i) int32_t offset = SDATA(i->src(0)).offset; switch (i->src(0).getFile()) { - case FILE_MEMORY_GLOBAL: code[1] = 0xc0000000; code[0] = 0x00000000; break; + case FILE_MEMORY_BUFFER: code[1] = 0xc0000000; code[0] = 0x00000000; break; case FILE_MEMORY_LOCAL: code[1] = 0x7a000000; code[0] = 0x00000002; break; case FILE_MEMORY_SHARED: code[0] = 0x00000002; @@ -1800,7 +1800,7 @@ CodeEmitterGK110::emitMOV(const Instruction *i) static inline bool uses64bitAddress(const Instruction *ldst) { - return ldst->src(0).getFile() == FILE_MEMORY_GLOBAL && + return ldst->src(0).getFile() == FILE_MEMORY_BUFFER && ldst->src(0).isIndirect(0) && ldst->getIndirect(0, 0)->reg.size == 8; } @@ -1862,7 +1862,7 @@ CodeEmitterGK110::emitCCTL(const Instruction *i) code[0] = 0x00000002 | (i->subOp << 2); - if (i->src(0).getFile() == FILE_MEMORY_GLOBAL) { + if (i->src(0).getFile() == FILE_MEMORY_BUFFER) { code[1] = 0x7b000000; } else { code[1] = 0x7c000000; diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp index e079a57..27f287f 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp @@ -2417,7 +2417,7 @@ void CodeEmitterGM107::emitCCTL() { unsigned width; - if (insn->src(0).getFile() == FILE_MEMORY_GLOBAL) { + if (insn->src(0).getFile() == FILE_MEMORY_BUFFER) { emitInsn(0xef600000); width = 30; } else { @@ -2988,7 +2988,7 @@ CodeEmitterGM107::emitInstruction(Instruction *i) case FILE_MEMORY_CONST : emitLDC(); break; case FILE_MEMORY_LOCAL : emitLDL(); break; case FILE_MEMORY_SHARED: emitLDS(); break; - case FILE_MEMORY_GLOBAL: emitLD(); break; + case FILE_MEMORY_BUFFER: emitLD(); break; default: assert(!"invalid load"); emitNOP(); @@ -2999,7 +2999,7 @@ CodeEmitterGM107::emitInstruction(Instruction *i) switch (insn->src(0).getFile()) { case FILE_MEMORY_LOCAL : emitSTL(); break; case FILE_MEMORY_SHARED: emitSTS(); break; - case FILE_MEMORY_GLOBAL: emitST(); break; + case FILE_MEMORY_BUFFER: emitST(); break; default: assert(!"invalid load"); emitNOP(); diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp index 682a19d..7476e21 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nv50.cpp @@ -662,7 +662,7 @@ CodeEmitterNV50::emitLOAD(const Instruction *i) code[0] = 0xd0000001; code[1] = 0x40000000; break; - case FILE_MEMORY_GLOBAL: + case FILE_MEMORY_BUFFER: code[0] = 0xd0000001 | (i->getSrc(0)->reg.fileIndex << 16); code[1] = 0x80000000; break; @@ -671,7 +671,7 @@ CodeEmitterNV50::emitLOAD(const Instruction *i) break; } if (sf == FILE_MEMORY_LOCAL || - sf == FILE_MEMORY_GLOBAL) + sf == FILE_MEMORY_BUFFER) emitLoadStoreSizeLG(i->sType, 21 + 32); setDst(i, 0); @@ -679,7 +679,7 @@ CodeEmitterNV50::emitLOAD(const Instruction *i) emitFlagsRd(i); emitFlagsWr(i); - if (i->src(0).getFile() == FILE_MEMORY_GLOBAL) { + if (i->src(0).getFile() == FILE_MEMORY_BUFFER) { srcId(*i->src(0).getIndirect(0), 9); } else { setAReg16(i, 0); @@ -699,7 +699,7 @@ CodeEmitterNV50::emitSTORE(const Instruction *i) code[1] = 0x80c00000; srcId(i->src(1), 32 + 14); break; - case FILE_MEMORY_GLOBAL: + case FILE_MEMORY_BUFFER: code[0] = 0xd0000001 | (i->getSrc(0)->reg.fileIndex << 16); code[1] = 0xa0000000; emitLoadStoreSizeLG(i->dType, 21 + 32); @@ -737,7 +737,7 @@ CodeEmitterNV50::emitSTORE(const Instruction *i) break; } - if (f == FILE_MEMORY_GLOBAL) + if (f == FILE_MEMORY_BUFFER) srcId(*i->src(0).getIndirect(0), 9); else setAReg16(i, 0); diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp index 8b9328b..6236659 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp @@ -280,7 +280,7 @@ void CodeEmitterNVC0::setAddressByFile(const ValueRef& src) { switch (src.getFile()) { - case FILE_MEMORY_GLOBAL: + case FILE_MEMORY_BUFFER: srcAddr32(src, 26, 0); break; case FILE_MEMORY_LOCAL: @@ -1768,7 +1768,7 @@ CodeEmitterNVC0::emitCachingMode(CacheMode c) static inline bool uses64bitAddress(const Instruction *ldst) { - return ldst->src(0).getFile() == FILE_MEMORY_GLOBAL && + return ldst->src(0).getFile() == FILE_MEMORY_BUFFER && ldst->src(0).isIndirect(0) && ldst->getIndirect(0, 0)->reg.size == 8; } @@ -1779,7 +1779,7 @@ CodeEmitterNVC0::emitSTORE(const Instruction *i) uint32_t opc; switch (i->src(0).getFile()) { - case FILE_MEMORY_GLOBAL: opc = 0x90000000; break; + case FILE_MEMORY_BUFFER: opc = 0x90000000; break; case FILE_MEMORY_LOCAL: opc = 0xc8000000; break; case FILE_MEMORY_SHARED: if (i->subOp == NV50_IR_SUBOP_STORE_UNLOCKED) { @@ -1828,7 +1828,7 @@ CodeEmitterNVC0::emitLOAD(const Instruction *i) code[0] = 0x00000005; switch (i->src(0).getFile()) { - case FILE_MEMORY_GLOBAL: opc = 0x80000000; break; + case FILE_MEMORY_BUFFER: opc = 0x80000000; break; case FILE_MEMORY_LOCAL: opc = 0xc0000000; break; case FILE_MEMORY_SHARED: if (i->subOp == NV50_IR_SUBOP_LOAD_LOCKED) { @@ -2090,7 +2090,7 @@ CodeEmitterNVC0::emitCCTL(const Instruction *i) { code[0] = 0x00000005 | (i->subOp << 5); - if (i->src(0).getFile() == FILE_MEMORY_GLOBAL) { + if (i->src(0).getFile() == FILE_MEMORY_BUFFER) { code[1] = 0x98000000; srcAddr32(i->src(0), 28, 2); } else { @@ -3121,7 +3121,7 @@ SchedDataCalculator::checkRd(const Value *v, int cycle, int& delay) const case FILE_MEMORY_LOCAL: case FILE_MEMORY_CONST: case FILE_MEMORY_SHARED: - case FILE_MEMORY_GLOBAL: + case FILE_MEMORY_BUFFER: case FILE_SYSTEM_VALUE: // TODO: any restrictions here ? break; diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp index 1e91ad3..91879e4 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp @@ -373,8 +373,8 @@ 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_MEMORY: return nv50_ir::FILE_MEMORY_GLOBAL; + case TGSI_FILE_BUFFER: return nv50_ir::FILE_MEMORY_BUFFER; + case TGSI_FILE_MEMORY: return nv50_ir::FILE_MEMORY_BUFFER; case TGSI_FILE_SAMPLER: case TGSI_FILE_NULL: default: @@ -2191,7 +2191,7 @@ Converter::getResourceBase(const int r) switch (r) { case TGSI_RESOURCE_GLOBAL: - sym = new_Symbol(prog, nv50_ir::FILE_MEMORY_GLOBAL, 15); + sym = new_Symbol(prog, nv50_ir::FILE_MEMORY_BUFFER, 15); break; case TGSI_RESOURCE_LOCAL: assert(prog->getType() == Program::TYPE_COMPUTE); @@ -2209,7 +2209,7 @@ Converter::getResourceBase(const int r) break; default: sym = new_Symbol(prog, - nv50_ir::FILE_MEMORY_GLOBAL, code-><a href="http://resources.at" rel="noreferrer" target="_blank">resources.at</a>(r).slot); + nv50_ir::FILE_MEMORY_BUFFER, code-><a href="http://resources.at" rel="noreferrer" target="_blank">resources.at</a>(r).slot); break; } return sym; diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp index d0936d8..563d7c2 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp @@ -1141,7 +1141,7 @@ NVC0LoweringPass::handleATOM(Instruction *atom) handleSharedATOM(atom); return true; default: - assert(atom->src(0).getFile() == FILE_MEMORY_GLOBAL); + assert(atom->src(0).getFile() == FILE_MEMORY_BUFFER); base = loadResInfo64(ind, atom->getSrc(0)->reg.fileIndex * 16); assert(base->reg.size == 8); if (ptr) @@ -1154,7 +1154,7 @@ NVC0LoweringPass::handleATOM(Instruction *atom) bld.mkOp1v(OP_RDSV, TYPE_U32, bld.getScratch(), bld.mkSysVal(sv, 0)); atom->setSrc(0, cloneShallow(func, atom->getSrc(0))); - atom->getSrc(0)->reg.file = FILE_MEMORY_GLOBAL; + atom->getSrc(0)->reg.file = FILE_MEMORY_BUFFER; if (ptr) base = bld.mkOp2v(OP_ADD, TYPE_U32, base, base, ptr); atom->setIndirect(0, 1, NULL); @@ -1571,7 +1571,7 @@ NVC0LoweringPass::handleSurfaceOpNVE4(TexInstruction *su) Instruction *red = bld.mkOp(OP_ATOM, su->dType, su->getDef(0)); red->subOp = su->subOp; if (!gMemBase) - gMemBase = bld.mkSymbol(FILE_MEMORY_GLOBAL, 0, TYPE_U32, 0); + gMemBase = bld.mkSymbol(FILE_MEMORY_BUFFER, 0, TYPE_U32, 0); red->setSrc(0, gMemBase); red->setSrc(1, su->getSrc(3)); if (su->subOp == NV50_IR_SUBOP_ATOM_CAS) @@ -1963,7 +1963,7 @@ NVC0LoweringPass::visit(Instruction *i) } else if (i->src(0).getFile() == FILE_SHADER_OUTPUT) { assert(prog->getType() == Program::TYPE_TESSELLATION_CONTROL); i->op = OP_VFETCH; - } else if (i->src(0).getFile() == FILE_MEMORY_GLOBAL) { + } else if (i->src(0).getFile() == FILE_MEMORY_BUFFER) { Value *ind = i->getIndirect(0, 1); Value *ptr = loadResInfo64(ind, i->getSrc(0)->reg.fileIndex * 16); // XXX come up with a way not to do this for EVERY little access but @@ -1987,7 +1987,7 @@ NVC0LoweringPass::visit(Instruction *i) break; case OP_ATOM: { - const bool cctl = i->src(0).getFile() == FILE_MEMORY_GLOBAL; + const bool cctl = i->src(0).getFile() == FILE_MEMORY_BUFFER; handleATOM(i); handleCasExch(i, cctl); } diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp index 66e7b2e..4a96d04 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp @@ -2580,14 +2580,14 @@ MemoryOpt::runOpt(BasicBlock *bb) ldst->op == OP_BAR || ldst->op == OP_MEMBAR) { purgeRecords(NULL, FILE_MEMORY_LOCAL); - purgeRecords(NULL, FILE_MEMORY_GLOBAL); + purgeRecords(NULL, FILE_MEMORY_BUFFER); purgeRecords(NULL, FILE_MEMORY_SHARED); purgeRecords(NULL, FILE_SHADER_OUTPUT); } else if (ldst->op == OP_ATOM || ldst->op == OP_CCTL) { - if (ldst->src(0).getFile() == FILE_MEMORY_GLOBAL) { + if (ldst->src(0).getFile() == FILE_MEMORY_BUFFER) { purgeRecords(NULL, FILE_MEMORY_LOCAL); - purgeRecords(NULL, FILE_MEMORY_GLOBAL); + purgeRecords(NULL, FILE_MEMORY_BUFFER); purgeRecords(NULL, FILE_MEMORY_SHARED); } else { purgeRecords(NULL, ldst->src(0).getFile()); @@ -2607,7 +2607,7 @@ MemoryOpt::runOpt(BasicBlock *bb) DataFile file = ldst->src(0).getFile(); // if ld l[]/g[] look for previous store to eliminate the reload - if (file == FILE_MEMORY_GLOBAL || file == FILE_MEMORY_LOCAL) { + if (file == FILE_MEMORY_BUFFER || file == FILE_MEMORY_LOCAL) { // TODO: shared memory ? rec = findRecord(ldst, false, isAdjacent); if (rec && !isAdjacent) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp index cfa85ec..73ed753 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_print.cpp @@ -455,7 +455,7 @@ int Symbol::print(char *buf, size_t size, case FILE_MEMORY_CONST: c = 'c'; break; case FILE_SHADER_INPUT: c = 'a'; break; case FILE_SHADER_OUTPUT: c = 'o'; break; - case FILE_MEMORY_GLOBAL: c = 'g'; break; + case FILE_MEMORY_BUFFER: c = 'g'; break; case FILE_MEMORY_SHARED: c = 's'; break; case FILE_MEMORY_LOCAL: c = 'l'; break; default: diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp index 2c4d7f5..1cd45a2 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp @@ -207,7 +207,7 @@ TargetNV50::getFileSize(DataFile file) const case FILE_MEMORY_CONST: return 65536; case FILE_SHADER_INPUT: return 0x200; case FILE_SHADER_OUTPUT: return 0x200; - case FILE_MEMORY_GLOBAL: return 0xffffffff; + case FILE_MEMORY_BUFFER: return 0xffffffff; case FILE_MEMORY_SHARED: return 16 << 10; case FILE_MEMORY_LOCAL: return 48 << 10; case FILE_SYSTEM_VALUE: return 16; @@ -406,7 +406,7 @@ TargetNV50::isAccessSupported(DataFile file, DataType ty) const if (ty == TYPE_B96 || ty == TYPE_NONE) return false; if (typeSizeof(ty) > 4) - return (file == FILE_MEMORY_LOCAL) || (file == FILE_MEMORY_GLOBAL); + return (file == FILE_MEMORY_LOCAL) || (file == FILE_MEMORY_BUFFER); return true; } @@ -508,7 +508,7 @@ int TargetNV50::getLatency(const Instruction *i) const if (i->op == OP_LOAD) { switch (i->src(0).getFile()) { case FILE_MEMORY_LOCAL: - case FILE_MEMORY_GLOBAL: + case FILE_MEMORY_BUFFER: return 100; // really 400 to 800 default: return 22; diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp index a03afa8..bda59a5 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp @@ -248,7 +248,7 @@ TargetNVC0::getFileSize(DataFile file) const case FILE_MEMORY_CONST: return 65536; case FILE_SHADER_INPUT: return 0x400; case FILE_SHADER_OUTPUT: return 0x400; - case FILE_MEMORY_GLOBAL: return 0xffffffff; + case FILE_MEMORY_BUFFER: return 0xffffffff; case FILE_MEMORY_SHARED: return 16 << 10; case FILE_MEMORY_LOCAL: return 48 << 10; case FILE_SYSTEM_VALUE: return 32; -- 2.7.2 </blockquote></div>