From b5e7907f3089d72109610769f083e80e452b0ff2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 31 Mar 2016 08:53:40 +0200 Subject: [PATCH] nouveau: codegen: LOAD: Take src swizzle into account The llvm TGSI backend uses pointers in registers and does things like: LOAD TEMP[0].y, MEMORY[0], TEMP[0] Expecting the data at address TEMP[0].x to get loaded to TEMP[0].y. But this will cause the data at TEMP[0].x + 4 to be loaded instead. This commit adds support for a swizzle suffix for the 1st source operand, which allows using: LOAD TEMP[0].y, MEMORY[0].xxxx, TEMP[0] And actually getting the desired behavior Signed-off-by: Hans de Goede Reviewed-by: Samuel Pitoiset Reviewed-by: Ilia Mirkin --- src/gallium/docs/source/tgsi.rst | 3 +++ src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 8 ++++++-- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst index 85c302f0dc3..4315707e643 100644 --- a/src/gallium/docs/source/tgsi.rst +++ b/src/gallium/docs/source/tgsi.rst @@ -2288,6 +2288,9 @@ Resource Access Opcodes texture arrays and 2D textures. address.w is always ignored. + A swizzle suffix may be added to the resource argument + this will cause the resource data to be swizzled accordingly. + .. opcode:: STORE - Write data to a shader resource Syntax: ``STORE resource, address, src`` 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 9b9f257b280..3708f3738e1 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp @@ -2385,14 +2385,18 @@ Converter::handleLOAD(Value *dst0[4]) Value *off; Symbol *sym; + uint32_t src0_component_offset = tgsi.getSrc(0).getSwizzle(c) * 4; + if (tgsi.getSrc(1).getFile() == TGSI_FILE_IMMEDIATE) { off = NULL; sym = makeSym(tgsi.getSrc(0).getFile(), r, -1, c, - tgsi.getSrc(1).getValueU32(0, info) + 4 * c); + tgsi.getSrc(1).getValueU32(0, info) + + src0_component_offset); } else { // yzw are ignored for buffers off = fetchSrc(1, 0); - sym = makeSym(tgsi.getSrc(0).getFile(), r, -1, c, 4 * c); + sym = makeSym(tgsi.getSrc(0).getFile(), r, -1, c, + src0_component_offset); } Instruction *ld = mkLoad(TYPE_U32, dst0[c], sym, off); -- 2.30.2