Displaying 4 results from an estimated 4 matches for "opproperti".
Did you mean:
opproperties
2015 Jan 02
0
[PATCH] nv50/ir: Fold sat into mad
...uveau/codegen/nv50_ir_target_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
index ebcb0ac..3694209 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
@@ -87,7 +87,7 @@ static const struct opProperties _initProps[] =
{ OP_MUL, 0x3, 0x0, 0x0, 0x0, 0x2, 0x1, 0x1, 0x2 },
{ OP_MAX, 0x3, 0x3, 0x0, 0x0, 0x2, 0x1, 0x1, 0x0 },
{ OP_MIN, 0x3, 0x3, 0x0, 0x0, 0x2, 0x1, 0x1, 0x0 },
- { OP_MAD, 0x7, 0x0, 0x0, 0x0, 0x6, 0x1, 0x1, 0x0 }, // special constraint
+ { OP_MAD, 0x7, 0x...
2015 Jan 04
0
[PATCH] nv50/ir: Add sat modifier for mul
...uveau/codegen/nv50_ir_target_nv50.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
index 3694209..c13c565 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
@@ -84,7 +84,7 @@ static const struct opProperties _initProps[] =
// neg abs not sat c[] s[], a[], imm
{ OP_ADD, 0x3, 0x0, 0x0, 0x8, 0x2, 0x1, 0x1, 0x2 },
{ OP_SUB, 0x3, 0x0, 0x0, 0x0, 0x2, 0x1, 0x1, 0x2 },
- { OP_MUL, 0x3, 0x0, 0x0, 0x0, 0x2, 0x1, 0x1, 0x2 },
+ { OP_MUL, 0x3, 0x0, 0x0, 0x8, 0x2, 0x1, 0x...
2014 Nov 23
3
[Bug 86618] New: [NV96] neg modifiers not working in MIN and MAX operations
...al to version without unary minus.
Only difference is lack of neg modifier.
After disabling modifiers shader works as expected:
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nv50.cpp
@@ -85,8 +85,8 @@ static const struct opProperties _initProps[] =
{ OP_ADD, 0x3, 0x0, 0x0, 0x8, 0x2, 0x1, 0x1, 0x2 },
{ OP_SUB, 0x3, 0x0, 0x0, 0x0, 0x2, 0x1, 0x1, 0x2 },
{ OP_MUL, 0x3, 0x0, 0x0, 0x0, 0x2, 0x1, 0x1, 0x2 },
- { OP_MAX, 0x3, 0x3, 0x0, 0x0, 0x2, 0x1, 0x1, 0x0 },
- { OP_MIN, 0x3, 0x3, 0x0, 0x0, 0x2, 0x1,...
2015 Feb 06
2
[PATCH 1/3] nv50/ir: Add support for MAD 4-byte opcode
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 ++++------