Renaming PyBuda\Buda occurances to Forge in TT-MLIR repo (#595)

docs/src/build.md

@@ -211,8 +211,8 @@ If you get the following error, it means you need to install clang which you can
 ### `sfpi`, `trisc`, `ncrisc` build failure
 
 ```
-pybuda/third_party/tt-mlir/third_party/tt-metal/src/tt-metal/tt_metal/third_party/sfpi/compiler/bin/riscv32-unknown-elf-g++: 1: version: not found
-pybuda/third_party/tt-mlir/third_party/tt-metal/src/tt-metal/tt_metal/third_party/sfpi/compiler/bin/riscv32-unknown-elf-g++: 2: oid: not found
+tt-forge-fe/third_party/tt-mlir/third_party/tt-metal/src/tt-metal/tt_metal/third_party/sfpi/compiler/bin/riscv32-unknown-elf-g++: 1: version: not found
+tt-forge-fe/third_party/tt-mlir/third_party/tt-metal/src/tt-metal/tt_metal/third_party/sfpi/compiler/bin/riscv32-unknown-elf-g++: 2: oid: not found
 size: '1961632': No such file
 size: '1961632': No such file
 size: '1961632': No such file

docs/src/overview.md

@@ -202,7 +202,7 @@ level of complexity downwards for the bottom, we will define a very
 aggressive TTNN backend for the MVP.
 Desired Optimization List:
 
--   BUDA (frontend)
+-   Forge-FE (frontend)
 
     -   Graph Optimizations, Constant Folding, Operation Fusion
 

docs/src/specs/runtime-stitching.md

@@ -13,8 +13,8 @@ between the compiler and the runtime.
 
 ### Simple Example
 ```
-mod_a = pybuda.compile(PyTorch_module_a)
-mod_b = pybuda.compile(PyTorch_module_b)
+mod_a = forge.compile(PyTorch_module_a)
+mod_b = forge.compile(PyTorch_module_b)
 
 for i in range(10):
     outs_a = mod_a(ins_a)
@@ -26,15 +26,15 @@ for i in range(10):
 `mod_a` it should be completely unaware that `mod_b` will take place and vice-versa.
 In order to achieve this we propose a new runtime concept called stitching:
 
-- pybuda invokes compile step for `mod_a`, tt-mlir compiler determines where the
+- forge invokes compile step for `mod_a`, tt-mlir compiler determines where the
   inputs (`ins_a`) should live, host, device dram, device l1. tt-mlir returns
-  metadata to pybuda describing where it wants the tensors to reside before invoking
+  metadata to forge describing where it wants the tensors to reside before invoking
   flatbuffer submission.
-- pybuda invokes compile step for `mod_b`, same happens as bullet 1
-- `mod_a` is invoked at runtime, pybuda runtime needs to inspect the compiler metadata
+- forge invokes compile step for `mod_b`, same happens as bullet 1
+- `mod_a` is invoked at runtime, forge runtime needs to inspect the compiler metadata
   to determine where the tensors should live.  Runtime manually invokes a new data
   copy command to get the tenors to the correct memory space / correct memory address.
-- pybuda runtime invokes `mod_a` program submit
+- forge runtime invokes `mod_a` program submit
 - `mod_b` is invoked at runtime, this time it might be that the compiler left
   the tensor outputs in L1, so no data copy is needed to start running `mod_b`
   since the inputs are already in the correct location.

test/ttmlir/Dialect/TTNN/multiple_add_with_loc.mlir

@@ -1,7 +1,7 @@
 // RUN: ttmlir-opt --ttir-to-ttnn-backend-pipeline %s | FileCheck %s
 #any_device = #tt.operand_constraint<dram|l1|scalar|tile|any_device|any_device_tile>
 #loc = loc("test_ops.py:17_0_0":0:0)
-module @pybuda_graph attributes {} {
+module attributes {} {
   func.func @main(%arg0: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0), %arg1: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0), %arg2: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0)) -> (tensor<1x32x32xf32>, tensor<1x32x32xf32>) {
     // CHECK: #[[LAYOUT_1:.*]] = #tt.layout<(d0, d1, d2) -> (d0 * 32 + d1, d2), undef, <8x8>, memref<4x4xf32, #dram>, interleaved>
     %0 = tensor.empty() : tensor<1x32x32xf32> loc(#loc5)

test/ttmlir/Dialect/TTNN/multiple_add_with_loc_grid_override.mlir

@@ -1,7 +1,7 @@
 // RUN: ttmlir-opt --ttir-to-ttnn-backend-pipeline="override-grid-sizes=add_1_0=4x4,add_2_0=4x4" %s | FileCheck %s
 #any_device = #tt.operand_constraint<dram|l1|scalar|tile|any_device|any_device_tile>
 #loc = loc("test_ops.py:17_0_0":0:0)
-module @pybuda_graph attributes {} {
+module attributes {} {
   func.func @main(%arg0: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0), %arg1: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0), %arg2: tensor<1x32x32xf32> loc("test_ops.py:17_0_0":0:0)) -> (tensor<1x32x32xf32>, tensor<1x32x32xf32>) {
     // CHECK: #[[LAYOUT_0:.*]] = #tt.layout<(d0, d1, d2) -> (d0 * 32 + d1, d2), undef, <8x8>, memref<4x4xf32, #system>, none_layout>
     // CHECK: #[[LAYOUT_1:.*]] = #tt.layout<(d0, d1, d2) -> (d0 * 32 + d1, d2), undef, <4x4>, memref<8x8xf32, #dram>, interleaved>