[LLVMGPU] Remove unused `--iree-codegen-llvmgpu-use-unaligned-gemm-vector-distribution` flag (#24308)

compiler/src/iree/compiler/Codegen/LLVMGPU/KernelConfig.cpp

diff --git a/compiler/src/iree/compiler/Codegen/LLVMGPU/KernelConfig.cpp b/compiler/src/iree/compiler/Codegen/LLVMGPU/KernelConfig.cpp
index b53c7c0..876a86f 100644
--- a/compiler/src/iree/compiler/Codegen/LLVMGPU/KernelConfig.cpp
+++ b/compiler/src/iree/compiler/Codegen/LLVMGPU/KernelConfig.cpp
@@ -80,15 +80,6 @@
         "enable the usage of the reduction vector distribution pipeline"),
     llvm::cl::init(true));
 
-// TODO (nirvedhmeshram): Drop this whole path after we have support with
-// TileAndFuse pipeline from completion of
-// https://github.com/iree-org/iree/issues/18858
-static llvm::cl::opt<bool> clGPUUnalignedGEMMVectorDistribution(
-    "iree-codegen-llvmgpu-use-unaligned-gemm-vector-distribution",
-    llvm::cl::desc("enable the usage of the vector distribution pipeline for "
-                   "unaligned GEMMs when supported"),
-    llvm::cl::init(false));
-
 static llvm::cl::opt<bool> clGPUUseTileAndFuseConvolution(
     "iree-codegen-llvmgpu-use-tile-and-fuse-convolution",
     llvm::cl::desc(

compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx942.mlir

diff --git a/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx942.mlir b/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx942.mlir
index 75cece3..1c82d60 100644
--- a/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx942.mlir
+++ b/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx942.mlir
@@ -1,6 +1,5 @@
 // RUN: iree-opt --split-input-file --iree-gpu-test-target=gfx942 --iree-codegen-llvmgpu-use-tile-and-fuse-matmul=false \
-// RUN:    --iree-codegen-llvmgpu-use-vector-distribution \
-// RUN:   --iree-codegen-llvmgpu-use-unaligned-gemm-vector-distribution --iree-codegen-llvmgpu-use-igemm=false \
+// RUN:    --iree-codegen-llvmgpu-use-vector-distribution --iree-codegen-llvmgpu-use-igemm=false \
 // RUN:   --pass-pipeline="builtin.module(iree-llvmgpu-select-lowering-strategy)" %s | FileCheck %s
 
 // TODO: This test is still using the legacy LLVMGPU kernel config. This needs

compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx950.mlir

diff --git a/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx950.mlir b/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx950.mlir
index 8ccf57a..ec99fd7 100644
--- a/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx950.mlir
+++ b/compiler/src/iree/compiler/Codegen/LLVMGPU/test/ROCDL/config_vector_distribute_gfx950.mlir
@@ -1,6 +1,5 @@
 // RUN: iree-opt --split-input-file --iree-gpu-test-target=gfx950 --iree-codegen-llvmgpu-use-tile-and-fuse-matmul=false \
-// RUN: --iree-codegen-llvmgpu-use-vector-distribution \
-// RUN:   --iree-codegen-llvmgpu-use-unaligned-gemm-vector-distribution --iree-codegen-llvmgpu-use-igemm=false \
+// RUN: --iree-codegen-llvmgpu-use-vector-distribution --iree-codegen-llvmgpu-use-igemm=false \
 // RUN:   --pass-pipeline="builtin.module(iree-llvmgpu-select-lowering-strategy)" %s | FileCheck %s
 
 // TODO: This test is still using the legacy LLVMGPU kernel config. This needs