[ET-VK] Efficient tiled int8 matmul

backends/vulkan/runtime/graph/ops/glsl/q_8w_linear_tiled.glsl

@@ -0,0 +1,92 @@
+/*
+ * Copyright (c) Meta Platforms, Inc. and affiliates.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of this source tree.
+ */
+
+#version 450 core
+
+#define PRECISION ${PRECISION}
+
+#define T ${buffer_scalar_type(DTYPE)}
+#define VEC4_T ${buffer_gvec_type(DTYPE, 4)}
+
+#define TILE_ROWS ${TILE_ROWS}
+
+${define_required_extensions(DTYPE)}
+
+$if STORAGE == "buffer":
+  ${define_required_extensions("int8")}
+
+#extension GL_EXT_control_flow_attributes : require
+
+layout(std430) buffer;
+
+${layout_declare_tensor(B, "w", "t_out", DTYPE, STORAGE, is_scalar_array=False)}
+${layout_declare_tensor(B, "r", "t_in", DTYPE, STORAGE, is_scalar_array=False)}
+${layout_declare_tensor(B, "r", "t_weight", "int8", STORAGE, is_scalar_array=False)}
+${layout_declare_tensor(B, "r", "t_scales", DTYPE, STORAGE, is_scalar_array=False)}
+
+
+layout(push_constant) uniform restrict Block {
+  ivec4 out_sizes;
+  ivec4 in_sizes;
+  ivec4 weight_sizes;
+};
+
+layout(local_size_x_id = 0, local_size_y_id = 1, local_size_z_id = 2) in;
+
+void main() {
+  const uint out_row = gl_GlobalInvocationID.y * TILE_ROWS;
+  const uint out_col = gl_GlobalInvocationID.x << 2;
+
+  if (out_col >= out_sizes.x || out_row >= out_sizes.y) {
+    return;
+  }
+
+  VEC4_T a[TILE_ROWS];
+  VEC4_T b[4];
+  VEC4_T c[TILE_ROWS];
+
+  $if STORAGE == "buffer":
+    const VEC4_T scales = VEC4_T(t_scales[out_col >> 2]);
+  $else:
+    const VEC4_T scales = VEC4_T(texelFetch(t_scales, ivec3(out_col >> 2, 0, 0), 0));
+
+  [[unroll]] for (int i = 0; i < TILE_ROWS; ++i) {
+    c[i] = VEC4_T(0.0);
+  }
+
+  for (int pos = 0; pos < in_sizes.x; pos += 4) {
+    // Preload weight tensor
+    [[unroll]] for (int i = 0; i < 4; i++) {
+      $if STORAGE == "buffer":
+        b[i] = t_weight[((pos + i) * B_sizes.x + out_col) >> 2];
+      $else:
+        b[i] = VEC4_T(texelFetch(t_weight, ivec3(out_col >> 2, pos + i, 0), 0));
+    }
+
+    // Preload input tensor
+    [[unroll]] for (int i = 0; i < TILE_ROWS; i++) {
+      $if STORAGE == "buffer":
+        a[i] = t_in[((out_row + i) * in_sizes.x + (pos)) >> 2];
+      $else:
+        a[i] = VEC4_T(texelFetch(t_in, ivec3(pos >> 2, out_row + i, 0), 0));
+    }
+
+    // Compute partial output
+    [[unroll]] for (int i = 0; i < TILE_ROWS; ++i) {
+        c[i] += a[i].x * b[0] + a[i].y * b[1] + a[i].z * b[2] + a[i].w * b[3];
+    }
+  }
+
+  // Store output tensor
+  [[unroll]] for (int i = 0; i < TILE_ROWS; ++i) {
+    $if STORAGE == "buffer":
+      t_out[((out_row + i) * out_sizes.x + out_col) >> 2] = c[i] * scales;
+    $else:
+      imageStore(t_out, ivec3(out_col >> 2, out_row + i, 0), c[i] * scales);
+  }
+}

backends/vulkan/runtime/graph/ops/glsl/q_8w_linear_tiled.yaml

@@ -0,0 +1,18 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+q_8w_linear_tiled:
+  parameter_names_with_default_values:
+    DTYPE: float
+    STORAGE: texture3d
+    TILE_ROWS: 4
+  shader_variants:
+    - NAME: q_8w_linear_tiled_o4x4_texture3d_float
+      STORAGE: texture3d
+      TILE_ROWS: 4
+    - NAME: q_8w_linear_tiled_o4x6_texture3d_float
+      STORAGE: texture3d
+      TILE_ROWS: 6