glsl: fix int16 type

This shouldn't be unsigned, or else we'll trigger asserts.

Fixes: 7f00d4dac8 ("glsl: Handle 16-bit types in loop analysis")
Reviewed-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10125>

src/compiler/glsl/loop_analysis.cpp

@@ -162,7 +162,7 @@ calculate_iterations(ir_rvalue *from, ir_rvalue *to, ir_rvalue *increment,
          iter = new(mem_ctx) ir_constant(int32_t(iter_value + bias[i]));
          break;
       case GLSL_TYPE_INT16:
-         iter = new(mem_ctx) ir_constant(uint16_t(iter_value + bias[i]));
+         iter = new(mem_ctx) ir_constant(int16_t(iter_value + bias[i]));
          break;
       case GLSL_TYPE_INT64:
          iter = new(mem_ctx) ir_constant(int64_t(iter_value + bias[i]));