i965/nir/vec4: Implement linear interpolation

[mesa.git] / src / mesa / drivers / dri / i965 / brw_compute.c

diff --git a/src/mesa/drivers/dri/i965/brw_compute.c b/src/mesa/drivers/dri/i965/brw_compute.c
index 044deae83c989e03a19cc30f55572051a7502f65..5693ab507d474c788bec3da04850f9477ec503db 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_compute.c
+++ b/src/mesa/drivers/dri/i965/brw_compute.c
@@ -45,7 +45,7 @@ brw_emit_gpgpu_walker(struct brw_context *brw, const GLuint *num_groups)
    unsigned thread_width_max =
       (group_size + simd_size - 1) / simd_size;
 
-   uint32_t right_mask = (1u << simd_size) - 1;
+   uint32_t right_mask = 0xffffffffu >> (32 - simd_size);
    const unsigned right_non_aligned = group_size & (simd_size - 1);
    if (right_non_aligned != 0)
       right_mask >>= (simd_size - right_non_aligned);
@@ -74,6 +74,11 @@ brw_emit_gpgpu_walker(struct brw_context *brw, const GLuint *num_groups)
    OUT_BATCH(right_mask);               /* Right Execution Mask */
    OUT_BATCH(0xffffffff);               /* Bottom Execution Mask */
    ADVANCE_BATCH();
+
+   BEGIN_BATCH(2);
+   OUT_BATCH(MEDIA_STATE_FLUSH << 16 | (2 - 2));
+   OUT_BATCH(0);
+   ADVANCE_BATCH();
 }