diff --git a/src/intel/compiler/brw_fs_copy_propagation.cpp b/src/intel/compiler/brw_fs_copy_propagation.cpp
index 343bac23889..6be8d8d8693 100644
--- a/src/intel/compiler/brw_fs_copy_propagation.cpp
+++ b/src/intel/compiler/brw_fs_copy_propagation.cpp
@@ -367,7 +367,8 @@ is_logic_op(enum opcode opcode)
 }
 
 static bool
-can_take_stride(fs_inst *inst, unsigned arg, unsigned stride,
+can_take_stride(fs_inst *inst, brw_reg_type dst_type,
+                unsigned arg, unsigned stride,
                 const gen_device_info *devinfo)
 {
    if (stride > 4)
@@ -377,9 +378,9 @@ can_take_stride(fs_inst *inst, unsigned arg, unsigned stride,
     * of the corresponding channel of the destination, and the provided stride
     * would break this restriction.
     */
-   if (has_dst_aligned_region_restriction(devinfo, inst) &&
+   if (has_dst_aligned_region_restriction(devinfo, inst, dst_type) &&
        !(type_sz(inst->src[arg].type) * stride ==
-           type_sz(inst->dst.type) * inst->dst.stride ||
+           type_sz(dst_type) * inst->dst.stride ||
          stride == 0))
       return false;
 
@@ -534,10 +535,15 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
    if (instruction_requires_packed_data(inst) && entry_stride != 1)
       return false;
 
+   const brw_reg_type dst_type = (has_source_modifiers &&
+                                  entry->dst.type != inst->src[arg].type) ?
+      entry->dst.type : inst->dst.type;
+
    /* Bail if the result of composing both strides would exceed the
     * hardware limit.
     */
-   if (!can_take_stride(inst, arg, entry_stride * inst->src[arg].stride,
+   if (!can_take_stride(inst, dst_type, arg,
+                        entry_stride * inst->src[arg].stride,
                         devinfo))
       return false;
 
diff --git a/src/intel/compiler/brw_ir_fs.h b/src/intel/compiler/brw_ir_fs.h
index 60f0c8bfa77..6becef748ce 100644
--- a/src/intel/compiler/brw_ir_fs.h
+++ b/src/intel/compiler/brw_ir_fs.h
@@ -553,7 +553,8 @@ is_unordered(const fs_inst *inst)
  */
 static inline bool
 has_dst_aligned_region_restriction(const gen_device_info *devinfo,
-                                   const fs_inst *inst)
+                                   const fs_inst *inst,
+                                   brw_reg_type dst_type)
 {
    const brw_reg_type exec_type = get_exec_type(inst);
    /* Even though the hardware spec claims that "integer DWord multiply"
@@ -567,13 +568,20 @@ has_dst_aligned_region_restriction(const gen_device_info *devinfo,
        (inst->opcode == BRW_OPCODE_MAD &&
         MIN2(type_sz(inst->src[1].type), type_sz(inst->src[2].type)) >= 4));
 
-   if (type_sz(inst->dst.type) > 4 || type_sz(exec_type) > 4 ||
+   if (type_sz(dst_type) > 4 || type_sz(exec_type) > 4 ||
        (type_sz(exec_type) == 4 && is_dword_multiply))
       return devinfo->is_cherryview || gen_device_info_is_9lp(devinfo);
    else
       return false;
 }
 
+static inline bool
+has_dst_aligned_region_restriction(const gen_device_info *devinfo,
+                                   const fs_inst *inst)
+{
+   return has_dst_aligned_region_restriction(devinfo, inst, inst->dst.type);
+}
+
 /**
  * Return whether the LOAD_PAYLOAD instruction is a plain copy of bits from
  * the specified register file into a VGRF.