i965/fs: Fix propagation of copies with strided source.

This has likely been broken since we started propagating copies not
matching the offset of the instruction exactly
(1728e74957a62b1b4b9fbb62a7de2c12b77c8a75).  The copy source stride
needs to be taken into account to find out the offset at the origin
that corresponds to the offset at the destination of the copy which is
being read by the instruction.  This has led to program miscompilation
on both my SIMD32 branch and Igalia's FP64 branch.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
index 3c702d8..83791bf 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
@@ -460,16 +460,26 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
           * parts of vgrfs so we have to do some reg_offset magic.
           */
 
-         /* Compute the offset of inst->src[arg] relative to inst->dst */
-         assert(entry->dst.subreg_offset == 0);
-         int rel_offset = inst->src[arg].reg_offset - entry->dst.reg_offset;
-         int rel_suboffset = inst->src[arg].subreg_offset;
-
-         /* Compute the final register offset (in bytes) */
-         int offset = entry->src.reg_offset * 32 + entry->src.subreg_offset;
-         offset += rel_offset * 32 + rel_suboffset;
-         inst->src[arg].reg_offset = offset / 32;
-         inst->src[arg].subreg_offset = offset % 32;
+         /* Compute the offset of inst->src[arg] relative to entry->dst */
+         const unsigned rel_offset = (inst->src[arg].reg_offset
+                                      - entry->dst.reg_offset) * REG_SIZE +
+                                     inst->src[arg].subreg_offset;
+
+         /* Compute the first component of the copy that the instruction is
+          * reading, and the base byte offset within that component.
+          */
+         assert(entry->dst.subreg_offset == 0 && entry->dst.stride == 1);
+         const unsigned component = rel_offset / type_sz(entry->dst.type);
+         const unsigned suboffset = rel_offset % type_sz(entry->dst.type);
+
+         /* Calculate the byte offset at the origin of the copy of the given
+          * component and suboffset.
+          */
+         const unsigned offset = suboffset +
+            component * entry->src.stride * type_sz(entry->src.type) +
+            entry->src.reg_offset * REG_SIZE + entry->src.subreg_offset;
+         inst->src[arg].reg_offset = offset / REG_SIZE;
+         inst->src[arg].subreg_offset = offset % REG_SIZE;
       }
       break;