i965/fs: Take into account misalignment in regs_written() and regs_read().

There was a workaround for this in fs_inst::size_read() for the
SHADER_OPCODE_MOV_INDIRECT instruction and FIXED_GRF register file
*only*.  We should take this possibility into account for the sources
and destinations of all instructions on all optimization passes that
need to quantize dataflow in 32B increments by adding the amount of
misalignment to the size read or written from the regs_read() and
regs_written() helpers respectively.

Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 60907cd20b9723327c17950d09aa2eb9fb2c9a99..375d73be5e91d3f5e6ece3282227ed7f03a6d3a0 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -863,31 +863,7 @@ fs_inst::size_read(int arg) const
    case SHADER_OPCODE_MOV_INDIRECT:
       if (arg == 0) {
          assert(src[2].file == IMM);
-         unsigned region_length = src[2].ud;
-
-         if (src[0].file == UNIFORM) {
-            assert(region_length % 4 == 0);
-            return region_length;
-         } else if (src[0].file == FIXED_GRF) {
-            /* If the start of the region is not register aligned, then
-             * there's some portion of the register that's technically
-             * unread at the beginning.
-             *
-             * However, the register allocator works in terms of whole
-             * registers, and does not use subnr.  It assumes that the
-             * read starts at the beginning of the register, and extends
-             * regs_read() whole registers beyond that.
-             *
-             * To compensate, we extend the region length to include this
-             * unread portion at the beginning.
-             */
-            if (src[0].subnr)
-               region_length += src[0].subnr;
-
-            return region_length;
-         } else {
-            assert(!"Invalid register file");
-         }
+         return src[2].ud;
       }
       break;
 

diff --git a/src/mesa/drivers/dri/i965/brw_ir_fs.h b/src/mesa/drivers/dri/i965/brw_ir_fs.h
index 0be67b7b2f9bad2c480686b67608a681b83ad883..c688345fdfda5fabdfeb130b39b5ed1299017134 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_ir_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_ir_fs.h
@@ -435,9 +435,9 @@ set_saturate(bool saturate, fs_inst *inst)
 inline unsigned
 regs_written(const fs_inst *inst)
 {
-   /* XXX - Take into account register-misaligned offsets correctly. */
    assert(inst->dst.file != UNIFORM && inst->dst.file != IMM);
-   return DIV_ROUND_UP(inst->size_written -
+   return DIV_ROUND_UP(reg_offset(inst->dst) % REG_SIZE +
+                       inst->size_written -
                        MIN2(inst->size_written, reg_padding(inst->dst)),
                        REG_SIZE);
 }
@@ -451,10 +451,10 @@ regs_written(const fs_inst *inst)
 inline unsigned
 regs_read(const fs_inst *inst, unsigned i)
 {
-   /* XXX - Take into account register-misaligned offsets correctly. */
    const unsigned reg_size =
       inst->src[i].file == UNIFORM || inst->src[i].file == IMM ? 4 : REG_SIZE;
-   return DIV_ROUND_UP(inst->size_read(i) -
+   return DIV_ROUND_UP(reg_offset(inst->src[i]) % reg_size +
+                       inst->size_read(i) -
                        MIN2(inst->size_read(i), reg_padding(inst->src[i])),
                        reg_size);
 }