i965/vec4: fix scratch reads for 64bit data
v2: Setup for a 64-bit scratch read by checking the type size of the
correct register
v3: Use byte_offset() instead of offset()
Reviewed-by: Matt Turner <mattst88@gmail.com>
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
index d4fe4fa..2edbabb 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -1482,7 +1482,18 @@
src_reg index = get_scratch_offset(block, inst, orig_src.reladdr,
reg_offset);
- emit_before(block, inst, SCRATCH_READ(temp, index));
+ if (type_sz(orig_src.type) < 8) {
+ emit_before(block, inst, SCRATCH_READ(temp, index));
+ } else {
+ dst_reg shuffled = dst_reg(this, glsl_type::dvec4_type);
+ dst_reg shuffled_float = retype(shuffled, BRW_REGISTER_TYPE_F);
+ emit_before(block, inst, SCRATCH_READ(shuffled_float, index));
+ index = get_scratch_offset(block, inst, orig_src.reladdr, reg_offset + 1);
+ vec4_instruction *last_read =
+ SCRATCH_READ(byte_offset(shuffled_float, REG_SIZE), index);
+ emit_before(block, inst, last_read);
+ shuffle_64bit_data(temp, src_reg(shuffled), false, block, last_read);
+ }
}
/**
@@ -1548,7 +1559,8 @@
/* Now handle scratch access on src */
if (src.file == VGRF && scratch_loc[src.nr] != -1) {
- dst_reg temp = dst_reg(this, glsl_type::vec4_type);
+ dst_reg temp = dst_reg(this, type_sz(src.type) == 8 ?
+ glsl_type::dvec4_type : glsl_type::vec4_type);
emit_scratch_read(block, inst, temp, src, scratch_loc[src.nr]);
src.nr = temp.nr;
src.offset %= REG_SIZE;