[Mesa-dev] [PATCH 41/53] intel/fs: Fix Gen7 compressed source region alignment restriction for SIMD32

[Jason Ekstrand]

From: Francisco Jerez <currojerez at riseup.net>

Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>
---
 src/intel/compiler/brw_fs.cpp | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp
index f583900..ae59716 100644
--- a/src/intel/compiler/brw_fs.cpp
+++ b/src/intel/compiler/brw_fs.cpp
@@ -5088,8 +5088,14 @@ get_fpu_lowered_simd_width(const struct gen_device_info *devinfo,
             type_sz(inst->dst.type) == 4 && inst->dst.stride == 1 &&
             type_sz(inst->src[i].type) == 2 && inst->src[i].stride == 1;
 
+         /* We check size_read(i) against size_written instead of REG_SIZE
+          * because we want to properly handle SIMD32.  In SIMD32, you can end
+          * up which writes 4 registers and a source that reads 2 registers
+          * and we may still need to lower all the way to SIMD8 in that case.
+          */
          if (inst->size_written > REG_SIZE &&
-             inst->size_read(i) != 0 && inst->size_read(i) <= REG_SIZE &&
+             inst->size_read(i) != 0 &&
+             inst->size_read(i) < inst->size_written &&
              !is_scalar_exception && !is_packed_word_exception) {
             const unsigned reg_count = DIV_ROUND_UP(inst->size_written, REG_SIZE);
             max_width = MIN2(max_width, inst->exec_size / reg_count);
-- 
2.5.0.400.gff86faf