intel/fs: the maximum supported stride width is 16

There are cases where we try to generate registers with a stride of
32, while the hardware maximum is just 16. This happens, for example,
when using 8 bit integers on SIMD32. This results in a crash because
the variable 'width' has a value of 32:

../../src/intel/compiler/brw_reg.h:550: brw_reg brw_vecn_reg(unsigned
int, brw_reg_file, unsigned int, unsigned int): Assertion `!"Invalid
register width"' failed.

This change prevents the crash and makes the tests pass.

Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>

diff --git a/src/intel/compiler/brw_fs_generator.cpp b/src/intel/compiler/brw_fs_generator.cpp
index a94625507916c74dc34246d6d5d7661562a0b422..65b9217ee7706e2147d11a05204ffaf4bfb1a11d 100644 (file)
--- a/src/intel/compiler/brw_fs_generator.cpp
+++ b/src/intel/compiler/brw_fs_generator.cpp
@@ -85,6 +85,8 @@ brw_reg_from_fs_reg(const struct gen_device_info *devinfo, fs_inst *inst,
          const unsigned phys_width = compressed ? inst->exec_size / 2 :
                                      inst->exec_size;
 
+         const unsigned max_hw_width = 16;
+
          /* XXX - The equation above is strictly speaking not correct on
           *       hardware that supports unbalanced GRF writes -- On Gen9+
           *       each decompressed chunk of the instruction may have a
@@ -97,7 +99,7 @@ brw_reg_from_fs_reg(const struct gen_device_info *devinfo, fs_inst *inst,
             brw_reg = brw_vecn_reg(1, brw_file_from_reg(reg), reg->nr, 0);
             brw_reg = stride(brw_reg, reg->stride, 1, 0);
          } else {
-            const unsigned width = MIN2(reg_width, phys_width);
+            const unsigned width = MIN3(reg_width, phys_width, max_hw_width);
             brw_reg = brw_vecn_reg(width, brw_file_from_reg(reg), reg->nr, 0);
             brw_reg = stride(brw_reg, width * reg->stride, width, reg->stride);
          }