[Mesa-dev] [PATCH 3/3] i965: Use correct VertStride on align16 instructions.

[Matt Turner]

In commit c35fa7a, we changed the "width" of DF source registers to 2,
which is conceptually fine. Unfortunately a VertStride of 2 is not
allowed by align16 instructions on IVB/BYT, and the regular VertStride
of 4 works fine in any case.

See generated_tests/spec/arb_gpu_shader_fp64/execution/built-in-functions/vs-round-double.shader_test
for example:

cmp.ge.f0(8)    g18<1>DF        g1<0>.xyxyDF    -g8<2>DF        { align16 1Q };
        ERROR: In Align16 mode, only VertStride of 0 or 4 is allowed
cmp.ge.f0(8)    g19<1>DF        g1<0>.xyxyDF    -g9<2>DF        { align16 2N };
        ERROR: In Align16 mode, only VertStride of 0 or 4 is allowed
---
 src/mesa/drivers/dri/i965/brw_eu_emit.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_eu_emit.c b/src/mesa/drivers/dri/i965/brw_eu_emit.c
index 888f95e..a01083f 100644
--- a/src/mesa/drivers/dri/i965/brw_eu_emit.c
+++ b/src/mesa/drivers/dri/i965/brw_eu_emit.c
@@ -512,10 +512,15 @@ brw_set_src0(struct brw_codegen *p, brw_inst *inst, struct brw_reg reg)
 	 /* This is an oddity of the fact we're using the same
 	  * descriptions for registers in align_16 as align_1:
 	  */
-	 if (reg.vstride == BRW_VERTICAL_STRIDE_8)
+         if (reg.vstride == BRW_VERTICAL_STRIDE_8) {
             brw_inst_set_src0_vstride(devinfo, inst, BRW_VERTICAL_STRIDE_4);
-	 else
+         } else if (devinfo->gen == 7 && !devinfo->is_haswell &&
+                    reg.type == BRW_REGISTER_TYPE_DF &&
+                    reg.vstride >= BRW_VERTICAL_STRIDE_1) {
+            brw_inst_set_src0_vstride(devinfo, inst, BRW_VERTICAL_STRIDE_4);
+         } else {
             brw_inst_set_src0_vstride(devinfo, inst, reg.vstride);
+         }
       }
    }
 }
@@ -594,10 +599,15 @@ brw_set_src1(struct brw_codegen *p, brw_inst *inst, struct brw_reg reg)
 	 /* This is an oddity of the fact we're using the same
 	  * descriptions for registers in align_16 as align_1:
 	  */
-	 if (reg.vstride == BRW_VERTICAL_STRIDE_8)
+         if (reg.vstride == BRW_VERTICAL_STRIDE_8) {
             brw_inst_set_src1_vstride(devinfo, inst, BRW_VERTICAL_STRIDE_4);
-	 else
+         } else if (devinfo->gen == 7 && !devinfo->is_haswell &&
+                    reg.type == BRW_REGISTER_TYPE_DF &&
+                    reg.vstride >= BRW_VERTICAL_STRIDE_1) {
+            brw_inst_set_src1_vstride(devinfo, inst, BRW_VERTICAL_STRIDE_4);
+         } else {
             brw_inst_set_src1_vstride(devinfo, inst, reg.vstride);
+         }
       }
    }
 }
-- 
2.7.3