From 93eae0d2a4157963638130b7ea2ad656f366e372 Mon Sep 17 00:00:00 2001 From: Iago Toral Quiroga Date: Wed, 13 Jul 2016 09:11:35 +0200 Subject: [PATCH] i965/vec4: don't propagate single-precision uniforms into 4-wide instructions Otherwise we end up producing code that violates the register region restriction that says that when execsize == width and hstride != 0 the vstride can't be 0. Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp index fba71ae..9b76f58 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_copy_propagation.cpp @@ -331,6 +331,17 @@ try_copy_propagate(const struct gen_device_info *devinfo, if (devinfo->gen < 8 && inst->size_written > REG_SIZE && is_uniform(value)) return false; + /* There is a regioning restriction such that if execsize == width + * and hstride != 0 then the vstride can't be 0. When we split instrutions + * that take a single-precision source (like F->DF conversions) we end up + * with a 4-wide source on an instruction with an execution size of 4. + * If we then copy-propagate the source from a uniform we also end up with a + * vstride of 0 and we violate the restriction. + */ + if (inst->exec_size == 4 && value.file == UNIFORM && + type_sz(value.type) == 4) + return false; + /* If the type of the copy value is different from the type of the * instruction then the swizzles and writemasks involved don't have the same * meaning and simply replacing the source would produce different semantics. -- 2.7.4