From: Alex Deucher <alexdeucher@gmail.com>
Date: Thu, 5 May 2011 22:54:03 +0000 (-0400)
Subject: r600g: fix up the rules for enabling SOURCE_FORMAT(EXPORT_NORM)
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=5939bc03bc15b9b1131463ffad04a7b2d987074d;p=mesa.git

r600g: fix up the rules for enabling SOURCE_FORMAT(EXPORT_NORM)

Setting SOURCE_FORMAT to EXPORT_NORM is an optimization.
Leaving SOURCE_FORMAT at 0 will work in all cases, but is less
efficient.  The conditions for the setting the EXPORT_NORM
optimization are as follows:

R600/RV6xx:
BLEND_CLAMP is enabled
BLEND_FLOAT32 is disabled
11-bit or smaller UNORM/SNORM/SRGB

R7xx/evergreen:
11-bit or smaller UNORM/SNORM/SRGB
16-bit or smaller FLOAT

Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
---

diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
index d60c153b482..9757811e8b6 100644
--- a/src/gallium/drivers/r600/evergreen_state.c
+++ b/src/gallium/drivers/r600/evergreen_state.c
@@ -710,14 +710,20 @@ static void evergreen_cb(struct r600_pipe_context *rctx, struct r600_pipe_state
 		S_028C70_ENDIAN(endian);
 
 
-	/* we can only set the export size if any thing is snorm/unorm component is > 11 bits,
-	   if we aren't a float, sint or uint */
+	/* EXPORT_NORM is an optimzation that can be enabled for better
+	 * performance in certain cases.
+	 * EXPORT_NORM can be enabled if:
+	 * - 11-bit or smaller UNORM/SNORM/SRGB
+	 * - 16-bit or smaller FLOAT
+	 */
 	/* FIXME: This should probably be the same for all CBs if we want
 	 * useful alpha tests. */
 	if (desc->colorspace != UTIL_FORMAT_COLORSPACE_ZS &&
-	    desc->channel[i].size < 12 && desc->channel[i].type != UTIL_FORMAT_TYPE_FLOAT &&
-	    ntype != V_028C70_NUMBER_UINT && ntype != V_028C70_NUMBER_SINT) {
-		color_info |= S_028C70_SOURCE_FORMAT(V_028C70_EXPORT_4C_16BPC);
+	    ((desc->channel[i].size < 12 &&
+	      desc->channel[i].type != UTIL_FORMAT_TYPE_FLOAT &&
+	      ntype != V_028C70_NUMBER_UINT && ntype != V_028C70_NUMBER_SINT) ||
+	     (desc->channel[i].size < 17 &&
+	      desc->channel[i].type == UTIL_FORMAT_TYPE_FLOAT))) {
 		rctx->export_16bpc = true;
 	} else {
 		rctx->export_16bpc = false;
diff --git a/src/gallium/drivers/r600/r600_state.c b/src/gallium/drivers/r600/r600_state.c
index 90c5ba2b31e..3f979cf170f 100644
--- a/src/gallium/drivers/r600/r600_state.c
+++ b/src/gallium/drivers/r600/r600_state.c
@@ -770,11 +770,36 @@ static void r600_cb(struct r600_pipe_context *rctx, struct r600_pipe_state *rsta
 		S_0280A0_NUMBER_TYPE(ntype) |
 		S_0280A0_ENDIAN(endian);
 
-	/* on R600 this can't be set if BLEND_CLAMP isn't set,
-	   if BLEND_FLOAT32 is set of > 11 bits in a UNORM or SNORM */
-	if (desc->colorspace != UTIL_FORMAT_COLORSPACE_ZS &&
-	    desc->channel[i].size < 12)
-		color_info |= S_0280A0_SOURCE_FORMAT(V_0280A0_EXPORT_NORM);
+	/* EXPORT_NORM is an optimzation that can be enabled for better
+	 * performance in certain cases
+	 */
+	if (rctx->family < CHIP_RV770) {
+		/* EXPORT_NORM can be enabled if:
+		 * - 11-bit or smaller UNORM/SNORM/SRGB
+		 * - BLEND_CLAMP is enabled
+		 * - BLEND_FLOAT32 is disabled
+		 */
+		if (desc->colorspace != UTIL_FORMAT_COLORSPACE_ZS &&
+		    (desc->channel[i].size < 12 &&
+		     desc->channel[i].type != UTIL_FORMAT_TYPE_FLOAT &&
+		     ntype != V_0280A0_NUMBER_UINT &&
+		     ntype != V_0280A0_NUMBER_SINT) &&
+		    G_0280A0_BLEND_CLAMP(color_info) &&
+		    !G_0280A0_BLEND_FLOAT32(color_info))
+			color_info |= S_0280A0_SOURCE_FORMAT(V_0280A0_EXPORT_NORM);
+	} else {
+		/* EXPORT_NORM can be enabled if:
+		 * - 11-bit or smaller UNORM/SNORM/SRGB
+		 * - 16-bit or smaller FLOAT
+		 */
+		if (desc->colorspace != UTIL_FORMAT_COLORSPACE_ZS &&
+		    ((desc->channel[i].size < 12 &&
+		      desc->channel[i].type != UTIL_FORMAT_TYPE_FLOAT &&
+		      ntype != V_0280A0_NUMBER_UINT && ntype != V_0280A0_NUMBER_SINT) ||
+		    (desc->channel[i].size < 17 &&
+		     desc->channel[i].type == UTIL_FORMAT_TYPE_FLOAT)))
+			color_info |= S_0280A0_SOURCE_FORMAT(V_0280A0_EXPORT_NORM);
+	}
 
 	r600_pipe_state_add_reg(rstate,
 				R_028040_CB_COLOR0_BASE + cb * 4,