All of lore.kernel.org
 help / color / mirror / Atom feed
From: Damien Lespiau <damien.lespiau@intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH i-g-t 18/26] assembler/skl: update read(...)
Date: Fri, 26 Sep 2014 15:03:16 +0100	[thread overview]
Message-ID: <1411740204-25709-18-git-send-email-damien.lespiau@intel.com> (raw)
In-Reply-To: <1411740204-25709-1-git-send-email-damien.lespiau@intel.com>

From: Zhao Yakui <yakui.zhao@intel.com>

READ(...) is used for Render Target read and Media Block read. But there is no
sampler cache agent on gen9. At the same time two message types don't
share the same cache agent any more. So a parameter is needed for cache agent.
The 2th parameter of read(...) is not used for gen6/gen7/gen8. Hence it is
reused as cache agent for SKL as that on ILK.

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
---
 assembler/gram.y | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/assembler/gram.y b/assembler/gram.y
index e56533d..157ce79 100644
--- a/assembler/gram.y
+++ b/assembler/gram.y
@@ -1609,7 +1609,27 @@ msgtarget:	NULL_TOKEN
 		| READ  LPAREN INTEGER COMMA INTEGER COMMA INTEGER COMMA
                 INTEGER RPAREN
 		{
-		  if (IS_GENp(8)) {
+                  if (IS_GENp(9)) {
+                      if ($5 != 0 &&
+			  $5 != GEN6_SFID_DATAPORT_RENDER_CACHE &&
+			  $5 != GEN7_SFID_DATAPORT_DATA_CACHE &&
+			  $5 != HSW_SFID_DATAPORT_DATA_CACHE1 &&
+			  $5 != SKL_SFID_DATAPORT_DCR0 &&
+			  $5 != SKL_SFID_DATAPORT_DATA_CACHE2) {
+			  error (&@9, "error: wrong cache type\n");
+		      }
+
+		      if ($5 == 0)
+			  gen8_set_sfid(GEN8(&$$), HSW_SFID_DATAPORT_DATA_CACHE1);
+		      else
+			  gen8_set_sfid(GEN8(&$$), $5);
+
+                      gen8_set_header_present(GEN8(&$$), 1);
+                      gen8_set_dp_binding_table_index(GEN8(&$$), $3);
+                      gen8_set_dp_message_control(GEN8(&$$), $7);
+                      gen8_set_dp_message_type(GEN8(&$$), $9);
+                      gen8_set_dp_category(GEN8(&$$), 0);
+                  } else if (IS_GENp(8)) {
                       gen8_set_sfid(GEN8(&$$), GEN6_SFID_DATAPORT_SAMPLER_CACHE);
                       gen8_set_header_present(GEN8(&$$), 1);
                       gen8_set_dp_binding_table_index(GEN8(&$$), $3);
-- 
1.8.3.1

  parent reply	other threads:[~2014-09-26 14:05 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-26 14:02 [PATCH i-g-t 01/26] skl: Add SKL PCI ids Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 02/26] skl: Add gen9 to intel_gen() Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 03/26] skl: initialize instdone bits for gen9 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 04/26] list-workarounds/skl: Add Skylake to the list of valid platorms Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 05/26] rendercopy/skl: Start the gen9 rendercopy from the gen8 version Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 06/26] rendercopy/skl: Set the 3DSTATE_VF state Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 07/26] rendercopy/skl: Update 3DSTATE_SBE Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 08/26] rendercopy/skl: Pass the context to rendercopy function on SKL Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 09/26] rendercopy/skl: update instruction length Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 10/26] rendercopy/skl: Set Instruction Buffer size Modify Enable to 1 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 11/26] rendercopy/skl: Fix the STATE_BASE_ADDRESS instruction length Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 12/26] rendercopy/skl: Fix the 3DSTATE_DS " Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 13/26] rendercopy/skl: Emit 3DSTATE_WM_HZ_OP Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 14/26] rendercopy/skl: Follow the spec to add the Pipeline selection mask Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 15/26] rendercopy/skl: Set the URB VS start address to 4 Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 16/26] assembler/skl: Add gen 9 to the -g option Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 17/26] assembler/skl: Redefine the cache agent type for some fixed functions Damien Lespiau
2014-09-26 14:03 ` Damien Lespiau [this message]
2014-09-26 14:03 ` [PATCH i-g-t 19/26] assembler/skl: Add more cache agent for write(...) Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 20/26] assembler/skl: update the extdesc field for SEND instruction Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 21/26] mediafill/skl: Start the gen9 media_fill from the gen8 version Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 22/26] mediafill/skl: follow the spec to update STATE_BASE_ADDRESS command Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 23/26] mediafill/skl: Follow the spec to add pipeline_select mask Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 24/26] mediafill/skl: Follow spec to configure FORCE_MEDIA_AWAKE in PIPELINE_SELECTION Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 25/26] mediafill/skl: Follow spec to configure media sampler DOP clock gating " Damien Lespiau
2014-09-26 14:03 ` [PATCH i-g-t 26/26] lib/skl: Return the render copy and media fill functions Damien Lespiau
2014-09-30 11:24 ` [PATCH i-g-t 01/26] skl: Add SKL PCI ids Damien Lespiau

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1411740204-25709-18-git-send-email-damien.lespiau@intel.com \
    --to=damien.lespiau@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.