[igt-dev] [PATCH i-g-t v3 1/2] lib/intel_compute: Prepare tgllp compute functions to be dg1 ready

Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed

From: "Zbigniew Kempczyński" <zbigniew.kempczynski@intel.com>
To: igt-dev@lists.freedesktop.org
Subject: [igt-dev] [PATCH i-g-t v3 1/2] lib/intel_compute: Prepare tgllp compute functions to be dg1 ready
Date: Tue, 14 Nov 2023 12:49:42 +0100	[thread overview]
Message-ID: <20231114114943.79965-2-zbigniew.kempczynski@intel.com> (raw)
In-Reply-To: <20231114114943.79965-1-zbigniew.kempczynski@intel.com>

Preparing dynamic, surface and indirect data states is similar between
platforms so lets simplify those function names. Also add indirect data
generator code which decreases large number of hardcoded lines.

Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
---
 lib/intel_compute.c | 115 ++++++++++++++------------------------------
 1 file changed, 35 insertions(+), 80 deletions(-)

diff --git a/lib/intel_compute.c b/lib/intel_compute.c
index 7f1ea90e72..772c22fa37 100644
--- a/lib/intel_compute.c
+++ b/lib/intel_compute.c
@@ -203,120 +203,75 @@ static void bo_execenv_exec(struct bo_execenv *execenv, uint64_t start_addr)
  */
 
 /**
- * tgllp_create_indirect_data:
+ * create_indirect_data:
  * @addr_bo_buffer_batch: pointer to batch buffer
  * @addr_input: input buffer gpu offset
  * @addr_output: output buffer gpu offset
  *
  * Prepares indirect data for compute pipeline.
  */
-static void tgllp_create_indirect_data(uint32_t *addr_bo_buffer_batch,
-				       uint64_t addr_input,
-				       uint64_t addr_output)
+static void create_indirect_data(uint32_t *addr_bo_buffer_batch,
+				 uint64_t addr_input,
+				 uint64_t addr_output,
+				 uint32_t end_value)
 {
-	int b = 0;
+	uint32_t val = 0;
+	int b = 0, curr = 0;
 
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000200;
+
 	addr_bo_buffer_batch[b++] = 0x00000001;
 	addr_bo_buffer_batch[b++] = 0x00000001;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
+
 	addr_bo_buffer_batch[b++] = addr_input & 0xffffffff;
 	addr_bo_buffer_batch[b++] = addr_input >> 32;
 	addr_bo_buffer_batch[b++] = addr_output & 0xffffffff;
 	addr_bo_buffer_batch[b++] = addr_output >> 32;
+
 	addr_bo_buffer_batch[b++] = 0x00000400;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
+
 	addr_bo_buffer_batch[b++] = 0x00000200;
 	addr_bo_buffer_batch[b++] = 0x00000001;
 	addr_bo_buffer_batch[b++] = 0x00000001;
 	addr_bo_buffer_batch[b++] = 0x00000000;
+
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
 	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00010000;
-	addr_bo_buffer_batch[b++] = 0x00030002;
-	addr_bo_buffer_batch[b++] = 0x00050004;
-	addr_bo_buffer_batch[b++] = 0x00070006;
-	addr_bo_buffer_batch[b++] = 0x00090008;
-	addr_bo_buffer_batch[b++] = 0x000B000A;
-	addr_bo_buffer_batch[b++] = 0x000D000C;
-	addr_bo_buffer_batch[b++] = 0x000F000E;
-	addr_bo_buffer_batch[b++] = 0x00110010;
-	addr_bo_buffer_batch[b++] = 0x00130012;
-	addr_bo_buffer_batch[b++] = 0x00150014;
-	addr_bo_buffer_batch[b++] = 0x00170016;
-	addr_bo_buffer_batch[b++] = 0x00190018;
-	addr_bo_buffer_batch[b++] = 0x001B001A;
-	addr_bo_buffer_batch[b++] = 0x001D001C;
-	addr_bo_buffer_batch[b++] = 0x001F001E;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00000000;
-	addr_bo_buffer_batch[b++] = 0x00210020;
-	addr_bo_buffer_batch[b++] = 0x00230022;
-	addr_bo_buffer_batch[b++] = 0x00250024;
-	addr_bo_buffer_batch[b++] = 0x00270026;
-	addr_bo_buffer_batch[b++] = 0x00290028;
-	addr_bo_buffer_batch[b++] = 0x002B002A;
-	addr_bo_buffer_batch[b++] = 0x002D002C;
-	addr_bo_buffer_batch[b++] = 0x002F002E;
-	addr_bo_buffer_batch[b++] = 0x00310030;
-	addr_bo_buffer_batch[b++] = 0x00330032;
-	addr_bo_buffer_batch[b++] = 0x00350034;
-	addr_bo_buffer_batch[b++] = 0x00370036;
-	addr_bo_buffer_batch[b++] = 0x00390038;
-	addr_bo_buffer_batch[b++] = 0x003B003A;
-	addr_bo_buffer_batch[b++] = 0x003D003C;
-	addr_bo_buffer_batch[b++] = 0x003F003E;
+
+	/*
+	 * Runtime prepares 32 16-bit incremented values packed to single dword.
+	 * Then it lefts 32 dword gap filled with zeroes. Pattern looks the
+	 * same for tgl and dg1 (apart of number of values).
+	 */
+	while (val < end_value) {
+		addr_bo_buffer_batch[b++] = val | ((val + 1) << 16);
+		val += 2;
+		if (++curr % 16 == 0)
+			b += 32;
+	}
 }
 
 /**
- * tgllp_create_surface_state:
+ * create_surface_state:
  * @addr_bo_buffer_batch: pointer to batch buffer
  * @addr_input: input buffer gpu offset
  * @addr_output: output buffer gpu offset
  *
  * Prepares surface state for compute pipeline.
  */
-static void tgllp_create_surface_state(uint32_t *addr_bo_buffer_batch,
-				       uint64_t addr_input,
-				       uint64_t addr_output)
+static void create_surface_state(uint32_t *addr_bo_buffer_batch,
+				 uint64_t addr_input,
+				 uint64_t addr_output)
 {
 	int b = 0;
 
@@ -387,14 +342,14 @@ static void tgllp_create_surface_state(uint32_t *addr_bo_buffer_batch,
 }
 
 /**
- * tgllp_create_dynamic_state:
+ * create_dynamic_state:
  * @addr_bo_buffer_batch: pointer to batch buffer
  * @offset_kernel: gpu offset of the shader
  *
  * Prepares dynamic state for compute pipeline.
  */
-static void tgllp_create_dynamic_state(uint32_t *addr_bo_buffer_batch,
-				       uint64_t offset_kernel)
+static void create_dynamic_state(uint32_t *addr_bo_buffer_batch,
+				 uint64_t offset_kernel)
 {
 	int b = 0;
 
@@ -582,9 +537,9 @@ static void tgl_compute_exec(int fd, const unsigned char *kernel,
 	bo_execenv_bind(&execenv, bo_dict, TGL_BO_DICT_ENTRIES);
 
 	memcpy(bo_dict[0].data, kernel, size);
-	tgllp_create_dynamic_state(bo_dict[1].data, OFFSET_KERNEL);
-	tgllp_create_surface_state(bo_dict[2].data, ADDR_INPUT, ADDR_OUTPUT);
-	tgllp_create_indirect_data(bo_dict[3].data, ADDR_INPUT, ADDR_OUTPUT);
+	create_dynamic_state(bo_dict[1].data, OFFSET_KERNEL);
+	create_surface_state(bo_dict[2].data, ADDR_INPUT, ADDR_OUTPUT);
+	create_indirect_data(bo_dict[3].data, ADDR_INPUT, ADDR_OUTPUT, 0x40);
 
 	dinput = (float *)bo_dict[4].data;
 	srand(time(NULL));
@@ -852,7 +807,7 @@ static void xehp_compute_exec(int fd, const unsigned char *kernel,
 	bo_execenv_bind(&execenv, bo_dict, XEHP_BO_DICT_ENTRIES);
 
 	memcpy(bo_dict[0].data, kernel, size);
-	tgllp_create_dynamic_state(bo_dict[1].data, OFFSET_KERNEL);
+	create_dynamic_state(bo_dict[1].data, OFFSET_KERNEL);
 	xehp_create_surface_state(bo_dict[2].data, ADDR_INPUT, ADDR_OUTPUT);
 	xehp_create_indirect_data(bo_dict[3].data, ADDR_INPUT, ADDR_OUTPUT);
 	xehp_create_surface_state(bo_dict[7].data, ADDR_INPUT, ADDR_OUTPUT);
-- 
2.34.1

next prev parent reply	other threads:[~2023-11-14 11:49 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-14 11:49 [igt-dev] [PATCH i-g-t v3 0/2] Add dg1 compute pipeline Zbigniew Kempczyński
2023-11-14 11:49 ` Zbigniew Kempczyński [this message]
2023-11-14 11:49 ` [igt-dev] [PATCH i-g-t v3 2/2] lib/intel_compute: Add dg1 compute implementation for i915 Zbigniew Kempczyński
2023-11-14 11:52   ` Francois Dugast
2023-11-14 12:19     ` Zbigniew Kempczyński
2023-11-14 14:00 ` [igt-dev] ✗ Fi.CI.BAT: failure for Add dg1 compute pipeline (rev3) Patchwork
2023-11-14 14:27 ` [igt-dev] ✓ CI.xeBAT: success " Patchwork
2023-11-15  6:50 ` [igt-dev] ✓ CI.xeBAT: success for Add dg1 compute pipeline (rev4) Patchwork
2023-11-15  6:58 ` [igt-dev] ✓ Fi.CI.BAT: " Patchwork
2023-11-17  0:19 ` [igt-dev] ✗ Fi.CI.IGT: failure " Patchwork
2023-11-17  5:53   ` Zbigniew Kempczyński

find likely ancestor, descendant, or conflicting patches for this message:
( dfblob:7f1ea90e7 dfblob:772c22fa3 )
 OR (
bs:"[igt-dev] [PATCH i-g-t v3 1/2] lib/intel_compute: Prepare tgllp compute functions to be dg1 ready" )
	(help)

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=20231114114943.79965-2-zbigniew.kempczynski@intel.com \
    --to=zbigniew.kempczynski@intel.com \
    --cc=igt-dev@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox