[igt-dev] [PATCH i-g-t 1/2] lib/gpgpu_fill/tgl: Implement gpgpu_fillfunc for TGL

[Katarzyna Dec]

Adding gen12p1_gpgpu_fillfunc to have gpgpu_fill running on TGL.
Gpgpu shader was generated using IGA (Intel Graphics Assembler)
based on Gen11 binary adding necessary SWSB dependencies and
changes in SEND instruction.

Shader source code and array containing its assembled version
have same names now to avoid ambiguity.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
Cc: Antonio Argenziano <antonio.argenziano at intel.com>
Signed-off-by: Katarzyna Dec <katarzyna.dec at intel.com>
Signed-off-by: Lukasz Kalamarz <lukasz.kalamarz at intel.com>
Signed-off-by: Zbigniew Kempczynski <zbigniew.kempczynski at intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi at intel.com>
---
 lib/gpgpu_fill.c                              | 22 +++++++++++++++++++
 lib/gpgpu_fill.h                              |  7 ++++++
 lib/i915/shaders/README                       |  2 ++
 .../shaders/gpgpu/gen12p1_gpgpu_kernel.asm    | 12 ++++++++++
 lib/intel_batchbuffer.c                       |  2 ++
 5 files changed, 45 insertions(+)
 create mode 100644 lib/i915/shaders/gpgpu/gen12p1_gpgpu_kernel.asm

diff --git a/lib/gpgpu_fill.c b/lib/gpgpu_fill.c
index 003f4616..ec7204b8 100644
--- a/lib/gpgpu_fill.c
+++ b/lib/gpgpu_fill.c
@@ -87,6 +87,19 @@ static const uint32_t gen11_gpgpu_kernel[][4] = {
 	{ 0x07800031, 0x20000a40, 0x06000e00, 0x82000010 },
 };
 
+static const uint32_t gen12p1_gpgpu_kernel[][4] = {
+	{ 0x00020061, 0x01050000, 0x00000104, 0x00000000 },
+	{ 0x00000069, 0x02058220, 0x02000024, 0x00000004 },
+	{ 0x00000061, 0x02250220, 0x000000c4, 0x00000000 },
+	{ 0x00030061, 0x04050220, 0x00460005, 0x00000000 },
+	{ 0x00010261, 0x04050220, 0x00220205, 0x00000000 },
+	{ 0x00000061, 0x04454220, 0x00000000, 0x0000000f },
+	{ 0x00040661, 0x05050220, 0x00000104, 0x00000000 },
+	{ 0x00049031, 0x00000000, 0xc0000414, 0x02a00000 },
+	{ 0x00030061, 0x70050220, 0x00460005, 0x00000000 },
+	{ 0x00040131, 0x00000004, 0x7020700c, 0x10000000 },
+};
+
 /*
  * This sets up the gpgpu pipeline,
  *
@@ -282,3 +295,12 @@ void gen11_gpgpu_fillfunc(struct intel_batchbuffer *batch,
 	__gen9_gpgpu_fillfunc(batch, dst, x, y, width, height, color,
 			      gen11_gpgpu_kernel, sizeof(gen11_gpgpu_kernel));
 }
+void gen12p1_gpgpu_fillfunc(struct intel_batchbuffer *batch,
+			  const struct igt_buf *dst,
+			  unsigned int x, unsigned int y,
+			  unsigned int width, unsigned int height,
+			  uint8_t color)
+{
+	__gen9_gpgpu_fillfunc(batch, dst, x, y, width, height, color,
+			      gen12p1_gpgpu_kernel, sizeof(gen12p1_gpgpu_kernel));
+}
diff --git a/lib/gpgpu_fill.h b/lib/gpgpu_fill.h
index e405df3e..91c7ef71 100644
--- a/lib/gpgpu_fill.h
+++ b/lib/gpgpu_fill.h
@@ -57,4 +57,11 @@ gen11_gpgpu_fillfunc(struct intel_batchbuffer *batch,
 		     unsigned int width, unsigned int height,
 		     uint8_t color);
 
+void
+gen12p1_gpgpu_fillfunc(struct intel_batchbuffer *batch,
+		       const struct igt_buf *dst,
+		       unsigned int x, unsigned int y,
+		       unsigned int width, unsigned int height,
+		       uint8_t color);
+
 #endif /* GPGPU_FILL_H */
diff --git a/lib/i915/shaders/README b/lib/i915/shaders/README
index 06b9883c..6f80111b 100644
--- a/lib/i915/shaders/README
+++ b/lib/i915/shaders/README
@@ -23,3 +23,5 @@ Commands used to generate the shader on gen8
 $> m4 media_fill.gxa > media_fill.gxm
 $> intel-gen4asm -g 8 -o <output> media_fill.gxm
 
+Gen11+ shader is generated using IGA (Intel Graphics Assembler).
+Binary can no longer be generated using intel-gen4asm.
diff --git a/lib/i915/shaders/gpgpu/gen12p1_gpgpu_kernel.asm b/lib/i915/shaders/gpgpu/gen12p1_gpgpu_kernel.asm
new file mode 100644
index 00000000..ede87a05
--- /dev/null
+++ b/lib/i915/shaders/gpgpu/gen12p1_gpgpu_kernel.asm
@@ -0,0 +1,12 @@
+L0:
+         mov (4|M0)               r1.0<1>:ub    r1.0<0;1,0>:ub
+         shl (1|M0)               r2.0<1>:ud    r0.1<0;1,0>:ud    0x4:ud
+         mov (1|M0)               r2.1<1>:ud    r0.6<0;1,0>:ud
+         mov (8|M0)               r4.0<1>:ud    r0.0<8;8,1>:ud
+         mov (2|M0)               r4.0<1>:ud    r2.0<2;2,1>:ud                   {@2}
+         mov (1|M0)               r4.2<1>:ud    0xF:ud
+         mov (16|M0)              r5.0<1>:ud    r1.0<0;1,0>:ud                   {@6}
+         send.dc1 (16|M0)         null     r4      null    0x0         0x40A8000  {@1, $0} //    wr:2h+0, rd:0, Media Block Write msc:0, to #0
+         mov (8|M0)               r112.0<1>:ud  r0.0<8;8,1>:ud
+         send.ts (16|M0)          null     r112    null    0x10000000  0x2000010  {EOT, @1} //    wr:1+0, rd:0, fc: 0x10
+L160:
diff --git a/lib/intel_batchbuffer.c b/lib/intel_batchbuffer.c
index 07de5cbb..7fac25b8 100644
--- a/lib/intel_batchbuffer.c
+++ b/lib/intel_batchbuffer.c
@@ -901,6 +901,8 @@ igt_fillfunc_t igt_get_gpgpu_fillfunc(int devid)
 		fill = gen9_gpgpu_fillfunc;
 	else if (IS_GEN11(devid))
 		fill = gen11_gpgpu_fillfunc;
+	else if (IS_TIGERLAKE(devid))
+		fill = gen12p1_gpgpu_fillfunc;
 
 	return fill;
 }
-- 
2.20.1