[PATCH i-g-t v2 3/5] lib/intel_compute_square_kernel: add loop shader binary for PTL

[Zbigniew Kempczyński]

Replace used increment shader with loop version.

Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
Cc: Francois Dugast <francois.dugast at intel.com>
Cc: Priyanka Dandamudi <priyanka.dandamudi at intel.com>
---
 lib/intel_compute_square_kernels.c | 36 ++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/lib/intel_compute_square_kernels.c b/lib/intel_compute_square_kernels.c
index 626dbc4cec..f67c048583 100644
--- a/lib/intel_compute_square_kernels.c
+++ b/lib/intel_compute_square_kernels.c
@@ -3881,6 +3881,40 @@ static const unsigned char xe2lpg_kernel_loop_bin[] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
 };
 
+static const unsigned char xe3lpg_kernel_loop_bin[] = {
+	0x65, 0x00, 0x00, 0x80, 0x20, 0x82, 0x05, 0x7f, 0x04, 0x00, 0x00, 0x02,
+	0xc0, 0xff, 0xff, 0xff, 0x40, 0x19, 0x00, 0x80, 0x20, 0x82, 0x05, 0x7f,
+	0x04, 0x7f, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x31, 0x20, 0x03, 0x80,
+	0x00, 0x00, 0x0c, 0x02, 0x8f, 0x7f, 0x00, 0xfa, 0x03, 0x00, 0x70, 0xf6,
+	0x61, 0x00, 0x10, 0x2c, 0x01, 0x00, 0x10, 0x00, 0x01, 0x00, 0x00, 0x80,
+	0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00, 0x00, 0x00,
+	0x01, 0x00, 0x00, 0x80, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x30,
+	0x00, 0x00, 0x00, 0x00, 0x66, 0x09, 0x00, 0x80, 0x20, 0x82, 0x01, 0x80,
+	0x00, 0x80, 0x00, 0x02, 0xc0, 0x04, 0x00, 0x40, 0x01, 0x09, 0x8c, 0x3c,
+	0x00, 0x00, 0x10, 0x00, 0x61, 0x00, 0x84, 0xa4, 0x04, 0x02, 0x10, 0x00,
+	0x31, 0x20, 0x03, 0x80, 0x00, 0x00, 0x0c, 0x03, 0x0c, 0x04, 0x00, 0xfb,
+	0x00, 0x00, 0xa0, 0x00, 0x70, 0x80, 0x14, 0x80, 0x60, 0x86, 0x01, 0x00,
+	0x04, 0x03, 0x00, 0x16, 0x34, 0x12, 0x34, 0x12, 0x20, 0x00, 0x00, 0x94,
+	0x00, 0x40, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, 0xff, 0xff, 0xff,
+	0x61, 0x1d, 0x10, 0x28, 0x7f, 0x01, 0x10, 0x00, 0x31, 0x20, 0x02, 0x80,
+	0x04, 0x00, 0x00, 0x00, 0x0c, 0x7f, 0x20, 0x30, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x01, 0x09, 0x00, 0x80, 0x00, 0x00, 0x01, 0x00,
+	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+
 unsigned char xelpg_kernel_square_bin[] = {
 	0x61, 0x00, 0x03, 0x80, 0x20, 0x42, 0x05, 0x7f, 0x00, 0x00, 0x00, 0x00,
 	0x00, 0x00, 0x00, 0x00, 0x65, 0x00, 0x00, 0x80, 0x20, 0x82, 0x45, 0x7f,
@@ -6688,6 +6722,8 @@ const struct intel_compute_kernels intel_compute_square_kernels[] = {
 		.long_kernel_size = sizeof(xe3lpg_kernel_inc_bin),
 		.sip_kernel = xe3lpg_kernel_sip_bin,
 		.sip_kernel_size = sizeof(xe3lpg_kernel_sip_bin),
+		.loop_kernel = xe3lpg_kernel_loop_bin,
+		.loop_kernel_size = sizeof(xe3lpg_kernel_loop_bin),
 	},
 	{}
 };
-- 
2.34.1