[PATCH v16 12/16] accel/rocket: add RK3576 NPU (RKNN) support

Jiaxing Hu gahing at gahingwoo.com
Sat Nov 7 22:59:13 PST 2026


Add support for the RK3576 NPU. It has two cores; each core needs six
clocks and one reset, with aclk_cbuf and hclk_cbuf on top of what the
RK3588 has.

The task number in PC_TASK_CON is 16 bits wide, not 12. BIT16, BIT17 and
BIT18 are pp_en, count_clear and last_layer_clear. Chaoyi Chen confirmed
this layout on the list:

  https://lore.kernel.org/all/4f300b78-d96d-4d98-8819-dc292b0c9b97@rock-chips.com/

The number of NPU cores is taken from the driver's own match table.

Signed-off-by: Jiaxing Hu <gahing at gahingwoo.com>
---
 drivers/accel/rocket/rocket_core.c   |  2 ++
 drivers/accel/rocket/rocket_core.h   |  3 ++-
 drivers/accel/rocket/rocket_device.c |  3 ++-
 drivers/accel/rocket/rocket_drv.c    | 14 +++++++++++---
 drivers/accel/rocket/rocket_drv.h    |  2 ++
 drivers/accel/rocket/rocket_job.c    | 20 ++++++++++++++++----
 6 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/drivers/accel/rocket/rocket_core.c b/drivers/accel/rocket/rocket_core.c
index b202d15816a3..128ebb4f19fb 100644
--- a/drivers/accel/rocket/rocket_core.c
+++ b/drivers/accel/rocket/rocket_core.c
@@ -32,6 +32,8 @@ int rocket_core_init(struct rocket_core *core)
 	core->clks[1].id = "hclk";
 	core->clks[2].id = "npu";
 	core->clks[3].id = "pclk";
+	core->clks[4].id = "aclk_cbuf";
+	core->clks[5].id = "hclk_cbuf";
 	err = devm_clk_bulk_get(dev, core->soc->num_clks, core->clks);
 	if (err)
 		return dev_err_probe(dev, err, "failed to get clocks for core %d\n", core->index);
diff --git a/drivers/accel/rocket/rocket_core.h b/drivers/accel/rocket/rocket_core.h
index bfbf5110b524..d5d353cc38e7 100644
--- a/drivers/accel/rocket/rocket_core.h
+++ b/drivers/accel/rocket/rocket_core.h
@@ -30,6 +30,7 @@
 struct rocket_soc_data {
 	unsigned int num_clks;
 	unsigned int num_resets;
+	bool task_con_16bit;
 };
 
 struct rocket_core {
@@ -42,7 +43,7 @@ struct rocket_core {
 	void __iomem *pc_iomem;
 	void __iomem *cna_iomem;
 	void __iomem *core_iomem;
-	struct clk_bulk_data clks[4];
+	struct clk_bulk_data clks[6];
 	struct reset_control_bulk_data resets[2];
 
 	struct iommu_group *iommu_group;
diff --git a/drivers/accel/rocket/rocket_device.c b/drivers/accel/rocket/rocket_device.c
index efd004194c1a..39e8b7c49896 100644
--- a/drivers/accel/rocket/rocket_device.c
+++ b/drivers/accel/rocket/rocket_device.c
@@ -9,6 +9,7 @@
 #include <linux/of.h>
 
 #include "rocket_device.h"
+#include "rocket_drv.h"
 
 struct rocket_device *rocket_device_init(struct platform_device *pdev,
 					 const struct drm_driver *rocket_drm_driver)
@@ -27,7 +28,7 @@ struct rocket_device *rocket_device_init(struct platform_device *pdev,
 	ddev = &rdev->ddev;
 	dev_set_drvdata(dev, rdev);
 
-	for_each_compatible_node(core_node, NULL, "rockchip,rk3588-rknn-core")
+	for_each_matching_node(core_node, rocket_dt_match)
 		if (of_device_is_available(core_node))
 			num_cores++;
 
diff --git a/drivers/accel/rocket/rocket_drv.c b/drivers/accel/rocket/rocket_drv.c
index 1030d8407b78..fff31c1ebe52 100644
--- a/drivers/accel/rocket/rocket_drv.c
+++ b/drivers/accel/rocket/rocket_drv.c
@@ -226,13 +226,21 @@ static void rocket_remove(struct platform_device *pdev)
 static const struct rocket_soc_data rk3588_soc_data = {
 	.num_clks = 4,
 	.num_resets = 2,
+	.task_con_16bit = false,
 };
 
-static const struct of_device_id dt_match[] = {
+static const struct rocket_soc_data rk3576_soc_data = {
+	.num_clks = 6,
+	.num_resets = 1,
+	.task_con_16bit = true,
+};
+
+const struct of_device_id rocket_dt_match[] = {
 	{ .compatible = "rockchip,rk3588-rknn-core", .data = &rk3588_soc_data },
+	{ .compatible = "rockchip,rk3576-rknn-core", .data = &rk3576_soc_data },
 	{}
 };
-MODULE_DEVICE_TABLE(of, dt_match);
+MODULE_DEVICE_TABLE(of, rocket_dt_match);
 
 static int find_core_for_dev(struct device *dev)
 {
@@ -291,7 +299,7 @@ static struct platform_driver rocket_driver = {
 	.driver	 = {
 		.name = "rocket",
 		.pm = pm_ptr(&rocket_pm_ops),
-		.of_match_table = dt_match,
+		.of_match_table = rocket_dt_match,
 	},
 };
 
diff --git a/drivers/accel/rocket/rocket_drv.h b/drivers/accel/rocket/rocket_drv.h
index 2c673bb99ccc..0cd692a66b85 100644
--- a/drivers/accel/rocket/rocket_drv.h
+++ b/drivers/accel/rocket/rocket_drv.h
@@ -6,10 +6,12 @@
 
 #include <drm/drm_mm.h>
 #include <drm/gpu_scheduler.h>
+#include <linux/device-id/of.h>
 
 #include "rocket_device.h"
 
 extern const struct dev_pm_ops rocket_pm_ops;
+extern const struct of_device_id rocket_dt_match[];
 
 struct rocket_iommu_domain {
 	struct iommu_domain *domain;
diff --git a/drivers/accel/rocket/rocket_job.c b/drivers/accel/rocket/rocket_job.c
index ea23a44b1d9e..a33c9ea694f0 100644
--- a/drivers/accel/rocket/rocket_job.c
+++ b/drivers/accel/rocket/rocket_job.c
@@ -31,6 +31,11 @@
 /* Bits 3:0 of PC_BASE_ADDRESS hold the mode selection bit and reserved bits */
 #define ROCKET_REGCMD_ALIGN	16
 
+#define RK3576_PC_TASK_CON_TASK_NUMBER(n)	((n) & 0xffff)
+#define RK3576_PC_TASK_CON_PP_EN		BIT(16)
+#define RK3576_PC_TASK_CON_COUNT_CLEAR		BIT(17)
+#define RK3576_PC_TASK_CON_LAST_LAYER_CLEAR	BIT(18)
+
 static struct rocket_job *
 to_rocket_job(struct drm_sched_job *sched_job)
 {
@@ -166,10 +171,17 @@ static void rocket_job_hw_submit(struct rocket_core *core, struct rocket_job *jo
 	rocket_pc_writel(core, INTERRUPT_MASK, PC_INTERRUPT_MASK_DPU_0 | PC_INTERRUPT_MASK_DPU_1);
 	rocket_pc_writel(core, INTERRUPT_CLEAR, PC_INTERRUPT_CLEAR_DPU_0 | PC_INTERRUPT_CLEAR_DPU_1);
 
-	rocket_pc_writel(core, TASK_CON, PC_TASK_CON_RESERVED_0(1) |
-					 PC_TASK_CON_TASK_COUNT_CLEAR(1) |
-					 PC_TASK_CON_TASK_NUMBER(1) |
-					 PC_TASK_CON_TASK_PP_EN(1));
+	if (core->soc->task_con_16bit)
+		rocket_pc_writel(core, TASK_CON,
+				 RK3576_PC_TASK_CON_LAST_LAYER_CLEAR |
+				 RK3576_PC_TASK_CON_COUNT_CLEAR |
+				 RK3576_PC_TASK_CON_PP_EN |
+				 RK3576_PC_TASK_CON_TASK_NUMBER(1));
+	else
+		rocket_pc_writel(core, TASK_CON, PC_TASK_CON_RESERVED_0(1) |
+						 PC_TASK_CON_TASK_COUNT_CLEAR(1) |
+						 PC_TASK_CON_TASK_NUMBER(1) |
+						 PC_TASK_CON_TASK_PP_EN(1));
 
 	rocket_pc_writel(core, TASK_DMA_BASE_ADDR, PC_TASK_DMA_BASE_ADDR_DMA_BASE_ADDR(0x0));
 
-- 
2.43.0




More information about the Linux-rockchip mailing list