Commit c48f1f45 authored by Lizhi Hou's avatar Lizhi Hou
Browse files

accel/amdxdna: Add hardware specific attributes



Add three hardware specific attributes to describe device capabilities:
  hwctx_limit: The maximum number of hardware context supported.
  max_tops: The maximum TOPS supported.
  curr_tops: The TOPS achievable with the current power and frequency
             configuration.

Reviewed-by: default avatarMario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: default avatarLizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20251104062546.833771-1-lizhi.hou@amd.com
parent a3fcddaa
Loading
Loading
Loading
Loading
+3 −0
Original line number Diff line number Diff line
@@ -195,6 +195,8 @@ struct amdxdna_dev_hdl {
	u32				clk_gating;
	u32				npuclk_freq;
	u32				hclk_freq;
	u32				max_tops;
	u32				curr_tops;

	/* Mailbox and the management channel */
	struct mailbox			*mbox;
@@ -246,6 +248,7 @@ struct amdxdna_dev_priv {
	u32				mbox_dev_addr;
	/* If mbox_size is 0, use BAR size. See MBOX_SIZE macro */
	u32				mbox_size;
	u32				hwctx_limit;
	u32				sram_dev_addr;
	struct aie2_bar_off_pair	sram_offs[SRAM_MAX_INDEX];
	struct aie2_bar_off_pair	psp_regs_off[PSP_MAX_REGS];
+11 −0
Original line number Diff line number Diff line
@@ -23,6 +23,13 @@
#define AIE2_SMU_SET_SOFT_DPMLEVEL	0x7
#define AIE2_SMU_SET_HARD_DPMLEVEL	0x8

#define NPU4_DPM_TOPS(ndev, dpm_level) \
({ \
	typeof(ndev) _ndev = ndev; \
	(4096 * (_ndev)->total_col * \
	 (_ndev)->priv->dpm_clk_tbl[dpm_level].hclk / 1000000); \
})

static int aie2_smu_exec(struct amdxdna_dev_hdl *ndev, u32 reg_cmd,
			 u32 reg_arg, u32 *out)
{
@@ -84,6 +91,8 @@ int npu1_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
	amdxdna_pm_suspend_put(ndev->xdna);
	ndev->hclk_freq = freq;
	ndev->dpm_level = dpm_level;
	ndev->max_tops = 2 * ndev->total_col;
	ndev->curr_tops = ndev->max_tops * freq / 1028;

	XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
		 ndev->npuclk_freq, ndev->hclk_freq);
@@ -121,6 +130,8 @@ int npu4_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level)
	ndev->npuclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].npuclk;
	ndev->hclk_freq = ndev->priv->dpm_clk_tbl[dpm_level].hclk;
	ndev->dpm_level = dpm_level;
	ndev->max_tops = NPU4_DPM_TOPS(ndev, ndev->max_dpm_level);
	ndev->curr_tops = NPU4_DPM_TOPS(ndev, dpm_level);

	XDNA_DBG(ndev->xdna, "MP-NPU clock %d, H clock %d\n",
		 ndev->npuclk_freq, ndev->hclk_freq);
+1 −0
Original line number Diff line number Diff line
@@ -79,6 +79,7 @@ static const struct amdxdna_dev_priv npu1_dev_priv = {
	.mbox_dev_addr  = NPU1_MBOX_BAR_BASE,
	.mbox_size      = 0, /* Use BAR size */
	.sram_dev_addr  = NPU1_SRAM_BAR_BASE,
	.hwctx_limit    = 6,
	.sram_offs      = {
		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU1_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU1_SRAM, MPNPU_SRAM_I2X_MAILBOX_15),
+1 −0
Original line number Diff line number Diff line
@@ -72,6 +72,7 @@ static const struct amdxdna_dev_priv npu2_dev_priv = {
	.mbox_dev_addr  = NPU2_MBOX_BAR_BASE,
	.mbox_size      = 0, /* Use BAR size */
	.sram_dev_addr  = NPU2_SRAM_BAR_BASE,
	.hwctx_limit    = 16,
	.sram_offs      = {
		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU2_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
+1 −0
Original line number Diff line number Diff line
@@ -99,6 +99,7 @@ static const struct amdxdna_dev_priv npu4_dev_priv = {
	.mbox_dev_addr  = NPU4_MBOX_BAR_BASE,
	.mbox_size      = 0, /* Use BAR size */
	.sram_dev_addr  = NPU4_SRAM_BAR_BASE,
	.hwctx_limit    = 16,
	.sram_offs      = {
		DEFINE_BAR_OFFSET(MBOX_CHANN_OFF, NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_0),
		DEFINE_BAR_OFFSET(FW_ALIVE_OFF,   NPU4_SRAM, MPNPU_SRAM_X2I_MAILBOX_15),
Loading