[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240610-xtheadvector-v2-8-97a48613ad64@rivosinc.com>
Date: Mon, 10 Jun 2024 15:56:45 -0700
From: Charlie Jenkins <charlie@...osinc.com>
To: Conor Dooley <conor@...nel.org>, Rob Herring <robh@...nel.org>,
Krzysztof Kozlowski <krzk+dt@...nel.org>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>, Albert Ou <aou@...s.berkeley.edu>,
Jisheng Zhang <jszhang@...nel.org>, Chen-Yu Tsai <wens@...e.org>,
Jernej Skrabec <jernej.skrabec@...il.com>,
Samuel Holland <samuel@...lland.org>, Jonathan Corbet <corbet@....net>,
Shuah Khan <shuah@...nel.org>, Guo Ren <guoren@...nel.org>,
Evan Green <evan@...osinc.com>, Andy Chiu <andy.chiu@...ive.com>,
Jessica Clarke <jrtc27@...c27.com>
Cc: linux-riscv@...ts.infradead.org, devicetree@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-sunxi@...ts.linux.dev,
linux-doc@...r.kernel.org, linux-kselftest@...r.kernel.org,
Charlie Jenkins <charlie@...osinc.com>, Heiko Stuebner <heiko@...ech.de>
Subject: [PATCH v2 08/13] riscv: Add xtheadvector instruction definitions
xtheadvector uses different encodings than standard vector for
vsetvli and vector loads/stores. Write the instruction formats to be
used in assembly code.
Co-developed-by: Heiko Stuebner <heiko@...ech.de>
Signed-off-by: Charlie Jenkins <charlie@...osinc.com>
---
arch/riscv/include/asm/vendor_extensions/thead.h | 26 ++++++++++++++++++++++++
1 file changed, 26 insertions(+)
diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h
index 48421d1553ad..27a253a20ab8 100644
--- a/arch/riscv/include/asm/vendor_extensions/thead.h
+++ b/arch/riscv/include/asm/vendor_extensions/thead.h
@@ -13,4 +13,30 @@
extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead;
+/* Extension specific helpers */
+
+/*
+ * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older
+ * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for
+ * vsetvli t4, x0, e8, m8, d1
+ */
+#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t"
+#define THEAD_VSETVLI_X0X0E8M8D1 ".long 0x00307057\n\t"
+
+/*
+ * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same
+ * encoding as the standard vse8.v and vle8.v, compilers seem to optimize
+ * the call resulting in a different encoding and then using a value for
+ * the "mop" field that is not part of vector-0.7.1
+ * So encode specific variants for vstate_save and _restore.
+ */
+#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t"
+#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t"
+#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t"
+#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t"
+#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t"
+#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t"
+#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t"
+#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t"
+
#endif
--
2.44.0
Powered by blists - more mailing lists