On 7/12/22 07:27, Ilya Leoshkevich wrote:
+/*
+ * vfmin/vfmax code generation.
+ */
+extern const char vfminmax_template[];
+extern const int vfminmax_template_size;
+extern const int vfminmax_offset;
+asm(".globl vfminmax_template\n"
+ "vfminmax_template:\n"
+ "vl %v25,0(%r3)\n"
+ "vl %v26,0(%r4)\n"
+ "0: vfmax %v24,%v25,%v26,2,0,0\n"
+ "vst %v24,0(%r2)\n"
+ "br %r14\n"
+ "1: .align 4\n"
+ ".globl vfminmax_template_size\n"
+ "vfminmax_template_size: .long 1b - vfminmax_template\n"
+ ".globl vfminmax_offset\n"
+ "vfminmax_offset: .long 0b - vfminmax_template\n");
...
+
+#define VFMIN 0xEE
+#define VFMAX 0xEF
+
+static void vfminmax(unsigned char *buf, unsigned int op,
+ unsigned int m4, unsigned int m5, unsigned int m6,
+ void *v1, const void *v2, const void *v3)
+{
+ memcpy(buf, vfminmax_template, vfminmax_template_size);
+ buf[vfminmax_offset + 3] = (m6 << 4) | m5;
+ buf[vfminmax_offset + 4] &= 0x0F;
+ buf[vfminmax_offset + 4] |= (m4 << 4);
+ buf[vfminmax_offset + 5] = op;
+ ((void (*)(void *, const void *, const void *))buf)(v1, v2, v3);
+}
This works, of course. It could be simpler using EXECUTE, to store just the one
instruction and not worry about an executable mapped page, but I guess it doesn't matter.
Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
r~
