tests/tcg/xtensa: add fp0 div and sqrt tests

Test exact division/sqrt DFPU sequences.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>

2 files changed, 158 insertions, 0 deletions

diff --git a/tests/tcg/xtensa/test_fp0_div.S b/tests/tcg/xtensa/test_fp0_div.S
new file mode 100644
index 0000000..c3e7ad7
--- /dev/null
+++ b/tests/tcg/xtensa/test_fp0_div.S
@@ -0,0 +1,82 @@
+#include "macros.inc"
+#include "fpu.h"
+
+test_suite fp0_div
+
+#if XCHAL_HAVE_FP_DIV
+
+.macro  divs_seq q, a, b, r, y, y0, an, bn, e, ex
+    div0.s      \y0, \b
+    nexp01.s    \bn, \b
+    const.s     \e, 1
+    maddn.s     \e, \bn, \y0
+    mov.s       \y, \y0
+    mov.s       \ex, \b
+    nexp01.s    \an, \a
+    maddn.s     \y, \e, \y0
+    const.s     \e, 1
+    const.s     \q, 0
+    neg.s       \r, \an
+    maddn.s     \e, \bn, \y
+    maddn.s     \q, \r, \y0
+    mkdadj.s    \ex, \a
+    maddn.s     \y, \e, \y
+    maddn.s     \r, \bn, \q
+    const.s     \e, 1
+    maddn.s     \e, \bn, \y
+    maddn.s     \q, \r, \y
+    neg.s       \r, \an
+    maddn.s     \y, \e, \y
+    maddn.s     \r, \bn, \q
+    addexpm.s   \q, \ex
+    addexp.s    \y, \ex
+    divn.s      \q, \r, \y
+.endm
+
+.macro div_s fr0, fr1, fr2
+    divs_seq    \fr0, \fr1, \fr2, f9, f10, f11, f12, f13, f14, f15
+.endm
+
+.macro movfp fr, v
+    movi        a2, \v
+    wfr         \fr, a2
+.endm
+
+.macro check_res fr, r, sr
+    rfr         a2, \fr
+    dump        a2
+    movi        a3, \r
+    assert      eq, a2, a3
+    rur         a2, fsr
+    movi        a3, \sr
+    assert      eq, a2, a3
+.endm
+
+test div_s
+    movi        a2, 1
+    wsr         a2, cpenable
+
+    test_op2    div_s, f0, f1, f2, 0x40000000, 0x40400000, \
+        0x3f2aaaab, 0x3f2aaaaa, 0x3f2aaaab, 0x3f2aaaaa, \
+             FSR_I,      FSR_I,      FSR_I,      FSR_I
+    test_op2    div_s, f3, f4, f5, F32_1, F32_0, \
+        F32_PINF, F32_PINF, F32_PINF, F32_PINF, \
+           FSR_Z,    FSR_Z,    FSR_Z,    FSR_Z
+    test_op2    div_s, f6, f7, f8, F32_0, F32_0, \
+        F32_DNAN, F32_DNAN, F32_DNAN, F32_DNAN, \
+           FSR_V,    FSR_V,    FSR_V,    FSR_V
+
+    /* MAX_FLOAT / 0.5 = +inf/MAX_FLOAT  */
+    test_op2    div_s, f0, f1, f2, F32_MAX, F32_0_5, \
+        F32_PINF, F32_MAX, F32_PINF, F32_MAX, \
+          FSR_OI,  FSR_OI,   FSR_OI,  FSR_OI
+
+    /* 0.5 / MAX_FLOAT = denorm  */
+    test_op2    div_s, f0, f1, f2, F32_0_5, F32_MAX, \
+        0x00100000, 0x00100000, 0x00100001, 0x00100000, \
+            FSR_UI,     FSR_UI,     FSR_UI,     FSR_UI
+test_end
+
+#endif
+
+test_suite_end
diff --git a/tests/tcg/xtensa/test_fp0_sqrt.S b/tests/tcg/xtensa/test_fp0_sqrt.S
new file mode 100644
index 0000000..585973d
--- /dev/null
+++ b/tests/tcg/xtensa/test_fp0_sqrt.S
@@ -0,0 +1,76 @@
+#include "macros.inc"
+#include "fpu.h"
+
+test_suite fp0_sqrt
+
+#if XCHAL_HAVE_FP_SQRT
+
+.macro  sqrt_seq r, a, y, t1, hn, h2, t5, h
+    sqrt0.s     \y, \a
+    const.s     \t1, 0
+    maddn.s     \t1, \y, \y
+    nexp01.s    \hn, \a
+    const.s     \r, 3
+    addexp.s    \hn, \r
+    maddn.s     \r, \t1, \hn
+    nexp01.s    \t1, \a
+    neg.s       \h2, \t1
+    maddn.s     \y, \r, \y
+    const.s     \r, 0
+    const.s     \t5, 0
+    const.s     \h, 0
+    maddn.s     \r, \h2, \y
+    maddn.s     \t5, \y, \hn
+    const.s     \hn, 3
+    maddn.s     \h, \hn, \y
+    maddn.s     \t1, \r, \r
+    maddn.s     \hn, \t5, \y
+    neg.s       \y, \h
+    maddn.s     \r, \t1, \y
+    maddn.s     \h, \hn, \h
+    mksadj.s    \y, \a
+    nexp01.s    \a, \a
+    maddn.s     \a, \r, \r
+    neg.s       \t1, \h
+    addexpm.s   \r, \y
+    addexp.s    \t1, \y
+    divn.s      \r, \a, \t1
+.endm
+
+.macro sqrt_s fr0, fr1
+    sqrt_seq    \fr0, \fr1, f10, f11, f12, f13, f14, f15
+.endm
+
+.macro movfp fr, v
+    movi        a2, \v
+    wfr         \fr, a2
+.endm
+
+.macro check_res fr, r, sr
+    rfr         a2, \fr
+    dump        a2
+    movi        a3, \r
+    assert      eq, a2, a3
+    rur         a2, fsr
+    movi        a3, \sr
+    assert      eq, a2, a3
+.endm
+
+test sqrt_s
+    movi        a2, 1
+    wsr         a2, cpenable
+
+    test_op1    sqrt_s, f0, f1, 0x40000000, \
+        0x3fb504f3, 0x3fb504f3, 0x3fb504f4, 0x3fb504f3, \
+             FSR_I,      FSR_I,      FSR_I,      FSR_I
+    test_op1    sqrt_s, f3, f4, F32_1, \
+        F32_1, F32_1, F32_1, F32_1, \
+        FSR__, FSR__, FSR__, FSR__
+    test_op1    sqrt_s, f6, f7, F32_MINUS | F32_1, \
+        F32_DNAN, F32_DNAN, F32_DNAN, F32_DNAN, \
+           FSR_V,    FSR_V,    FSR_V,    FSR_V
+test_end
+
+#endif
+
+test_suite_end