diff options
| author | Matheus Ferst <matheus.ferst@eldorado.org.br> | 2022-03-05 07:16:46 +0100 |
|---|---|---|
| committer | Cédric Le Goater <clg@kaod.org> | 2022-03-05 07:16:46 +0100 |
| commit | 63c2b746bebef3ec9de4f29d5beeea4ee809c892 (patch) | |
| tree | 7db1fa2a7e4e3c9a6ca3a6e0cad939f710586074 | |
| parent | 8189cb850728fd52cd98f5ee4640b5dc4e40239d (diff) | |
| download | qemu-63c2b746bebef3ec9de4f29d5beeea4ee809c892.zip qemu-63c2b746bebef3ec9de4f29d5beeea4ee809c892.tar.gz qemu-63c2b746bebef3ec9de4f29d5beeea4ee809c892.tar.bz2 | |
tests/tcg/ppc64le: emit bcdsub with .long when needed
Based on GCC docs[1], we use the '-mpower8-vector' flag at config-time
to detect the toolchain support to the bcdsub instruction. LLVM/Clang
supports this flag since version 3.6[2], but the instruction and related
builtins were only added in LLVM 14[3]. In the absence of other means to
detect this support at config-time, we resort to __has_builtin to
identify the presence of __builtin_bcdsub at compile-time. If the
builtin is not available, the instruction is emitted with a ".long".
[1] https://gcc.gnu.org/onlinedocs/gcc-8.3.0/gcc/PowerPC-AltiVec_002fVSX-Built-in-Functions.html
[2] https://github.com/llvm/llvm-project/commit/59eb767e11d4ffefb5f55409524e5c8416b2b0db
[3] https://github.com/llvm/llvm-project/commit/c933c2eb334660c131f4afc9d194fafb0cec0423
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Message-Id: <20220304165417.1981159-5-matheus.ferst@eldorado.org.br>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
| -rw-r--r-- | tests/tcg/ppc64le/bcdsub.c | 73 |
1 files changed, 42 insertions, 31 deletions
diff --git a/tests/tcg/ppc64le/bcdsub.c b/tests/tcg/ppc64le/bcdsub.c index 12da19b..87c8c44 100644 --- a/tests/tcg/ppc64le/bcdsub.c +++ b/tests/tcg/ppc64le/bcdsub.c @@ -9,37 +9,48 @@ #define CRF_SO (1 << 0) #define UNDEF 0 -/* - * Use GPR pairs to load the VSR values and place the resulting VSR and CR6 in - * th, tl, and cr. Note that we avoid newer instructions (e.g., mtvsrdd/mfvsrld) - * so we can run this test on POWER8 machines. - */ -#define BCDSUB(AH, AL, BH, BL, PS) \ - asm ("mtvsrd 32, %3\n\t" \ - "mtvsrd 33, %4\n\t" \ - "xxmrghd 32, 32, 33\n\t" \ - "mtvsrd 33, %5\n\t" \ - "mtvsrd 34, %6\n\t" \ - "xxmrghd 33, 33, 34\n\t" \ - "bcdsub. 0, 0, 1, %7\n\t" \ - "mfocrf %0, 0b10\n\t" \ - "mfvsrd %1, 32\n\t" \ - "xxswapd 32, 32\n\t" \ - "mfvsrd %2, 32\n\t" \ - : "=r" (cr), "=r" (th), "=r" (tl) \ - : "r" (AH), "r" (AL), "r" (BH), "r" (BL), "i" (PS) \ - : "v0", "v1", "v2"); - -#define TEST(AH, AL, BH, BL, PS, TH, TL, CR6) \ - do { \ - int cr = 0; \ - uint64_t th, tl; \ - BCDSUB(AH, AL, BH, BL, PS); \ - if (TH != UNDEF || TL != UNDEF) { \ - assert(tl == TL); \ - assert(th == TH); \ - } \ - assert((cr >> 4) == CR6); \ +#ifdef __has_builtin +#if !__has_builtin(__builtin_bcdsub) +#define NO_BUILTIN_BCDSUB +#endif +#endif + +#ifdef NO_BUILTIN_BCDSUB +#define BCDSUB(T, A, B, PS) \ + ".long 4 << 26 | (" #T ") << 21 | (" #A ") << 16 | (" #B ") << 11" \ + " | 1 << 10 | (" #PS ") << 9 | 65\n\t" +#else +#define BCDSUB(T, A, B, PS) "bcdsub. " #T ", " #A ", " #B ", " #PS "\n\t" +#endif + +#define TEST(AH, AL, BH, BL, PS, TH, TL, CR6) \ + do { \ + int cr = 0; \ + uint64_t th, tl; \ + /* \ + * Use GPR pairs to load the VSR values and place the resulting VSR and\ + * CR6 in th, tl, and cr. Note that we avoid newer instructions (e.g., \ + * mtvsrdd/mfvsrld) so we can run this test on POWER8 machines. \ + */ \ + asm ("mtvsrd 32, %3\n\t" \ + "mtvsrd 33, %4\n\t" \ + "xxmrghd 32, 32, 33\n\t" \ + "mtvsrd 33, %5\n\t" \ + "mtvsrd 34, %6\n\t" \ + "xxmrghd 33, 33, 34\n\t" \ + BCDSUB(0, 0, 1, PS) \ + "mfocrf %0, 0b10\n\t" \ + "mfvsrd %1, 32\n\t" \ + "xxswapd 32, 32\n\t" \ + "mfvsrd %2, 32\n\t" \ + : "=r" (cr), "=r" (th), "=r" (tl) \ + : "r" (AH), "r" (AL), "r" (BH), "r" (BL) \ + : "v0", "v1", "v2"); \ + if (TH != UNDEF || TL != UNDEF) { \ + assert(tl == TL); \ + assert(th == TH); \ + } \ + assert((cr >> 4) == CR6); \ } while (0) /* |