target/arm: Convert PMUL.8 to gvec

The gvec form will be needed for implementing SVE2.

Extend the implementation to operate on uint64_t instead of uint32_t.
Use a counted inner loop instead of terminating when op1 goes to zero,
looking toward the required implementation for ARMv8.4-DIT.

Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200216214232.4230-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 30 insertions, 0 deletions

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index fcb3663903..854de0e279 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -1134,3 +1134,33 @@ void HELPER(gvec_ushl_h)(void *vd, void *vn, void *vm, uint32_t desc)
     }
     clear_tail(d, opr_sz, simd_maxsz(desc));
 }
+
+/*
+ * 8x8->8 polynomial multiply.
+ *
+ * Polynomial multiplication is like integer multiplication except the
+ * partial products are XORed, not added.
+ *
+ * TODO: expose this as a generic vector operation, as it is a common
+ * crypto building block.
+ */
+void HELPER(gvec_pmul_b)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    intptr_t i, j, opr_sz = simd_oprsz(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 8; ++i) {
+        uint64_t nn = n[i];
+        uint64_t mm = m[i];
+        uint64_t rr = 0;
+
+        for (j = 0; j < 8; ++j) {
+            uint64_t mask = (nn & 0x0101010101010101ull) * 0xff;
+            rr ^= mm & mask;
+            mm = (mm << 1) & 0xfefefefefefefefeull;
+            nn >>= 1;
+        }
+        d[i] = rr;
+    }
+    clear_tail(d, opr_sz, simd_maxsz(desc));
+}