@@ -219,11 +219,6 @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *);
int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *);
int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
-/*
- * 8 x 8 -> 16 vector polynomial multiply where the inputs are
- * in the low 8 bits of each 16-bit element
-*/
-uint64_t pmull_h(uint64_t op1, uint64_t op2);
/*
* 16 x 16 -> 32 vector polynomial multiply where the inputs are
* in the low 16 bits of each 32-bit element
@@ -26,6 +26,7 @@
#include "exec/exec-all.h"
#include "tcg/tcg.h"
#include "fpu/softfloat.h"
+#include "crypto/clmul.h"
static uint16_t mve_eci_mask(CPUARMState *env)
{
@@ -984,15 +985,12 @@ DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL)
* Polynomial multiply. We can always do this generating 64 bits
* of the result at a time, so we don't need to use DO_2OP_L.
*/
-#define VMULLPH_MASK 0x00ff00ff00ff00ffULL
#define VMULLPW_MASK 0x0000ffff0000ffffULL
-#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK)
-#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8)
#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK)
#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16)
-DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH)
-DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH)
+DO_2OP(vmullpbh, 8, uint64_t, clmul_8x4_even)
+DO_2OP(vmullpth, 8, uint64_t, clmul_8x4_odd)
DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW)
DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW)
@@ -23,6 +23,7 @@
#include "tcg/tcg-gvec-desc.h"
#include "fpu/softfloat.h"
#include "qemu/int128.h"
+#include "crypto/clmul.h"
#include "vec_internal.h"
/*
@@ -1986,21 +1987,11 @@ void HELPER(gvec_ushl_h)(void *vd, void *vn, void *vm, uint32_t desc)
*/
void HELPER(gvec_pmul_b)(void *vd, void *vn, void *vm, uint32_t desc)
{
- intptr_t i, j, opr_sz = simd_oprsz(desc);
+ intptr_t i, 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;
+ d[i] = clmul_8x8_low(n[i], m[i]);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
@@ -2038,22 +2029,6 @@ void HELPER(gvec_pmull_q)(void *vd, void *vn, void *vm, uint32_t desc)
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-/*
- * 8x8->16 polynomial multiply.
- *
- * The byte inputs are expanded to (or extracted from) half-words.
- * Note that neon and sve2 get the inputs from different positions.
- * This allows 4 bytes to be processed in parallel with uint64_t.
- */
-
-static uint64_t expand_byte_to_half(uint64_t x)
-{
- return (x & 0x000000ff)
- | ((x & 0x0000ff00) << 8)
- | ((x & 0x00ff0000) << 16)
- | ((x & 0xff000000) << 24);
-}
-
uint64_t pmull_w(uint64_t op1, uint64_t op2)
{
uint64_t result = 0;
@@ -2067,30 +2042,14 @@ uint64_t pmull_w(uint64_t op1, uint64_t op2)
return result;
}
-uint64_t pmull_h(uint64_t op1, uint64_t op2)
-{
- uint64_t result = 0;
- int i;
- for (i = 0; i < 8; ++i) {
- uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff;
- result ^= op2 & mask;
- op1 >>= 1;
- op2 <<= 1;
- }
- return result;
-}
-
void HELPER(neon_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc)
{
int hi = simd_data(desc);
uint64_t *d = vd, *n = vn, *m = vm;
- uint64_t nn = n[hi], mm = m[hi];
-
- d[0] = pmull_h(expand_byte_to_half(nn), expand_byte_to_half(mm));
- nn >>= 32;
- mm >>= 32;
- d[1] = pmull_h(expand_byte_to_half(nn), expand_byte_to_half(mm));
+ Int128 r = clmul_8x8_packed(n[hi], m[hi]);
+ d[0] = int128_getlo(r);
+ d[1] = int128_gethi(r);
clear_tail(d, 16, simd_maxsz(desc));
}
@@ -2101,11 +2060,13 @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc)
intptr_t i, 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] >> shift) & 0x00ff00ff00ff00ffull;
- uint64_t mm = (m[i] >> shift) & 0x00ff00ff00ff00ffull;
+ for (i = 0; i < opr_sz / 8; i += 2) {
+ Int128 nn = int128_make128(n[i] >> shift, n[i + 1] >> shift);
+ Int128 mm = int128_make128(m[i] >> shift, m[i + 1] >> shift);
+ Int128 r = clmul_8x8_even(nn, mm);
- d[i] = pmull_h(nn, mm);
+ d[0] = int128_getlo(r);
+ d[1] = int128_gethi(r);
}
}
Use generic routines for 8-bit carry-less multiply. Remove our local version of pmull_h. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/vec_internal.h | 5 --- target/arm/tcg/mve_helper.c | 8 ++--- target/arm/tcg/vec_helper.c | 63 +++++++---------------------------- 3 files changed, 15 insertions(+), 61 deletions(-)