[Qemu-devel] [RFC PATCH v4 71/75] target/i386: convert pmuludq/pmaddwd helpers to gvec style

[Jan Bobek <jan.bobek@gmail.com>]

Make these helpers suitable for use with tcg_gen_gvec_* functions.
---
 target/i386/ops_sse.h        | 27 +++++++++++++++++----------
 target/i386/ops_sse_header.h |  4 ++--
 target/i386/translate.c      | 18 ++++++++----------
 3 files changed, 27 insertions(+), 22 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 1661bd7c64..384a835662 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -485,22 +485,29 @@ void glue(helper_pavgw, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
     glue(clear_high, SUFFIX)(d, oprsz, maxsz);
 }
 
-void glue(helper_pmuludq, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pmuludq, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
 {
-    d->Q(0) = (uint64_t)s->L(0) * (uint64_t)d->L(0);
-#if SHIFT == 1
-    d->Q(1) = (uint64_t)s->L(2) * (uint64_t)d->L(2);
-#endif
+    const intptr_t oprsz = simd_oprsz(desc);
+    const intptr_t maxsz = simd_maxsz(desc);
+
+    for (intptr_t i = 0; i * sizeof(uint64_t) < oprsz; ++i) {
+        const uint64_t t = (uint64_t)a->L(2 * i) * (uint64_t)b->L(2 * i);
+        d->Q(i) = t;
+    }
+    glue(clear_high, SUFFIX)(d, oprsz, maxsz);
 }
 
-void glue(helper_pmaddwd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
+void glue(helper_pmaddwd, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
 {
-    int i;
+    const intptr_t oprsz = simd_oprsz(desc);
+    const intptr_t maxsz = simd_maxsz(desc);
 
-    for (i = 0; i < (2 << SHIFT); i++) {
-        d->L(i) = (int16_t)s->W(2 * i) * (int16_t)d->W(2 * i) +
-            (int16_t)s->W(2 * i + 1) * (int16_t)d->W(2 * i + 1);
+    for (intptr_t i = 0; i * sizeof(uint32_t) < oprsz; ++i) {
+        const int32_t t0 = (int32_t)a->W(2 * i + 0) * (int32_t)b->W(2 * i + 0);
+        const int32_t t1 = (int32_t)a->W(2 * i + 1) * (int32_t)b->W(2 * i + 1);
+        d->L(i) = t0 + t1;
     }
+    glue(clear_high, SUFFIX)(d, oprsz, maxsz);
 }
 
 #if SHIFT == 0
diff --git a/target/i386/ops_sse_header.h b/target/i386/ops_sse_header.h
index b5e8aae897..18d39ca649 100644
--- a/target/i386/ops_sse_header.h
+++ b/target/i386/ops_sse_header.h
@@ -71,8 +71,8 @@ DEF_HELPER_3(glue(pavgusb, SUFFIX), void, env, Reg, Reg)
 #endif
 DEF_HELPER_4(glue(pavgw, SUFFIX), void, Reg, Reg, Reg, i32)
 
-DEF_HELPER_3(glue(pmuludq, SUFFIX), void, env, Reg, Reg)
-DEF_HELPER_3(glue(pmaddwd, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_4(glue(pmuludq, SUFFIX), void, Reg, Reg, Reg, i32)
+DEF_HELPER_4(glue(pmaddwd, SUFFIX), void, Reg, Reg, Reg, i32)
 
 DEF_HELPER_3(glue(psadbw, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_4(glue(maskmov, SUFFIX), void, env, Reg, Reg, tl)
diff --git a/target/i386/translate.c b/target/i386/translate.c
index 77b2e18f34..55607db09c 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -2806,8 +2806,6 @@ static const SSEFunc_0_epp sse_op_table1[256][4] = {
     [0xe6] = { NULL, gen_helper_cvttpd2dq, gen_helper_cvtdq2pd, gen_helper_cvtpd2dq },
     [0xe7] = { SSE_SPECIAL , SSE_SPECIAL },  /* movntq, movntq */
     [0xf0] = { NULL, NULL, NULL, SSE_SPECIAL }, /* lddqu */
-    [0xf4] = MMX_OP2(pmuludq),
-    [0xf5] = MMX_OP2(pmaddwd),
     [0xf6] = MMX_OP2(psadbw),
     [0xf7] = { (SSEFunc_0_epp)gen_helper_maskmov_mmx,
                (SSEFunc_0_epp)gen_helper_maskmov_xmm }, /* XXX: casts */
@@ -6129,10 +6127,10 @@ DEF_GEN_INSN3_GVEC(vpmulhuw, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmulhuw
 DEF_GEN_INSN3_HELPER_EPP(pmuldq, pmuldq_xmm, Vdq, Vdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmuldq, pmuldq_xmm, Vdq, Hdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmuldq, pmuldq_xmm, Vqq, Hqq, Wqq)
-DEF_GEN_INSN3_HELPER_EPP(pmuludq, pmuludq_mmx, Pq, Pq, Qq)
-DEF_GEN_INSN3_HELPER_EPP(pmuludq, pmuludq_xmm, Vdq, Vdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmuludq, pmuludq_xmm, Vdq, Hdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmuludq, pmuludq_xmm, Vqq, Hqq, Wqq)
+DEF_GEN_INSN3_GVEC(pmuludq, Pq, Pq, Qq, 3_ool, MM_OPRSZ, MM_MAXSZ, pmuludq_mmx)
+DEF_GEN_INSN3_GVEC(pmuludq, Vdq, Vdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmuludq_xmm)
+DEF_GEN_INSN3_GVEC(vpmuludq, Vdq, Hdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmuludq_xmm)
+DEF_GEN_INSN3_GVEC(vpmuludq, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmuludq_xmm)
 DEF_GEN_INSN3_HELPER_EPP(pmulhrsw, pmulhrsw_mmx, Pq, Pq, Qq)
 DEF_GEN_INSN3_HELPER_EPP(pmulhrsw, pmulhrsw_xmm, Vdq, Vdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmulhrsw, pmulhrsw_xmm, Vdq, Hdq, Wdq)
@@ -6147,10 +6145,10 @@ DEF_GEN_INSN3_HELPER_EPP(mulss, mulss, Vd, Vd, Wd)
 DEF_GEN_INSN3_HELPER_EPP(vmulss, mulss, Vd, Hd, Wd)
 DEF_GEN_INSN3_HELPER_EPP(mulsd, mulsd, Vq, Vq, Wq)
 DEF_GEN_INSN3_HELPER_EPP(vmulsd, mulsd, Vq, Hq, Wq)
-DEF_GEN_INSN3_HELPER_EPP(pmaddwd, pmaddwd_mmx, Pq, Pq, Qq)
-DEF_GEN_INSN3_HELPER_EPP(pmaddwd, pmaddwd_xmm, Vdq, Vdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmaddwd, pmaddwd_xmm, Vdq, Hdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmaddwd, pmaddwd_xmm, Vqq, Hqq, Wqq)
+DEF_GEN_INSN3_GVEC(pmaddwd, Pq, Pq, Qq, 3_ool, MM_OPRSZ, MM_MAXSZ, pmaddwd_mmx)
+DEF_GEN_INSN3_GVEC(pmaddwd, Vdq, Vdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmaddwd_xmm)
+DEF_GEN_INSN3_GVEC(vpmaddwd, Vdq, Hdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmaddwd_xmm)
+DEF_GEN_INSN3_GVEC(vpmaddwd, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, pmaddwd_xmm)
 DEF_GEN_INSN3_HELPER_EPP(pmaddubsw, pmaddubsw_mmx, Pq, Pq, Qq)
 DEF_GEN_INSN3_HELPER_EPP(pmaddubsw, pmaddubsw_xmm, Vdq, Vdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmaddubsw, pmaddubsw_xmm, Vdq, Hdq, Wdq)
-- 
2.20.1