[Qemu-devel] [RFC PATCH v4 69/75] target/i386: convert pmullw/pmulhw/pmulhuw helpers to gvec style

[Jan Bobek]

Make these helpers suitable for use with tcg_gen_gvec_* functions.

Signed-off-by: Jan Bobek <address@hidden>
---
 target/i386/ops_sse.h        | 42 ++++++++++++++++++++++++++++++------
 target/i386/ops_sse_header.h |  6 +++---
 target/i386/translate.c      | 27 +++++++++++------------
 3 files changed, 51 insertions(+), 24 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 168e581c0c..6ec116573b 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -412,20 +412,50 @@ static inline int satsw(int x)
     }
 }
 
-#define FMULLW(a, b) ((a) * (b))
 #define FMULHRW(a, b) (((int16_t)(a) * (int16_t)(b) + 0x8000) >> 16)
-#define FMULHUW(a, b) ((a) * (b) >> 16)
-#define FMULHW(a, b) ((int16_t)(a) * (int16_t)(b) >> 16)
 
 #define FAVG(a, b) (((a) + (b) + 1) >> 1)
 #endif
 
-SSE_HELPER_W(helper_pmullw, FMULLW)
+void glue(helper_pmullw, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
+{
+    const intptr_t oprsz = simd_oprsz(desc);
+    const intptr_t maxsz = simd_maxsz(desc);
+
+    for (intptr_t i = 0; i * sizeof(uint16_t) < oprsz; ++i) {
+        const uint32_t t = (uint32_t)a->W(i) * (uint32_t)b->W(i);
+        d->W(i) = t;
+    }
+    glue(clear_high, SUFFIX)(d, oprsz, maxsz);
+}
+
 #if SHIFT == 0
 SSE_HELPER_W(helper_pmulhrw, FMULHRW)
 #endif
-SSE_HELPER_W(helper_pmulhuw, FMULHUW)
-SSE_HELPER_W(helper_pmulhw, FMULHW)
+
+void glue(helper_pmulhuw, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
+{
+    const intptr_t oprsz = simd_oprsz(desc);
+    const intptr_t maxsz = simd_maxsz(desc);
+
+    for (intptr_t i = 0; i * sizeof(uint16_t) < oprsz; ++i) {
+        const uint32_t t = (uint32_t)a->W(i) * (uint32_t)b->W(i);
+        d->W(i) = t >> 16;
+    }
+    glue(clear_high, SUFFIX)(d, oprsz, maxsz);
+}
+
+void glue(helper_pmulhw, SUFFIX)(Reg *d, Reg *a, Reg *b, uint32_t desc)
+{
+    const intptr_t oprsz = simd_oprsz(desc);
+    const intptr_t maxsz = simd_maxsz(desc);
+
+    for (intptr_t i = 0; i * sizeof(uint16_t) < oprsz; ++i) {
+        const int32_t t = (int32_t)a->W(i) * (int32_t)b->W(i);
+        d->W(i) = t >> 16;
+    }
+    glue(clear_high, SUFFIX)(d, oprsz, maxsz);
+}
 
 SSE_HELPER_B(helper_pavgb, FAVG)
 SSE_HELPER_W(helper_pavgw, FAVG)
diff --git a/target/i386/ops_sse_header.h b/target/i386/ops_sse_header.h
index 724692a689..7e6411fc82 100644
--- a/target/i386/ops_sse_header.h
+++ b/target/i386/ops_sse_header.h
@@ -58,12 +58,12 @@ DEF_HELPER_3(glue(pslldqi, SUFFIX), void, Reg, Reg, i32)
 DEF_HELPER_3(glue(psrldqi, SUFFIX), void, Reg, Reg, i32)
 #endif
 
-DEF_HELPER_3(glue(pmullw, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_4(glue(pmullw, SUFFIX), void, Reg, Reg, Reg, i32)
 #if SHIFT == 0
 DEF_HELPER_3(glue(pmulhrw, SUFFIX), void, env, Reg, Reg)
 #endif
-DEF_HELPER_3(glue(pmulhuw, SUFFIX), void, env, Reg, Reg)
-DEF_HELPER_3(glue(pmulhw, SUFFIX), void, env, Reg, Reg)
+DEF_HELPER_4(glue(pmulhuw, SUFFIX), void, Reg, Reg, Reg, i32)
+DEF_HELPER_4(glue(pmulhw, SUFFIX), void, Reg, Reg, Reg, i32)
 
 DEF_HELPER_3(glue(pavgb, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_3(glue(pavgw, SUFFIX), void, env, Reg, Reg)
diff --git a/target/i386/translate.c b/target/i386/translate.c
index 03f7c6e450..79f8c1ddac 100644
--- a/target/i386/translate.c
+++ b/target/i386/translate.c
@@ -2801,13 +2801,10 @@ static const SSEFunc_0_epp sse_op_table1[256][4] = {
     [0xc4] = { SSE_SPECIAL, SSE_SPECIAL }, /* pinsrw */
     [0xc5] = { SSE_SPECIAL, SSE_SPECIAL }, /* pextrw */
     [0xd0] = { NULL, gen_helper_addsubpd, NULL, gen_helper_addsubps },
-    [0xd5] = MMX_OP2(pmullw),
     [0xd6] = { NULL, SSE_SPECIAL, SSE_SPECIAL, SSE_SPECIAL },
     [0xd7] = { SSE_SPECIAL, SSE_SPECIAL }, /* pmovmskb */
     [0xe0] = MMX_OP2(pavgb),
     [0xe3] = MMX_OP2(pavgw),
-    [0xe4] = MMX_OP2(pmulhuw),
-    [0xe5] = MMX_OP2(pmulhw),
     [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 */
@@ -6116,21 +6113,21 @@ DEF_GEN_INSN3_HELPER_EPP(addsubpd, addsubpd, Vdq, Vdq, 
Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vaddsubpd, addsubpd, Vdq, Hdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vaddsubpd, addsubpd, Vqq, Hqq, Wqq)
 
-DEF_GEN_INSN3_HELPER_EPP(pmullw, pmullw_mmx, Pq, Pq, Qq)
-DEF_GEN_INSN3_HELPER_EPP(pmullw, pmullw_xmm, Vdq, Vdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmullw, pmullw_xmm, Vdq, Hdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmullw, pmullw_xmm, Vqq, Hqq, Wqq)
+DEF_GEN_INSN3_GVEC(pmullw, Pq, Pq, Qq, 3_ool, MM_OPRSZ, MM_MAXSZ, pmullw_mmx)
+DEF_GEN_INSN3_GVEC(pmullw, Vdq, Vdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmullw_xmm)
+DEF_GEN_INSN3_GVEC(vpmullw, Vdq, Hdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmullw_xmm)
+DEF_GEN_INSN3_GVEC(vpmullw, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmullw_xmm)
 DEF_GEN_INSN3_HELPER_EPP(pmulld, pmulld_xmm, Vdq, Vdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmulld, pmulld_xmm, Vdq, Hdq, Wdq)
 DEF_GEN_INSN3_HELPER_EPP(vpmulld, pmulld_xmm, Vqq, Hqq, Wqq)
-DEF_GEN_INSN3_HELPER_EPP(pmulhw, pmulhw_mmx, Pq, Pq, Qq)
-DEF_GEN_INSN3_HELPER_EPP(pmulhw, pmulhw_xmm, Vdq, Vdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmulhw, pmulhw_xmm, Vdq, Hdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmulhw, pmulhw_xmm, Vqq, Hqq, Wqq)
-DEF_GEN_INSN3_HELPER_EPP(pmulhuw, pmulhuw_mmx, Pq, Pq, Qq)
-DEF_GEN_INSN3_HELPER_EPP(pmulhuw, pmulhuw_xmm, Vdq, Vdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmulhuw, pmulhuw_xmm, Vdq, Hdq, Wdq)
-DEF_GEN_INSN3_HELPER_EPP(vpmulhuw, pmulhuw_xmm, Vqq, Hqq, Wqq)
+DEF_GEN_INSN3_GVEC(pmulhw, Pq, Pq, Qq, 3_ool, MM_OPRSZ, MM_MAXSZ, pmulhw_mmx)
+DEF_GEN_INSN3_GVEC(pmulhw, Vdq, Vdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhw_xmm)
+DEF_GEN_INSN3_GVEC(vpmulhw, Vdq, Hdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhw_xmm)
+DEF_GEN_INSN3_GVEC(vpmulhw, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhw_xmm)
+DEF_GEN_INSN3_GVEC(pmulhuw, Pq, Pq, Qq, 3_ool, MM_OPRSZ, MM_MAXSZ, pmulhuw_mmx)
+DEF_GEN_INSN3_GVEC(pmulhuw, Vdq, Vdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhuw_xmm)
+DEF_GEN_INSN3_GVEC(vpmulhuw, Vdq, Hdq, Wdq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhuw_xmm)
+DEF_GEN_INSN3_GVEC(vpmulhuw, Vqq, Hqq, Wqq, 3_ool, XMM_OPRSZ, XMM_MAXSZ, 
pmulhuw_xmm)
 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)
-- 
2.20.1