Skip to contentSkip to conversation

s390x/tcg: Implement Vector-Enhancements Facility 2

PATCH In review David Miller 4 participants 19 messages Mar 23, 2022 – Apr 28, 2022

lore
Share & tools
lore
#0 lore raw

v5 cover s390x/tcg: Implement Vector-Enhancements Facility 2

Implement Vector-Enhancements Facility 2 for s390x

resolves: https://gitlab.com/qemu-project/qemu/-/issues/738

implements:

    VECTOR LOAD ELEMENTS REVERSED               (VLER)
    VECTOR LOAD BYTE REVERSED ELEMENTS          (VLBR)
    VECTOR LOAD BYTE REVERSED ELEMENT           (VLEBRH, VLEBRF, VLEBRG)
    VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO  (VLLEBRZ)

VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE (VLBRREP)
VECTOR STORE ELEMENTS REVERSED (VSTER)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTBR)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTEBRH, VSTEBRF, VSTEBRG)
VECTOR SHIFT LEFT DOUBLE BY BIT (VSLD)
VECTOR SHIFT RIGHT DOUBLE BY BIT (VSRD)
VECTOR STRING SEARCH (VSTRS)

modifies:
VECTOR FP CONVERT FROM FIXED (VCFPS)
VECTOR FP CONVERT FROM LOGICAL (VCFPL)
VECTOR FP CONVERT TO FIXED (VCSFP)
VECTOR FP CONVERT TO LOGICAL (VCLFP)
VECTOR SHIFT LEFT (VSL)
VECTOR SHIFT RIGHT ARITHMETIC (VSRA)
VECTOR SHIFT RIGHT LOGICAL (VSRL)

David Miller (9):
tcg: Implement tcg_gen_{h,w}swap_{i32,i64} target/s390x: vxeh2: vector convert short/32b target/s390x: vxeh2: vector string search target/s390x: vxeh2: Update for changes to vector shifts target/s390x: vxeh2: vector shift double by bit target/s390x: vxeh2: vector {load, store} elements reversed target/s390x: vxeh2: vector {load, store} byte reversed elements target/s390x: vxeh2: vector {load, store} byte reversed element target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model tests/tcg/s390x: Tests for Vector Enhancements Facility 2 target/s390x: Fix writeback to v1 in helper_vstl

Richard Henderson (2):
tcg: Implement tcg_gen_{h,w}swap_{i32,i64} target/s390x: Fix writeback to v1 in helper_vstl

 include/tcg/tcg-op.h                 |   6 +
 target/s390x/gen-features.c          |   2 +
 target/s390x/helper.h                |  13 +
 target/s390x/tcg/insn-data.def       |  40 ++-
 target/s390x/tcg/translate.c         |   3 +-
 target/s390x/tcg/translate_vx.c.inc  | 461 ++++++++++++++++++++++++---
 target/s390x/tcg/vec_fpu_helper.c    |  31 ++
 target/s390x/tcg/vec_helper.c        |   2 -
 target/s390x/tcg/vec_int_helper.c    |  55 ++++
 target/s390x/tcg/vec_string_helper.c |  99 ++++++
 tcg/tcg-op.c                         |  30 ++
 tests/tcg/s390x/Makefile.target      |   8 +
 tests/tcg/s390x/vx.h                 |  19 ++
 tests/tcg/s390x/vxeh2_vcvt.c         |  88 +++++
 tests/tcg/s390x/vxeh2_vlstr.c        | 139 ++++++++
 tests/tcg/s390x/vxeh2_vs.c           |  93 ++++++
 16 files changed, 1034 insertions(+), 55 deletions(-)
 create mode 100644 tests/tcg/s390x/vx.h
 create mode 100644 tests/tcg/s390x/vxeh2_vcvt.c
 create mode 100644 tests/tcg/s390x/vxeh2_vlstr.c
 create mode 100644 tests/tcg/s390x/vxeh2_vs.c
Signature · 1 line
2.34.1
#1 lore raw

PATCH v5 1/11 tcg: Implement tcg_gen_{h,w}swap_{i32,i64}

From: Richard Henderson <[email protected]>

Swap half-words (16-bit) and words (32-bit) within a larger value. Mirrors functions of the same names within include/qemu/bitops.h.

---
 include/tcg/tcg-op.h |  6 ++++++
 tcg/tcg-op.c         | 30 ++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)
include/tcg/tcg-op.h +6 -0
index caa0a63612..b09b8b4a05 100644
@@ -332,6 +332,7 @@ void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags);
 void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg);
 void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
 void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
@@ -531,6 +532,8 @@ void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
 void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
 void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg);
 void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
 void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
@@ -1077,6 +1080,8 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t);
 #define tcg_gen_bswap32_tl tcg_gen_bswap32_i64
 #define tcg_gen_bswap64_tl tcg_gen_bswap64_i64
 #define tcg_gen_bswap_tl tcg_gen_bswap64_i64
+#define tcg_gen_hswap_tl tcg_gen_hswap_i64
+#define tcg_gen_wswap_tl tcg_gen_wswap_i64
 #define tcg_gen_concat_tl_i64 tcg_gen_concat32_i64
 #define tcg_gen_extr_i64_tl tcg_gen_extr32_i64
 #define tcg_gen_andc_tl tcg_gen_andc_i64
@@ -1192,6 +1197,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t);
 #define tcg_gen_bswap16_tl tcg_gen_bswap16_i32
 #define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S)
 #define tcg_gen_bswap_tl tcg_gen_bswap32_i32
+#define tcg_gen_hswap_tl tcg_gen_hswap_i32
 #define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
 #define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
 #define tcg_gen_andc_tl tcg_gen_andc_i32
tcg/tcg-op.c +30 -0
index 65e1c94c2d..ae336ff6c2 100644
@@ -1056,6 +1056,12 @@ void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg)
     }
 }
 
+void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    /* Swapping 2 16-bit elements is a rotate. */
+    tcg_gen_rotli_i32(ret, arg, 16);
+}
+
 void tcg_gen_smin_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b)
 {
     tcg_gen_movcond_i32(TCG_COND_LT, ret, a, b, a, b);
@@ -1792,6 +1798,30 @@ void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg)
     }
 }
 
+void tcg_gen_hswap_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    uint64_t m = 0x0000ffff0000ffffull;
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    /* See include/qemu/bitops.h, hswap64. */
+    tcg_gen_rotli_i64(t1, arg, 32);
+    tcg_gen_andi_i64(t0, t1, m);
+    tcg_gen_shli_i64(t0, t0, 16);
+    tcg_gen_shri_i64(t1, t1, 16);
+    tcg_gen_andi_i64(t1, t1, m);
+    tcg_gen_or_i64(ret, t0, t1);
+
+    tcg_temp_free_i64(t0);
+    tcg_temp_free_i64(t1);
+}
+
+void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    /* Swapping 2 32-bit elements is a rotate. */
+    tcg_gen_rotli_i64(ret, arg, 32);
+}
+
 void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg)
 {
     if (TCG_TARGET_REG_BITS == 32) {
Signature · 1 line
2.34.1
#2 lore raw

PATCH v5 2/11 target/s390x: vxeh2: vector convert short/32b

In reply to David Miller
---
 target/s390x/helper.h               |  4 +++
 target/s390x/tcg/translate_vx.c.inc | 44 ++++++++++++++++++++++++++---
 target/s390x/tcg/vec_fpu_helper.c   | 31 ++++++++++++++++++++
 3 files changed, 75 insertions(+), 4 deletions(-)
target/s390x/helper.h +4 -0
index 69f69cf718..7cbcbd7f0b 100644
@@ -275,6 +275,10 @@ DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32
 DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfche128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vfche128_cc, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdg32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcdlg32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vcgd32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vclgd32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
target/s390x/tcg/translate_vx.c.inc +40 -4

63 lines not on this page · raw message

target/s390x/tcg/vec_fpu_helper.c +31 -0
index 1a77993471..6834dbc540 100644
@@ -176,6 +176,30 @@ static void vop128_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
     *v1 = tmp;
 }
 
+static float32 vcdg32(float32 a, float_status *s)
+{
+    return int32_to_float32(a, s);
+}
+
+static float32 vcdlg32(float32 a, float_status *s)
+{
+    return uint32_to_float32(a, s);
+}
+
+static float32 vcgd32(float32 a, float_status *s)
+{
+    const float32 tmp = float32_to_int32(a, s);
+
+    return float32_is_any_nan(a) ? INT32_MIN : tmp;
+}
+
+static float32 vclgd32(float32 a, float_status *s)
+{
+    const float32 tmp = float32_to_uint32(a, s);
+
+    return float32_is_any_nan(a) ? 0 : tmp;
+}
+
 static float64 vcdg64(float64 a, float_status *s)
 {
     return int64_to_float64(a, s);
@@ -211,6 +235,9 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env,   \
     vop##BITS##_2(v1, v2, env, se, XxC, erm, FN, GETPC());                     \
 }
 
+#define DEF_GVEC_VOP2_32(NAME)                                                 \
+DEF_GVEC_VOP2_FN(NAME, NAME##32, 32)
+
 #define DEF_GVEC_VOP2_64(NAME)                                                 \
 DEF_GVEC_VOP2_FN(NAME, NAME##64, 64)
 
@@ -219,6 +246,10 @@ DEF_GVEC_VOP2_FN(NAME, float32_##OP, 32)                                       \
 DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)                                       \
 DEF_GVEC_VOP2_FN(NAME, float128_##OP, 128)
 
+DEF_GVEC_VOP2_32(vcdg)
+DEF_GVEC_VOP2_32(vcdlg)
+DEF_GVEC_VOP2_32(vcgd)
+DEF_GVEC_VOP2_32(vclgd)
 DEF_GVEC_VOP2_64(vcdg)
 DEF_GVEC_VOP2_64(vcdlg)
 DEF_GVEC_VOP2_64(vcgd)
Signature · 1 line
2.34.1
#3 lore raw

PATCH v5 3/11 target/s390x: vxeh2: vector string search

In reply to David Miller
---
 target/s390x/helper.h                |  6 ++
 target/s390x/tcg/insn-data.def       |  2 +
 target/s390x/tcg/translate.c         |  3 +-
 target/s390x/tcg/translate_vx.c.inc  | 25 +++++++
 target/s390x/tcg/vec_string_helper.c | 99 ++++++++++++++++++++++++++++
 5 files changed, 134 insertions(+), 1 deletion(-)
target/s390x/helper.h +6 -0
index 7cbcbd7f0b..7412130883 100644
@@ -246,6 +246,12 @@ DEF_HELPER_6(gvec_vstrc_cc32, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_6(gvec_vstrc_cc_rt8, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_6(gvec_vstrc_cc_rt16, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_8, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_16, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_32, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_zs8, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_zs16, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_6(gvec_vstrs_zs32, void, ptr, cptr, cptr, cptr, env, i32)
 
 /* === Vector Floating-Point Instructions */
 DEF_HELPER_FLAGS_5(gvec_vfa32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
target/s390x/tcg/insn-data.def +2 -0
index 6c8a8b229f..46add91a0e 100644
@@ -1246,6 +1246,8 @@
     F(0xe75c, VISTR,   VRR_a, V,   0, 0, 0, 0, vistr, 0, IF_VEC)
 /* VECTOR STRING RANGE COMPARE */
     F(0xe78a, VSTRC,   VRR_d, V,   0, 0, 0, 0, vstrc, 0, IF_VEC)
+/* VECTOR STRING SEARCH */
+    F(0xe78b, VSTRS,   VRR_d, VE2, 0, 0, 0, 0, vstrs, 0, IF_VEC)
 
 /* === Vector Floating-Point Instructions */
 
target/s390x/tcg/translate.c +2 -1
index 904b51542f..d9ac29573d 100644
@@ -6222,7 +6222,8 @@ enum DisasInsnEnum {
 #define FAC_PCI         S390_FEAT_ZPCI /* z/PCI facility */
 #define FAC_AIS         S390_FEAT_ADAPTER_INT_SUPPRESSION
 #define FAC_V           S390_FEAT_VECTOR /* vector facility */
-#define FAC_VE          S390_FEAT_VECTOR_ENH /* vector enhancements facility 1 */
+#define FAC_VE          S390_FEAT_VECTOR_ENH  /* vector enhancements facility 1 */
+#define FAC_VE2         S390_FEAT_VECTOR_ENH2 /* vector enhancements facility 2 */
 #define FAC_MIE2        S390_FEAT_MISC_INSTRUCTION_EXT2 /* miscellaneous-instruction-extensions facility 2 */
 #define FAC_MIE3        S390_FEAT_MISC_INSTRUCTION_EXT3 /* miscellaneous-instruction-extensions facility 3 */
 
target/s390x/tcg/translate_vx.c.inc +25 -0
index ea28e40d4f..29e4dd78a8 100644
@@ -2497,6 +2497,31 @@ static DisasJumpType op_vstrc(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
+static DisasJumpType op_vstrs(DisasContext *s, DisasOps *o)
+{
+    typedef void (*helper_vstrs)(TCGv_ptr, TCGv_ptr, TCGv_ptr,
+                                 TCGv_ptr, TCGv_ptr, TCGv_i32);
+    static const helper_vstrs fns[3][2] = {
+        { gen_helper_gvec_vstrs_8, gen_helper_gvec_vstrs_zs8 },
+        { gen_helper_gvec_vstrs_16, gen_helper_gvec_vstrs_zs16 },
+        { gen_helper_gvec_vstrs_32, gen_helper_gvec_vstrs_zs32 },
+    };
+    const uint8_t es = get_field(s, m5);
+    const uint8_t m6 = get_field(s, m6);
+    const bool zs = extract32(m6, 1, 1);
+
+    if (es > ES_32 || m6 & ~2) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    gen_gvec_4_ptr(get_field(s, v1), get_field(s, v2),
+                   get_field(s, v3), get_field(s, v4),
+                   cpu_env, 0, fns[es][zs]);
+    set_cc_static(s);
+    return DISAS_NEXT;
+}
+
 static DisasJumpType op_vfa(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m4);
target/s390x/tcg/vec_string_helper.c +99 -0

102 lines not on this page · raw message

Signature · 1 line
2.34.1
#4 lore raw

PATCH v5 4/11 target/s390x: vxeh2: Update for changes to vector shifts

In reply to David Miller
---
 target/s390x/helper.h               |  3 ++
 target/s390x/tcg/insn-data.def      | 12 ++---
 target/s390x/tcg/translate_vx.c.inc | 75 ++++++++++++-----------------
 target/s390x/tcg/vec_int_helper.c   | 55 +++++++++++++++++++++
 4 files changed, 95 insertions(+), 50 deletions(-)
target/s390x/helper.h +3 -0
index 7412130883..bf33d86f74 100644
@@ -203,8 +203,11 @@ DEF_HELPER_FLAGS_3(gvec_vpopct16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_verim8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_verim16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vsl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_vsl_ve2, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vsra, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_vsra_ve2, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vsrl, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_vsrl_ve2, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vscbi16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_4(gvec_vtm, void, ptr, cptr, env, i32)
target/s390x/tcg/insn-data.def +6 -6
index 46add91a0e..f487a64abf 100644
@@ -1204,19 +1204,19 @@
     F(0xe778, VESRLV,  VRR_c, V,   0, 0, 0, 0, vesv, 0, IF_VEC)
     F(0xe738, VESRL,   VRS_a, V,   la2, 0, 0, 0, ves, 0, IF_VEC)
 /* VECTOR SHIFT LEFT */
-    F(0xe774, VSL,     VRR_c, V,   0, 0, 0, 0, vsl, 0, IF_VEC)
+    E(0xe774, VSL,     VRR_c, V,   0, 0, 0, 0, vsl, 0, 0, IF_VEC)
 /* VECTOR SHIFT LEFT BY BYTE */
-    F(0xe775, VSLB,    VRR_c, V,   0, 0, 0, 0, vsl, 0, IF_VEC)
+    E(0xe775, VSLB,    VRR_c, V,   0, 0, 0, 0, vsl, 0, 1, IF_VEC)
 /* VECTOR SHIFT LEFT DOUBLE BY BYTE */
     F(0xe777, VSLDB,   VRI_d, V,   0, 0, 0, 0, vsldb, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC */
-    F(0xe77e, VSRA,    VRR_c, V,   0, 0, 0, 0, vsra, 0, IF_VEC)
+    E(0xe77e, VSRA,    VRR_c, V,   0, 0, 0, 0, vsra, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC BY BYTE */
-    F(0xe77f, VSRAB,   VRR_c, V,   0, 0, 0, 0, vsra, 0, IF_VEC)
+    E(0xe77f, VSRAB,   VRR_c, V,   0, 0, 0, 0, vsra, 0, 1, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL */
-    F(0xe77c, VSRL,    VRR_c, V,   0, 0, 0, 0, vsrl, 0, IF_VEC)
+    E(0xe77c, VSRL,    VRR_c, V,   0, 0, 0, 0, vsrl, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
-    F(0xe77d, VSRLB,   VRR_c, V,   0, 0, 0, 0, vsrl, 0, IF_VEC)
+    E(0xe77d, VSRLB,   VRR_c, V,   0, 0, 0, 0, vsrl, 0, 1, IF_VEC)
 /* VECTOR SUBTRACT */
     F(0xe7f7, VS,      VRR_c, V,   0, 0, 0, 0, vs, 0, IF_VEC)
 /* VECTOR SUBTRACT COMPUTE BORROW INDICATION */
target/s390x/tcg/translate_vx.c.inc +31 -44

94 lines not on this page · raw message

target/s390x/tcg/vec_int_helper.c +55 -0

73 lines not on this page · raw message

Signature · 1 line
2.34.1
#5 lore raw

PATCH v5 5/11 target/s390x: vxeh2: vector shift double by bit

In reply to David Miller
---
 target/s390x/tcg/insn-data.def      |  6 +++-
 target/s390x/tcg/translate_vx.c.inc | 55 +++++++++++++++++++++++++----
 2 files changed, 53 insertions(+), 8 deletions(-)
target/s390x/tcg/insn-data.def +5 -1
index f487a64abf..98a31a557d 100644
@@ -1207,12 +1207,16 @@
     E(0xe774, VSL,     VRR_c, V,   0, 0, 0, 0, vsl, 0, 0, IF_VEC)
 /* VECTOR SHIFT LEFT BY BYTE */
     E(0xe775, VSLB,    VRR_c, V,   0, 0, 0, 0, vsl, 0, 1, IF_VEC)
+/* VECTOR SHIFT LEFT DOUBLE BY BIT */
+    E(0xe786, VSLD,    VRI_d, VE2, 0, 0, 0, 0, vsld, 0, 0, IF_VEC)
 /* VECTOR SHIFT LEFT DOUBLE BY BYTE */
-    F(0xe777, VSLDB,   VRI_d, V,   0, 0, 0, 0, vsldb, 0, IF_VEC)
+    E(0xe777, VSLDB,   VRI_d, V,   0, 0, 0, 0, vsld, 0, 1, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC */
     E(0xe77e, VSRA,    VRR_c, V,   0, 0, 0, 0, vsra, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT ARITHMETIC BY BYTE */
     E(0xe77f, VSRAB,   VRR_c, V,   0, 0, 0, 0, vsra, 0, 1, IF_VEC)
+/* VECTOR SHIFT RIGHT DOUBLE BY BIT */
+    F(0xe787, VSRD,    VRI_d, VE2, 0, 0, 0, 0, vsrd, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL */
     E(0xe77c, VSRL,    VRR_c, V,   0, 0, 0, 0, vsrl, 0, 0, IF_VEC)
 /* VECTOR SHIFT RIGHT LOGICAL BY BYTE */
target/s390x/tcg/translate_vx.c.inc +48 -7

70 lines not on this page · raw message

Signature · 1 line
2.34.1
#6 lore raw

PATCH v5 6/11 target/s390x: vxeh2: vector {load, store} elements reversed

In reply to David Miller
---
 target/s390x/tcg/insn-data.def      |  4 ++
 target/s390x/tcg/translate_vx.c.inc | 84 +++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+)
target/s390x/tcg/insn-data.def +4 -0
index 98a31a557d..b524541a7d 100644
@@ -1037,6 +1037,8 @@
     E(0xe741, VLEIH,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_16, IF_VEC)
     E(0xe743, VLEIF,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_32, IF_VEC)
     E(0xe742, VLEIG,   VRI_a, V,   0, 0, 0, 0, vlei, 0, ES_64, IF_VEC)
+/* VECTOR LOAD ELEMENTS REVERSED */
+    F(0xe607, VLER,    VRX,   VE2, la2, 0, 0, 0, vler, 0, IF_VEC)
 /* VECTOR LOAD GR FROM VR ELEMENT */
     F(0xe721, VLGV,    VRS_c, V,   la2, 0, r1, 0, vlgv, 0, IF_VEC)
 /* VECTOR LOAD LOGICAL ELEMENT AND ZERO */
@@ -1082,6 +1084,8 @@
     E(0xe709, VSTEH,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_16, IF_VEC)
     E(0xe70b, VSTEF,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_32, IF_VEC)
     E(0xe70a, VSTEG,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_64, IF_VEC)
+/* VECTOR STORE ELEMENTS REVERSED */
+    F(0xe60f, VSTER,   VRX,   VE2, la2, 0, 0, 0, vster, 0, IF_VEC)
 /* VECTOR STORE MULTIPLE */
     F(0xe73e, VSTM,    VRS_a, V,   la2, 0, 0, 0, vstm, 0, IF_VEC)
 /* VECTOR STORE WITH LENGTH */
target/s390x/tcg/translate_vx.c.inc +84 -0

96 lines not on this page · raw message

Signature · 1 line
2.34.1
#7 lore raw

PATCH v5 7/11 target/s390x: vxeh2: vector {load, store} byte reversed elements

In reply to David Miller
---
 target/s390x/tcg/insn-data.def      |   4 +
 target/s390x/tcg/translate_vx.c.inc | 113 ++++++++++++++++++++++++++++
 2 files changed, 117 insertions(+)
target/s390x/tcg/insn-data.def +4 -0
index b524541a7d..ee6e1dc9e5 100644
@@ -1027,6 +1027,8 @@
     F(0xe756, VLR,     VRR_a, V,   0, 0, 0, 0, vlr, 0, IF_VEC)
 /* VECTOR LOAD AND REPLICATE */
     F(0xe705, VLREP,   VRX,   V,   la2, 0, 0, 0, vlrep, 0, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENTS */
+    F(0xe606, VLBR,    VRX,   VE2, la2, 0, 0, 0, vlbr, 0, IF_VEC)
 /* VECTOR LOAD ELEMENT */
     E(0xe700, VLEB,    VRX,   V,   la2, 0, 0, 0, vle, 0, ES_8, IF_VEC)
     E(0xe701, VLEH,    VRX,   V,   la2, 0, 0, 0, vle, 0, ES_16, IF_VEC)
@@ -1079,6 +1081,8 @@
     F(0xe75f, VSEG,    VRR_a, V,   0, 0, 0, 0, vseg, 0, IF_VEC)
 /* VECTOR STORE */
     F(0xe70e, VST,     VRX,   V,   la2, 0, 0, 0, vst, 0, IF_VEC)
+/* VECTOR STORE BYTE REVERSED ELEMENTS */
+    F(0xe60e, VSTBR,    VRX,   VE2, la2, 0, 0, 0, vstbr, 0, IF_VEC)
 /* VECTOR STORE ELEMENT */
     E(0xe708, VSTEB,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_8, IF_VEC)
     E(0xe709, VSTEH,   VRX,   V,   la2, 0, 0, 0, vste, 0, ES_16, IF_VEC)
target/s390x/tcg/translate_vx.c.inc +113 -0

125 lines not on this page · raw message

Signature · 1 line
2.34.1
#8 lore raw

Re: [PATCH v5 07/11] target/s390x: vxeh2: vector {load, store} byte reversed elements

Quoted 21 lines
target/s390x/tcg/translate_vx.c.inc +21 -0
+static DisasJumpType op_vlbr(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s, m3);
+    TCGv_i64 t0, t1;
+
+    if (es < ES_16 || es > ES_128) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+
+
+    if (es == ES_128) {
+        tcg_gen_qemu_ld_i64(t1, o->addr1, get_mem_index(s), MO_LEUQ);
+        gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+        tcg_gen_qemu_ld_i64(t0, o->addr1, get_mem_index(s), MO_LEUQ);
+        goto write;
+    }
+

target/s390x/tcg/translate_vx.c.inc static DisasJumpType op_vlrep(DisasContext *s, DisasOps *o) · line 490

Quoted 10 lines
target/s390x/tcg/translate_vx.c.inc +10 -0
+    /* Begin with byte reversed doublewords... */
+    tcg_gen_qemu_ld_i64(t0, o->addr1, get_mem_index(s), MO_LEUQ);
+    gen_addi_and_wrap_i64(s, o->addr1, o->addr1, 8);
+    tcg_gen_qemu_ld_i64(t1, o->addr1, get_mem_index(s), MO_LEUQ);
+
+    /*
+     * For 16 and 32-bit elements, the doubleword bswap also reversed
+     * the order of the elements.  Perform a larger order swap to put
+     * them back into place.  For the 128-bit "element", finish the
+     * bswap by swapping the doublewords.

The last sentence still needs to go.

[...]

Quoted 21 lines
target/s390x/tcg/translate_vx.c.inc +21 -0
+static DisasJumpType op_vstbr(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s, m3);
+    TCGv_i64 t0, t1;
+
+    if (es < ES_16 || es > ES_128) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    /* Probe write access before actually modifying memory */
+    gen_helper_probe_write_access(cpu_env, o->addr1, tcg_constant_i64(16));
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i64();
+
+
+    if (es == ES_128) {
+        read_vec_element_i64(t1, get_field(s, v1), 0, ES_64);
+        read_vec_element_i64(t0, get_field(s, v1), 1, ES_64);
+        goto write;

target/s390x/tcg/translate_vx.c.inc static DisasJumpType op_vst(DisasContext *s, DisasOps *o) · line 1087

Quoted 10 lines
target/s390x/tcg/translate_vx.c.inc +10 -0
+    }
+
+    read_vec_element_i64(t0, get_field(s, v1), 0, ES_64);
+    read_vec_element_i64(t1, get_field(s, v1), 1, ES_64);
+
+    /*
+     * For 16 and 32-bit elements, the doubleword bswap below will
+     * reverse the order of the elements.  Perform a larger order
+     * swap to put them back into place.  For the 128-bit "element",
+     * finish the bswap by swapping the doublewords.

Dito.

I assume Thomas can fixup when applying.

Signature · 3 lines
Thanks,

David / dhildenb
#9 lore raw

PATCH v5 8/11 target/s390x: vxeh2: vector {load, store} byte reversed element

In reply to David Miller
---
 target/s390x/tcg/insn-data.def      | 12 ++++
 target/s390x/tcg/translate_vx.c.inc | 85 +++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)
target/s390x/tcg/insn-data.def +12 -0
index ee6e1dc9e5..5e448bb2c4 100644
@@ -1027,6 +1027,14 @@
     F(0xe756, VLR,     VRR_a, V,   0, 0, 0, 0, vlr, 0, IF_VEC)
 /* VECTOR LOAD AND REPLICATE */
     F(0xe705, VLREP,   VRX,   V,   la2, 0, 0, 0, vlrep, 0, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT */
+    E(0xe601, VLEBRH,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_16, IF_VEC)
+    E(0xe603, VLEBRF,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_32, IF_VEC)
+    E(0xe602, VLEBRG,  VRX,   VE2, la2, 0, 0, 0, vlebr, 0, ES_64, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE */
+    F(0xe605, VLBRREP, VRX,   VE2, la2, 0, 0, 0, vlbrrep, 0, IF_VEC)
+/* VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO */
+    F(0xe604, VLLEBRZ, VRX,   VE2, la2, 0, 0, 0, vllebrz, 0, IF_VEC)
 /* VECTOR LOAD BYTE REVERSED ELEMENTS */
     F(0xe606, VLBR,    VRX,   VE2, la2, 0, 0, 0, vlbr, 0, IF_VEC)
 /* VECTOR LOAD ELEMENT */
@@ -1081,6 +1089,10 @@
     F(0xe75f, VSEG,    VRR_a, V,   0, 0, 0, 0, vseg, 0, IF_VEC)
 /* VECTOR STORE */
     F(0xe70e, VST,     VRX,   V,   la2, 0, 0, 0, vst, 0, IF_VEC)
+/* VECTOR STORE BYTE REVERSED ELEMENT */
+    E(0xe609, VSTEBRH,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_16, IF_VEC)
+    E(0xe60b, VSTEBRF,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_32, IF_VEC)
+    E(0xe60a, VSTEBRG,  VRX,   VE2, la2, 0, 0, 0, vstebr, 0, ES_64, IF_VEC)
 /* VECTOR STORE BYTE REVERSED ELEMENTS */
     F(0xe60e, VSTBR,    VRX,   VE2, la2, 0, 0, 0, vstbr, 0, IF_VEC)
 /* VECTOR STORE ELEMENT */
target/s390x/tcg/translate_vx.c.inc +85 -0

97 lines not on this page · raw message

Signature · 1 line
2.34.1
#10 lore raw

PATCH v5 9/11 target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model

In reply to David Miller
---
 target/s390x/gen-features.c | 2 ++
 1 file changed, 2 insertions(+)
target/s390x/gen-features.c +2 -0
index 22846121c4..499a3b10a8 100644
@@ -740,7 +740,9 @@ static uint16_t qemu_V6_2[] = {
 
 static uint16_t qemu_LATEST[] = {
     S390_FEAT_MISC_INSTRUCTION_EXT3,
+    S390_FEAT_VECTOR_ENH2,
 };
+
 /* add all new definitions before this point */
 static uint16_t qemu_MAX[] = {
     /* generates a dependency warning, leave it out for now */
Signature · 1 line
2.34.1
#11 lore raw

Re: [PATCH v5 09/11] target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model

I am sending v5 now as I'm away from my desk until Sunday. As I'm unsure whether or not this just needs a V7_0 and the patch shown as an example isn't a direct correlation : I've left it out for now.
I will dig into it further Monday March 28th.

Thanks
- David Miller

Quoted 24 lines · David Miller
---
 target/s390x/gen-features.c | 2 ++
 1 file changed, 2 insertions(+)
target/s390x/gen-features.c +2 -1
index 22846121c4..499a3b10a8 100644
@@ -740,7 +740,9 @@ static uint16_t qemu_V6_2[] = {
 
 static uint16_t qemu_LATEST[] = {
     S390_FEAT_MISC_INSTRUCTION_EXT3,
+    S390_FEAT_VECTOR_ENH2,
 };
+
 /* add all new definitions before this point */
 static uint16_t qemu_MAX[] = {
     /* generates a dependency warning, leave it out for now */
--

2.34.1

#12 lore raw

Re: [PATCH v5 09/11] target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model

Quoted 5 lines · David Miller

I am sending v5 now as I'm away from my desk until Sunday. As I'm unsure whether or not this just needs a V7_0 and the patch shown as an example isn't a direct correlation : I've left it out for now.
I will dig into it further Monday March 28th.

We can tackle this after the 7.0 release, then basing it on the new compat machines and most probably on [1].

Should be easy to adjust.

[1] https://lkml.kernel.org/r/[email protected]

Signature · 3 lines
Thanks,

David / dhildenb
#13 lore raw

PATCH v5 10/11 tests/tcg/s390x: Tests for Vector Enhancements Facility 2

In reply to David Miller
---
 tests/tcg/s390x/Makefile.target |   8 ++
 tests/tcg/s390x/vx.h            |  19 +++++
 tests/tcg/s390x/vxeh2_vcvt.c    |  88 ++++++++++++++++++++
 tests/tcg/s390x/vxeh2_vlstr.c   | 139 ++++++++++++++++++++++++++++++++
 tests/tcg/s390x/vxeh2_vs.c      |  93 +++++++++++++++++++++
 5 files changed, 347 insertions(+)
 create mode 100644 tests/tcg/s390x/vx.h
 create mode 100644 tests/tcg/s390x/vxeh2_vcvt.c
 create mode 100644 tests/tcg/s390x/vxeh2_vlstr.c
 create mode 100644 tests/tcg/s390x/vxeh2_vs.c
tests/tcg/s390x/Makefile.target +8 -0
index 8c9b6a13ce..921a056dd1 100644
@@ -16,6 +16,14 @@ TESTS+=shift
 TESTS+=trap
 TESTS+=signals-s390x
 
+VECTOR_TESTS=vxeh2_vs
+VECTOR_TESTS+=vxeh2_vcvt
+VECTOR_TESTS+=vxeh2_vlstr
+
+TESTS+=$(VECTOR_TESTS)
+
+$(VECTOR_TESTS): CFLAGS+=-march=z15 -O2
+
 ifneq ($(HAVE_GDB_BIN),)
 GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py
 
tests/tcg/s390x/vx.h new file +19 -0
new file mode 100644
index 0000000000..2e66f8b714
@@ -0,0 +1,19 @@
+#ifndef QEMU_TESTS_S390X_VX_H
+#define QEMU_TESTS_S390X_VX_H
+
+typedef union S390Vector {
+    uint64_t d[2];  /* doubleword */
+    uint32_t w[4];  /* word */
+    uint16_t h[8];  /* halfword */
+    uint8_t  b[16]; /* byte */
+    float    f[4];  /* float32 */
+    double   fd[2]; /* float64 */
+    __uint128_t v;
+} S390Vector;
+
+#define ES8  0
+#define ES16 1
+#define ES32 2
+#define ES64 3
+
+#endif
\ No newline at end of file
tests/tcg/s390x/vxeh2_vcvt.c new file +88 -0

88 lines not on this page · raw message

tests/tcg/s390x/vxeh2_vlstr.c new file +139 -0

139 lines not on this page · raw message

tests/tcg/s390x/vxeh2_vs.c new file +93 -0

93 lines not on this page · raw message

Signature · 1 line
2.34.1
#14 lore raw

PATCH v5 11/11 target/s390x: Fix writeback to v1 in helper_vstl

In reply to David Miller

From: Richard Henderson <[email protected]>

Fixes 0e0a5b49ad58 ("s390x/tcg: Implement VECTOR STORE WITH LENGTH")
---
 target/s390x/tcg/vec_helper.c | 2 --
 1 file changed, 2 deletions(-)
target/s390x/tcg/vec_helper.c +0 -2
index ededf13cf0..48d86722b2 100644
@@ -200,7 +200,6 @@ void HELPER(vstl)(CPUS390XState *env, const void *v1, uint64_t addr,
         addr = wrap_address(env, addr + 8);
         cpu_stq_data_ra(env, addr, s390_vec_read_element64(v1, 1), GETPC());
     } else {
-        S390Vector tmp = {};
         int i;
 
         for (i = 0; i < bytes; i++) {
@@ -209,6 +208,5 @@ void HELPER(vstl)(CPUS390XState *env, const void *v1, uint64_t addr,
             cpu_stb_data_ra(env, addr, byte, GETPC());
             addr = wrap_address(env, addr + 1);
         }
-        *(S390Vector *)v1 = tmp;
     }
 }
Signature · 1 line
2.34.1
#15 lore raw
In reply to David Miller

Am 23.03.22 um 14:57 schrieb David Miller:

Quoted 40 lines

Implement Vector-Enhancements Facility 2 for s390x

resolves: https://gitlab.com/qemu-project/qemu/-/issues/738

implements:

     VECTOR LOAD ELEMENTS REVERSED               (VLER)
     VECTOR LOAD BYTE REVERSED ELEMENTS          (VLBR)
     VECTOR LOAD BYTE REVERSED ELEMENT           (VLEBRH, VLEBRF, VLEBRG)
     VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO  (VLLEBRZ)

VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE (VLBRREP)
VECTOR STORE ELEMENTS REVERSED (VSTER)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTBR)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTEBRH, VSTEBRF, VSTEBRG)
VECTOR SHIFT LEFT DOUBLE BY BIT (VSLD)
VECTOR SHIFT RIGHT DOUBLE BY BIT (VSRD)
VECTOR STRING SEARCH (VSTRS)

modifies:
VECTOR FP CONVERT FROM FIXED (VCFPS)
VECTOR FP CONVERT FROM LOGICAL (VCFPL)
VECTOR FP CONVERT TO FIXED (VCSFP)
VECTOR FP CONVERT TO LOGICAL (VCLFP)
VECTOR SHIFT LEFT (VSL)
VECTOR SHIFT RIGHT ARITHMETIC (VSRA)
VECTOR SHIFT RIGHT LOGICAL (VSRL)

David Miller (9):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: vxeh2: vector convert short/32b
   target/s390x: vxeh2: vector string search
   target/s390x: vxeh2: Update for changes to vector shifts
   target/s390x: vxeh2: vector shift double by bit
   target/s390x: vxeh2: vector {load, store} elements reversed
   target/s390x: vxeh2: vector {load, store} byte reversed elements
   target/s390x: vxeh2: vector {load, store} byte reversed element
   target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model
   tests/tcg/s390x: Tests for Vector Enhancements Facility 2
   target/s390x: Fix writeback to v1 in helper_vstl
Quoted 3 lines

Richard Henderson (2):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: Fix writeback to v1 in helper_vstl

I guess we can now re-do this series against 7.1-devel (qemu/master) which does have the machine compat changes. Apart from that this should be ready now?

#16 lore raw
Quoted 41 lines · Christian Borntraeger

Am 23.03.22 um 14:57 schrieb David Miller:

Quoted 40 lines

Implement Vector-Enhancements Facility 2 for s390x

resolves: https://gitlab.com/qemu-project/qemu/-/issues/738

implements:

     VECTOR LOAD ELEMENTS REVERSED               (VLER)
     VECTOR LOAD BYTE REVERSED ELEMENTS          (VLBR)
     VECTOR LOAD BYTE REVERSED ELEMENT           (VLEBRH, VLEBRF, VLEBRG)
     VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO  (VLLEBRZ)

VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE (VLBRREP)
VECTOR STORE ELEMENTS REVERSED (VSTER)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTBR)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTEBRH, VSTEBRF, VSTEBRG)
VECTOR SHIFT LEFT DOUBLE BY BIT (VSLD)
VECTOR SHIFT RIGHT DOUBLE BY BIT (VSRD)
VECTOR STRING SEARCH (VSTRS)

modifies:
VECTOR FP CONVERT FROM FIXED (VCFPS)
VECTOR FP CONVERT FROM LOGICAL (VCFPL)
VECTOR FP CONVERT TO FIXED (VCSFP)
VECTOR FP CONVERT TO LOGICAL (VCLFP)
VECTOR SHIFT LEFT (VSL)
VECTOR SHIFT RIGHT ARITHMETIC (VSRA)
VECTOR SHIFT RIGHT LOGICAL (VSRL)

David Miller (9):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: vxeh2: vector convert short/32b
   target/s390x: vxeh2: vector string search
   target/s390x: vxeh2: Update for changes to vector shifts
   target/s390x: vxeh2: vector shift double by bit
   target/s390x: vxeh2: vector {load, store} elements reversed
   target/s390x: vxeh2: vector {load, store} byte reversed elements
   target/s390x: vxeh2: vector {load, store} byte reversed element
   target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model
   tests/tcg/s390x: Tests for Vector Enhancements Facility 2
   target/s390x: Fix writeback to v1 in helper_vstl
Quoted 8 lines
Quoted 3 lines

Richard Henderson (2):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: Fix writeback to v1 in helper_vstl

I guess we can now re-do this series against 7.1-devel (qemu/master) which does have the machine compat changes. Apart from that this should be ready now?

Yes, I think so. I can respin with the proper compat changes if requested.

Signature · 3 lines
Thanks,

David / dhildenb
Tested-by
#17 lore raw
Quoted 47 lines · David Hildenbrand
Quoted 46 lines · Christian Borntraeger

Am 23.03.22 um 14:57 schrieb David Miller:

Quoted 43 lines

Implement Vector-Enhancements Facility 2 for s390x

resolves: https://gitlab.com/qemu-project/qemu/-/issues/738

implements:

      VECTOR LOAD ELEMENTS REVERSED               (VLER)
      VECTOR LOAD BYTE REVERSED ELEMENTS          (VLBR)
      VECTOR LOAD BYTE REVERSED ELEMENT           (VLEBRH, VLEBRF, VLEBRG)
      VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO  (VLLEBRZ)

VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE (VLBRREP)
VECTOR STORE ELEMENTS REVERSED (VSTER)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTBR)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTEBRH, VSTEBRF, VSTEBRG)
VECTOR SHIFT LEFT DOUBLE BY BIT (VSLD)
VECTOR SHIFT RIGHT DOUBLE BY BIT (VSRD)
VECTOR STRING SEARCH (VSTRS)

modifies:
VECTOR FP CONVERT FROM FIXED (VCFPS)
VECTOR FP CONVERT FROM LOGICAL (VCFPL)
VECTOR FP CONVERT TO FIXED (VCSFP)
VECTOR FP CONVERT TO LOGICAL (VCLFP)
VECTOR SHIFT LEFT (VSL)
VECTOR SHIFT RIGHT ARITHMETIC (VSRA)
VECTOR SHIFT RIGHT LOGICAL (VSRL)

David Miller (9):

    tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
    target/s390x: vxeh2: vector convert short/32b
    target/s390x: vxeh2: vector string search
    target/s390x: vxeh2: Update for changes to vector shifts
    target/s390x: vxeh2: vector shift double by bit
    target/s390x: vxeh2: vector {load, store} elements reversed
    target/s390x: vxeh2: vector {load, store} byte reversed elements
    target/s390x: vxeh2: vector {load, store} byte reversed element
    target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model
    tests/tcg/s390x: Tests for Vector Enhancements Facility 2
    target/s390x: Fix writeback to v1 in helper_vstl

Richard Henderson (2):

    tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
    target/s390x: Fix writeback to v1 in helper_vstl
Quoted 5 lines
Quoted 3 lines

I guess we can now re-do this series against 7.1-devel (qemu/master) which does have the machine compat changes. Apart from that this should be ready now?

Yes, I think so. I can respin with the proper compat changes if requested.

FWIW, I played with the series a little bit, and did not spot any obvious problems anymore, so feel free to add:

If you send a v6 with the compat stuff fixed, I can queue it for my next s390x pull request.

Thomas

#18 lore raw
In reply to David Hildenbrand

I'm playing catch up a bit here, as I was out sick for a few days. It would be very much appreciated if you could do so, as I'm not familiar with what is required.

Thanks
- David Miller

Quoted 59 lines · David Hildenbrand
Quoted 41 lines · Christian Borntraeger

Am 23.03.22 um 14:57 schrieb David Miller:

Quoted 40 lines

Implement Vector-Enhancements Facility 2 for s390x

resolves: https://gitlab.com/qemu-project/qemu/-/issues/738

implements:

     VECTOR LOAD ELEMENTS REVERSED               (VLER)
     VECTOR LOAD BYTE REVERSED ELEMENTS          (VLBR)
     VECTOR LOAD BYTE REVERSED ELEMENT           (VLEBRH, VLEBRF, VLEBRG)
     VECTOR LOAD BYTE REVERSED ELEMENT AND ZERO  (VLLEBRZ)

VECTOR LOAD BYTE REVERSED ELEMENT AND REPLICATE (VLBRREP)
VECTOR STORE ELEMENTS REVERSED (VSTER)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTBR)
VECTOR STORE BYTE REVERSED ELEMENTS (VSTEBRH, VSTEBRF, VSTEBRG)
VECTOR SHIFT LEFT DOUBLE BY BIT (VSLD)
VECTOR SHIFT RIGHT DOUBLE BY BIT (VSRD)
VECTOR STRING SEARCH (VSTRS)

modifies:
VECTOR FP CONVERT FROM FIXED (VCFPS)
VECTOR FP CONVERT FROM LOGICAL (VCFPL)
VECTOR FP CONVERT TO FIXED (VCSFP)
VECTOR FP CONVERT TO LOGICAL (VCLFP)
VECTOR SHIFT LEFT (VSL)
VECTOR SHIFT RIGHT ARITHMETIC (VSRA)
VECTOR SHIFT RIGHT LOGICAL (VSRL)

David Miller (9):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: vxeh2: vector convert short/32b
   target/s390x: vxeh2: vector string search
   target/s390x: vxeh2: Update for changes to vector shifts
   target/s390x: vxeh2: vector shift double by bit
   target/s390x: vxeh2: vector {load, store} elements reversed
   target/s390x: vxeh2: vector {load, store} byte reversed elements
   target/s390x: vxeh2: vector {load, store} byte reversed element
   target/s390x: add S390_FEAT_VECTOR_ENH2 to qemu CPU model
   tests/tcg/s390x: Tests for Vector Enhancements Facility 2
   target/s390x: Fix writeback to v1 in helper_vstl
Quoted 8 lines
Quoted 3 lines

Richard Henderson (2):

   tcg: Implement tcg_gen_{h,w}swap_{i32,i64}
   target/s390x: Fix writeback to v1 in helper_vstl

I guess we can now re-do this series against 7.1-devel (qemu/master) which does have the machine compat changes. Apart from that this should be ready now?

Yes, I think so. I can respin with the proper compat changes if requested.

--
Thanks,

David / dhildenb