From: "Jan Beulich" <JBeulich@suse.com>
To: xen-devel <xen-devel@lists.xenproject.org>
Cc: George Dunlap <George.Dunlap@eu.citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Wei Liu <wei.liu2@citrix.com>
Subject: [PATCH v4 33/44] x86emul: basic AVX512BW testing
Date: Tue, 25 Sep 2018 07:47:34 -0600 [thread overview]
Message-ID: <5BAA3C7602000078001EBB19@prv1-mh.provo.novell.com> (raw)
In-Reply-To: <5BAA34B502000078001EB9B6@prv1-mh.provo.novell.com>
Test various of the insns which have been implemented already.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
v4: Add __AVX512VL__ conditional around majority of OVR() additions.
Correct eq() for 1- and 2-byte cases.
v3: New.
--- a/tools/tests/x86_emulator/Makefile
+++ b/tools/tests/x86_emulator/Makefile
@@ -13,7 +13,7 @@ all: $(TARGET)
run: $(TARGET)
./$(TARGET)
-SIMD := 3dnow sse sse2 sse4 avx avx2 xop avx512f
+SIMD := 3dnow sse sse2 sse4 avx avx2 xop avx512f avx512bw
FMA := fma4 fma
SG := avx2-sg
TESTCASES := blowfish $(SIMD) $(FMA) $(SG)
@@ -63,6 +63,9 @@ xop-flts := $(avx-flts)
avx512f-vecs := 64 16 32
avx512f-ints := 4 8
avx512f-flts := 4 8
+avx512bw-vecs := $(avx512f-vecs)
+avx512bw-ints := 1 2
+avx512bw-flts :=
avx512f-opmask-vecs := 2
avx512dq-opmask-vecs := 1
--- a/tools/tests/x86_emulator/simd.c
+++ b/tools/tests/x86_emulator/simd.c
@@ -31,6 +31,10 @@ ENTRY(simd_test);
# define eq(x, y) ((BR(cmpps, _mask, x, y, 0, -1) & ALL_TRUE) == ALL_TRUE)
# elif FLOAT_SIZE == 8
# define eq(x, y) (BR(cmppd, _mask, x, y, 0, -1) == ALL_TRUE)
+# elif (INT_SIZE == 1 || UINT_SIZE == 1) && defined(__AVX512BW__)
+# define eq(x, y) (B(pcmpeqb, _mask, (vqi_t)(x), (vqi_t)(y), -1) == ALL_TRUE)
+# elif (INT_SIZE == 2 || UINT_SIZE == 2) && defined(__AVX512BW__)
+# define eq(x, y) (B(pcmpeqw, _mask, (vhi_t)(x), (vhi_t)(y), -1) == ALL_TRUE)
# elif INT_SIZE == 4 || UINT_SIZE == 4
# define eq(x, y) (B(pcmpeqd, _mask, (vsi_t)(x), (vsi_t)(y), -1) == ALL_TRUE)
# elif INT_SIZE == 8 || UINT_SIZE == 8
@@ -368,6 +372,87 @@ static inline bool _to_bool(byte_vec_t b
# define max(x, y) ((vec_t)B(pmaxuq, _mask, (vdi_t)(x), (vdi_t)(y), (vdi_t)undef(), ~0))
# define min(x, y) ((vec_t)B(pminuq, _mask, (vdi_t)(x), (vdi_t)(y), (vdi_t)undef(), ~0))
# endif
+#elif (INT_SIZE == 1 || UINT_SIZE == 1 || INT_SIZE == 2 || UINT_SIZE == 2) && \
+ defined(__AVX512BW__) && (VEC_SIZE == 64 || defined(__AVX512VL__))
+# if INT_SIZE == 1 || UINT_SIZE == 1
+# define broadcast(x) ({ \
+ vec_t t_; \
+ asm ( "%{evex%} vpbroadcastb %1, %0" \
+ : "=v" (t_) : "m" (*(char[1]){ x }) ); \
+ t_; \
+})
+# define broadcast2(x) ({ \
+ vec_t t_; \
+ asm ( "vpbroadcastb %k1, %0" : "=v" (t_) : "r" (x) ); \
+ t_; \
+})
+# if VEC_SIZE == 16
+# define interleave_hi(x, y) ((vec_t)B(punpckhbw, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define interleave_lo(x, y) ((vec_t)B(punpcklbw, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define swap(x) ((vec_t)B(pshufb, _mask, (vqi_t)(x), (vqi_t)(inv - 1), (vqi_t)undef(), ~0))
+# elif defined(__AVX512VBMI__)
+# define interleave_hi(x, y) ((vec_t)B(vpermi2varqi, _mask, (vqi_t)(x), interleave_hi, (vqi_t)(y), ~0))
+# define interleave_lo(x, y) ((vec_t)B(vpermt2varqi, _mask, interleave_lo, (vqi_t)(x), (vqi_t)(y), ~0))
+# endif
+# define mix(x, y) ((vec_t)B(movdquqi, _mask, (vqi_t)(x), (vqi_t)(y), \
+ (0b0101010101010101010101010101010101010101010101010101010101010101LL & ALL_TRUE)))
+# define shrink1(x) ((half_t)B(pmovwb, _mask, (vhi_t)(x), (vqi_half_t){}, ~0))
+# define shrink2(x) ((quarter_t)B(pmovdb, _mask, (vsi_t)(x), (vqi_quarter_t){}, ~0))
+# define shrink3(x) ((eighth_t)B(pmovqb, _mask, (vdi_t)(x), (vqi_eighth_t){}, ~0))
+# elif INT_SIZE == 2 || UINT_SIZE == 2
+# define broadcast(x) ({ \
+ vec_t t_; \
+ asm ( "%{evex%} vpbroadcastw %1, %0" \
+ : "=v" (t_) : "m" (*(short[1]){ x }) ); \
+ t_; \
+})
+# define broadcast2(x) ({ \
+ vec_t t_; \
+ asm ( "vpbroadcastw %k1, %0" : "=v" (t_) : "r" (x) ); \
+ t_; \
+})
+# if VEC_SIZE == 16
+# define interleave_hi(x, y) ((vec_t)B(punpckhwd, _mask, (vhi_t)(x), (vhi_t)(y), (vhi_t)undef(), ~0))
+# define interleave_lo(x, y) ((vec_t)B(punpcklwd, _mask, (vhi_t)(x), (vhi_t)(y), (vhi_t)undef(), ~0))
+# define swap(x) ((vec_t)B(pshufd, _mask, \
+ (vsi_t)B(pshufhw, _mask, \
+ B(pshuflw, _mask, (vhi_t)(x), 0b00011011, (vhi_t)undef(), ~0), \
+ 0b00011011, (vhi_t)undef(), ~0), \
+ 0b01001110, (vsi_t)undef(), ~0))
+# else
+# define interleave_hi(x, y) ((vec_t)B(vpermi2varhi, _mask, (vhi_t)(x), interleave_hi, (vhi_t)(y), ~0))
+# define interleave_lo(x, y) ((vec_t)B(vpermt2varhi, _mask, interleave_lo, (vhi_t)(x), (vhi_t)(y), ~0))
+# endif
+# define mix(x, y) ((vec_t)B(movdquhi, _mask, (vhi_t)(x), (vhi_t)(y), \
+ (0b01010101010101010101010101010101 & ALL_TRUE)))
+# define shrink1(x) ((half_t)B(pmovdw, _mask, (vsi_t)(x), (vhi_half_t){}, ~0))
+# define shrink2(x) ((quarter_t)B(pmovqw, _mask, (vdi_t)(x), (vhi_quarter_t){}, ~0))
+# endif
+# if INT_SIZE == 1
+# define max(x, y) ((vec_t)B(pmaxsb, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define min(x, y) ((vec_t)B(pminsb, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define widen1(x) ((vec_t)B(pmovsxbw, _mask, (vqi_half_t)(x), (vhi_t)undef(), ~0))
+# define widen2(x) ((vec_t)B(pmovsxbd, _mask, (vqi_quarter_t)(x), (vsi_t)undef(), ~0))
+# define widen3(x) ((vec_t)B(pmovsxbq, _mask, (vqi_eighth_t)(x), (vdi_t)undef(), ~0))
+# elif UINT_SIZE == 1
+# define max(x, y) ((vec_t)B(pmaxub, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define min(x, y) ((vec_t)B(pminub, _mask, (vqi_t)(x), (vqi_t)(y), (vqi_t)undef(), ~0))
+# define widen1(x) ((vec_t)B(pmovzxbw, _mask, (vqi_half_t)(x), (vhi_t)undef(), ~0))
+# define widen2(x) ((vec_t)B(pmovzxbd, _mask, (vqi_quarter_t)(x), (vsi_t)undef(), ~0))
+# define widen3(x) ((vec_t)B(pmovzxbq, _mask, (vqi_eighth_t)(x), (vdi_t)undef(), ~0))
+# elif INT_SIZE == 2
+# define max(x, y) B(pmaxsw, _mask, x, y, undef(), ~0)
+# define min(x, y) B(pminsw, _mask, x, y, undef(), ~0)
+# define mul_hi(x, y) B(pmulhw, _mask, x, y, undef(), ~0)
+# define widen1(x) ((vec_t)B(pmovsxwd, _mask, x, (vsi_t)undef(), ~0))
+# define widen2(x) ((vec_t)B(pmovsxwq, _mask, x, (vdi_t)undef(), ~0))
+# elif UINT_SIZE == 2
+# define max(x, y) ((vec_t)B(pmaxuw, _mask, (vhi_t)(x), (vhi_t)(y), (vhi_t)undef(), ~0))
+# define min(x, y) ((vec_t)B(pminuw, _mask, (vhi_t)(x), (vhi_t)(y), (vhi_t)undef(), ~0))
+# define mul_hi(x, y) ((vec_t)B(pmulhuw, _mask, (vhi_t)(x), (vhi_t)(y), (vhi_t)undef(), ~0))
+# define widen1(x) ((vec_t)B(pmovzxwd, _mask, (vhi_half_t)(x), (vsi_t)undef(), ~0))
+# define widen2(x) ((vec_t)B(pmovzxwq, _mask, (vhi_quarter_t)(x), (vdi_t)undef(), ~0))
+# endif
#elif VEC_SIZE == 16 && defined(__SSE2__)
# if INT_SIZE == 1 || UINT_SIZE == 1
# define interleave_hi(x, y) ((vec_t)__builtin_ia32_punpckhbw128((vqi_t)(x), (vqi_t)(y)))
@@ -559,7 +644,7 @@ static inline bool _to_bool(byte_vec_t b
# endif
# endif
#endif
-#if VEC_SIZE == 16 && defined(__SSSE3__)
+#if VEC_SIZE == 16 && defined(__SSSE3__) && !defined(__AVX512VL__)
# if INT_SIZE == 1
# define abs(x) ((vec_t)__builtin_ia32_pabsb128((vqi_t)(x)))
# elif INT_SIZE == 2
@@ -783,6 +868,40 @@ static inline half_t low_half(vec_t x)
}
# endif
+# if !defined(low_quarter) && defined(QUARTER_SIZE)
+static inline quarter_t low_quarter(vec_t x)
+{
+# if QUARTER_SIZE < VEC_SIZE
+ quarter_t y;
+ unsigned int i;
+
+ for ( i = 0; i < ELEM_COUNT / 4; ++i )
+ y[i] = x[i];
+
+ return y;
+# else
+ return x;
+# endif
+}
+# endif
+
+# if !defined(low_eighth) && defined(EIGHTH_SIZE)
+static inline eighth_t low_eighth(vec_t x)
+{
+# if EIGHTH_SIZE < VEC_SIZE
+ eighth_t y;
+ unsigned int i;
+
+ for ( i = 0; i < ELEM_COUNT / 4; ++i )
+ y[i] = x[i];
+
+ return y;
+# else
+ return x;
+# endif
+}
+# endif
+
#endif
#if defined(__AVX512F__) && defined(FLOAT_SIZE)
@@ -1111,7 +1230,7 @@ int simd_test(void)
y = interleave_lo(alt < 0, alt < 0);
y = interleave_lo(z, y);
touch(x);
- z = widen2(x);
+ z = widen2(low_quarter(x));
touch(x);
if ( !eq(z, y) ) return __LINE__;
@@ -1120,7 +1239,7 @@ int simd_test(void)
y = interleave_lo(y, y);
y = interleave_lo(z, y);
touch(x);
- z = widen3(x);
+ z = widen3(low_eighth(x));
touch(x);
if ( !eq(z, y) ) return __LINE__;
# endif
@@ -1142,14 +1261,14 @@ int simd_test(void)
# ifdef widen2
touch(src);
- x = widen2(src);
+ x = widen2(low_quarter(src));
touch(src);
if ( !eq(x, z) ) return __LINE__;
# endif
# ifdef widen3
touch(src);
- x = widen3(src);
+ x = widen3(low_eighth(src));
touch(src);
if ( !eq(x, interleave_lo(z, (vec_t){})) ) return __LINE__;
# endif
@@ -1169,6 +1288,36 @@ int simd_test(void)
if ( aux2[i] != src[i] )
return __LINE__;
}
+#endif
+
+#if defined(widen2) && defined(shrink2)
+ {
+ quarter_t aux1 = low_quarter(src), aux2;
+
+ touch(aux1);
+ x = widen2(aux1);
+ touch(x);
+ aux2 = shrink2(x);
+ touch(aux2);
+ for ( i = 0; i < ELEM_COUNT / 4; ++i )
+ if ( aux2[i] != src[i] )
+ return __LINE__;
+ }
+#endif
+
+#if defined(widen3) && defined(shrink3)
+ {
+ eighth_t aux1 = low_eighth(src), aux2;
+
+ touch(aux1);
+ x = widen3(aux1);
+ touch(x);
+ aux2 = shrink3(x);
+ touch(aux2);
+ for ( i = 0; i < ELEM_COUNT / 8; ++i )
+ if ( aux2[i] != src[i] )
+ return __LINE__;
+ }
#endif
#ifdef dup_lo
--- a/tools/tests/x86_emulator/simd.h
+++ b/tools/tests/x86_emulator/simd.h
@@ -95,6 +95,32 @@ typedef int __attribute__((vector_size(H
typedef long long __attribute__((vector_size(HALF_SIZE))) vdi_half_t;
# endif
+# if ELEM_COUNT >= 4
+# if VEC_SIZE > 64
+# define QUARTER_SIZE (VEC_SIZE / 4)
+# else
+# define QUARTER_SIZE 16
+# endif
+typedef typeof((vec_t){}[0]) __attribute__((vector_size(QUARTER_SIZE))) quarter_t;
+typedef char __attribute__((vector_size(QUARTER_SIZE))) vqi_quarter_t;
+typedef short __attribute__((vector_size(QUARTER_SIZE))) vhi_quarter_t;
+typedef int __attribute__((vector_size(QUARTER_SIZE))) vsi_quarter_t;
+typedef long long __attribute__((vector_size(QUARTER_SIZE))) vdi_quarter_t;
+# endif
+
+# if ELEM_COUNT >= 8
+# if VEC_SIZE > 128
+# define EIGHTH_SIZE (VEC_SIZE / 8)
+# else
+# define EIGHTH_SIZE 16
+# endif
+typedef typeof((vec_t){}[0]) __attribute__((vector_size(EIGHTH_SIZE))) eighth_t;
+typedef char __attribute__((vector_size(EIGHTH_SIZE))) vqi_eighth_t;
+typedef short __attribute__((vector_size(EIGHTH_SIZE))) vhi_eighth_t;
+typedef int __attribute__((vector_size(EIGHTH_SIZE))) vsi_eighth_t;
+typedef long long __attribute__((vector_size(EIGHTH_SIZE))) vdi_eighth_t;
+# endif
+
#endif
#if VEC_SIZE == 16
@@ -182,6 +208,9 @@ OVR_SFP(broadcast);
OVR_SFP(comi);
OVR_FP(add);
OVR_INT(add);
+OVR_BW(adds);
+OVR_BW(addus);
+OVR_BW(avg);
OVR_FP(div);
OVR(extractps);
OVR_FMA(fmadd, FP);
@@ -214,6 +243,8 @@ OVR_INT(srl);
OVR_DQ(srlv);
OVR_FP(sub);
OVR_INT(sub);
+OVR_BW(subs);
+OVR_BW(subus);
OVR_SFP(ucomi);
OVR_VFP(unpckh);
OVR_VFP(unpckl);
@@ -275,6 +306,31 @@ OVR(punpckldq);
OVR(punpcklqdq);
#endif
+#ifdef __AVX512BW__
+OVR(pextrb);
+OVR(pextrw);
+OVR(pinsrb);
+OVR(pinsrw);
+# ifdef __AVX512VL__
+OVR(pmaddwd);
+OVR(pmovsxbw);
+OVR(pmovzxbw);
+OVR(pmulhuw);
+OVR(pmulhw);
+OVR(pmullw);
+OVR(psadbw);
+OVR(pshufb);
+OVR(pshufhw);
+OVR(pshuflw);
+OVR(punpckhbw);
+OVR(punpckhwd);
+OVR(punpcklbw);
+OVR(punpcklwd);
+OVR(slldq);
+OVR(srldq);
+# endif
+#endif
+
#undef OVR_VFP
#undef OVR_SFP
#undef OVR_INT
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -22,6 +22,7 @@ asm ( ".pushsection .test, \"ax\", @prog
#include "avx512dq-opmask.h"
#include "avx512bw-opmask.h"
#include "avx512f.h"
+#include "avx512bw.h"
#define verbose false /* Switch to true for far more logging. */
@@ -105,6 +106,11 @@ static bool simd_check_avx512bw(void)
}
#define simd_check_avx512bw_opmask simd_check_avx512bw
+static bool simd_check_avx512bw_vl(void)
+{
+ return cpu_has_avx512bw && cpu_has_avx512vl;
+}
+
static void simd_set_regs(struct cpu_user_regs *regs)
{
if ( cpu_has_mmx )
@@ -284,6 +290,18 @@ static const struct {
AVX512VL(VL u64x2, avx512f, 16u8),
AVX512VL(VL s64x4, avx512f, 32i8),
AVX512VL(VL u64x4, avx512f, 32u8),
+ SIMD(AVX512BW s8x64, avx512bw, 64i1),
+ SIMD(AVX512BW u8x64, avx512bw, 64u1),
+ SIMD(AVX512BW s16x32, avx512bw, 64i2),
+ SIMD(AVX512BW u16x32, avx512bw, 64u2),
+ AVX512VL(BW+VL s8x16, avx512bw, 16i1),
+ AVX512VL(BW+VL u8x16, avx512bw, 16u1),
+ AVX512VL(BW+VL s8x32, avx512bw, 32i1),
+ AVX512VL(BW+VL u8x32, avx512bw, 32u1),
+ AVX512VL(BW+VL s16x8, avx512bw, 16i2),
+ AVX512VL(BW+VL u16x8, avx512bw, 16u2),
+ AVX512VL(BW+VL s16x16, avx512bw, 32i2),
+ AVX512VL(BW+VL u16x16, avx512bw, 32u2),
#undef AVX512VL_
#undef AVX512VL
#undef SIMD_
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2018-09-25 13:47 UTC|newest]
Thread overview: 465+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-09 8:15 [PATCH 0/6] x86emul: fixes, improvements, and beginnings of AVX512 support Jan Beulich
2018-08-09 8:23 ` [PATCH 1/6] x86emul: fix FMA scalar operand sizes Jan Beulich
2018-08-09 8:24 ` [PATCH 2/6] x86emul: extend MASKMOV{Q,DQU} tests Jan Beulich
2018-08-09 8:24 ` [PATCH 3/6] x86emul: support AVX512 opmask insns Jan Beulich
2018-08-09 8:25 ` [PATCH 4/6] x86emul: clean up AVX2 insn use in test harness Jan Beulich
2018-08-09 8:25 ` [PATCH 5/6] x86emul: correct EVEX decoding Jan Beulich
2018-08-09 8:26 ` [PATCH 6/6] x86emul: generalize vector length handling for AVX512/EVEX Jan Beulich
2018-08-29 14:20 ` [PATCH v2 0/6] x86emul: fixes, improvements, and beginnings of AVX512 support Jan Beulich
2018-08-29 14:23 ` [PATCH v2 1/6] x86emul: fix FMA scalar operand sizes Jan Beulich
2018-09-03 16:43 ` Andrew Cooper
2018-09-04 7:52 ` Jan Beulich
2018-08-29 14:23 ` [PATCH v2 2/6] x86emul: extend MASKMOV{Q,DQU} tests Jan Beulich
2018-09-03 16:44 ` [PATCH v2 2/6] x86emul: extend MASKMOV{Q, DQU} tests Andrew Cooper
2018-08-29 14:24 ` [PATCH v2 3/6] x86emul: support AVX512 opmask insns Jan Beulich
2018-09-03 17:57 ` Andrew Cooper
2018-09-04 7:58 ` Jan Beulich
2018-08-29 14:24 ` [PATCH v2 4/6] x86emul: clean up AVX2 insn use in test harness Jan Beulich
2018-09-03 18:04 ` Andrew Cooper
2018-08-29 14:25 ` [PATCH v2 5/6] x86emul: correct EVEX decoding Jan Beulich
2018-09-04 10:48 ` Andrew Cooper
2018-09-04 12:48 ` Jan Beulich
2018-08-29 14:25 ` [PATCH v2 6/6] x86emul: generalize vector length handling for AVX512/EVEX Jan Beulich
2018-09-04 11:02 ` Andrew Cooper
2018-09-04 12:50 ` Jan Beulich
2018-09-18 11:46 ` [PATCH v3 00/34] x86emul: fixes, improvements, and beginnings of AVX512 support Jan Beulich
2018-09-18 11:53 ` [PATCH v3 01/34] x86emul: support AVX512 opmask insns Jan Beulich
2018-10-25 18:32 ` Andrew Cooper
2018-10-26 9:03 ` Jan Beulich
2018-10-26 11:29 ` Andrew Cooper
2018-10-26 11:59 ` Jan Beulich
2018-10-26 12:19 ` Andrew Cooper
2018-10-26 12:34 ` Jan Beulich
2018-09-18 11:53 ` [PATCH v3 02/34] x86/HVM: grow MMIO cache data size to 64 bytes Jan Beulich
2018-09-18 16:05 ` Paul Durrant
2018-10-25 18:36 ` Andrew Cooper
2018-10-26 9:04 ` Jan Beulich
2018-10-26 11:29 ` Andrew Cooper
2018-09-18 11:55 ` [PATCH v3 03/34] x86emul: correct EVEX decoding Jan Beulich
2018-09-18 11:55 ` [PATCH v3 04/34] x86emul: generalize vector length handling for AVX512/EVEX Jan Beulich
2018-09-18 11:56 ` [PATCH v3 05/34] x86emul: support basic AVX512 moves Jan Beulich
2018-09-18 11:57 ` [PATCH v3 06/34] x86emul: test for correct EVEX Disp8 scaling Jan Beulich
2018-09-18 11:57 ` [PATCH v3 07/34] x86emul: use AVX512 logic for emulating V{, P}MASKMOV* Jan Beulich
2018-09-18 11:58 ` [PATCH v3 08/34] x86emul: support AVX512F legacy-equivalent arithmetic FP insns Jan Beulich
2018-09-18 11:59 ` [PATCH v3 09/34] x86emul: support AVX512DQ logic " Jan Beulich
2018-09-18 11:59 ` [PATCH v3 10/34] x86emul: support AVX512F "normal" FP compare insns Jan Beulich
2018-09-18 12:00 ` [PATCH v3 11/34] x86emul: support AVX512F misc legacy-equivalent FP insns Jan Beulich
2018-09-18 12:00 ` [PATCH v3 12/34] x86emul: support AVX512F fused-multiply-add insns Jan Beulich
2018-09-18 12:01 ` [PATCH v3 13/34] x86emul: support AVX512F legacy-equivalent logic insns Jan Beulich
2018-09-18 12:02 ` [PATCH v3 14/34] x86emul: support AVX512{F, DQ} FP broadcast insns Jan Beulich
2018-09-18 12:03 ` [PATCH v3 15/34] x86emul: support AVX512F v{, u}comis{d, s} insns Jan Beulich
2018-09-18 12:03 ` [PATCH v3 16/34] x86emul/test: introduce eq() Jan Beulich
2018-09-18 12:04 ` [PATCH v3 17/34] x86emul: support AVX512{F, BW} packed integer compare insns Jan Beulich
2018-09-18 12:05 ` [PATCH v3 18/34] x86emul: support AVX512{F, BW} packed integer arithmetic insns Jan Beulich
2018-09-18 12:05 ` [PATCH v3 19/34] x86emul: use simd_128 also for legacy vector shift insns Jan Beulich
2018-09-18 12:05 ` [PATCH v3 20/34] x86emul: support AVX512{F, BW} shift/rotate insns Jan Beulich
2018-09-18 12:06 ` [PATCH v3 21/34] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2018-09-18 12:07 ` [PATCH v3 22/34] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2018-09-18 12:07 ` [PATCH v3 23/34] x86emul: basic AVX512F testing Jan Beulich
2018-09-18 12:08 ` [PATCH v3 24/34] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2018-09-18 12:09 ` [PATCH v3 25/34] x86emul: basic AVX512VL testing Jan Beulich
2018-09-18 12:09 ` [PATCH v3 26/34] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2018-09-18 12:09 ` [PATCH v3 27/34] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2018-09-18 12:10 ` [PATCH v3 28/34] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2018-09-18 12:11 ` [PATCH v3 29/34] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2018-09-18 12:11 ` [PATCH v3 29/34] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2018-09-18 12:12 ` [PATCH v3 30/34] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2018-09-18 12:14 ` [PATCH v3 32/34] x86emul: basic AVX512BW testing Jan Beulich
2018-09-18 12:14 ` [PATCH v3 33/34] x86emul: basic AVX512DQ testing Jan Beulich
2018-09-18 12:14 ` [PATCH v3 34/34] x86emul: also allow running the 32-bit harness on a 64-bit distro Jan Beulich
2018-09-25 13:14 ` [PATCH v4 00/44] x86emul: fixes, improvements, and beginnings of AVX512 support Jan Beulich
2018-09-25 13:25 ` [PATCH v4 01/44] x86emul: support AVX512 opmask insns Jan Beulich
2018-09-26 6:06 ` Jan Beulich
2018-09-25 13:26 ` [PATCH v4 02/44] x86/HVM: grow MMIO cache data size to 64 bytes Jan Beulich
2018-09-25 13:27 ` [PATCH v4 03/44] x86emul: correct EVEX decoding Jan Beulich
2018-10-26 14:33 ` Andrew Cooper
2018-09-25 13:28 ` [PATCH v4 04/44] x86emul: generalize vector length handling for AVX512/EVEX Jan Beulich
2018-10-26 16:10 ` Andrew Cooper
2018-09-25 13:28 ` [PATCH v4 05/44] x86emul: support basic AVX512 moves Jan Beulich
2018-11-13 17:12 ` Andrew Cooper
2018-11-14 14:35 ` Jan Beulich
2018-11-14 16:26 ` Andrew Cooper
2018-11-15 9:54 ` Jan Beulich
2018-09-25 13:29 ` [PATCH v4 06/44] x86emul: test for correct EVEX Disp8 scaling Jan Beulich
2018-11-12 17:42 ` Andrew Cooper
2018-11-13 11:12 ` Jan Beulich
2018-11-13 15:45 ` Andrew Cooper
2018-11-14 14:17 ` Jan Beulich
2018-11-14 14:42 ` Andrew Cooper
2018-11-14 14:58 ` Jan Beulich
2018-09-25 13:29 ` [PATCH v4 07/44] x86emul: also allow running the 32-bit harness on a 64-bit distro Jan Beulich
2018-11-12 17:50 ` Andrew Cooper
2018-11-13 11:42 ` Jan Beulich
2018-11-13 15:58 ` Andrew Cooper
2018-11-14 8:42 ` Jan Beulich
2018-09-25 13:30 ` [PATCH v4 08/44] x86emul: use AVX512 logic for emulating V{, P}MASKMOV* Jan Beulich
2018-11-13 18:12 ` Andrew Cooper
2018-09-25 13:31 ` [PATCH v4 09/44] x86emul: support AVX512F legacy-equivalent arithmetic FP insns Jan Beulich
2018-11-13 18:21 ` Andrew Cooper
2018-09-25 13:32 ` [PATCH v4 10/44] x86emul: support AVX512DQ logic " Jan Beulich
2018-11-13 18:56 ` Andrew Cooper
2018-09-25 13:32 ` [PATCH v4 11/44] x86emul: support AVX512F "normal" FP compare insns Jan Beulich
2018-11-13 19:04 ` Andrew Cooper
2018-11-14 14:41 ` Jan Beulich
2018-11-14 14:45 ` Andrew Cooper
2018-09-25 13:33 ` [PATCH v4 12/44] x86emul: support AVX512F misc legacy-equivalent FP insns Jan Beulich
2018-11-13 19:17 ` Andrew Cooper
2018-09-25 13:33 ` [PATCH v4 13/44] x86emul: support AVX512F fused-multiply-add insns Jan Beulich
2018-11-13 19:28 ` Andrew Cooper
2018-09-25 13:34 ` [PATCH v4 14/44] x86emul: support AVX512F legacy-equivalent logic insns Jan Beulich
2018-11-13 19:30 ` Andrew Cooper
2018-09-25 13:35 ` [PATCH v4 15/44] x86emul: support AVX512{F, DQ} FP broadcast insns Jan Beulich
2018-11-13 19:37 ` Andrew Cooper
2018-09-25 13:35 ` [PATCH v4 16/44] x86emul: support AVX512F v{, u}comis{d, s} insns Jan Beulich
2018-11-13 19:39 ` Andrew Cooper
2018-09-25 13:36 ` [PATCH v4 17/44] x86emul/test: introduce eq() Jan Beulich
2018-10-26 11:31 ` Andrew Cooper
2018-09-25 13:37 ` [PATCH v4 18/44] x86emul: support AVX512{F, BW} packed integer compare insns Jan Beulich
2018-09-25 13:37 ` [PATCH v4 19/44] x86emul: support AVX512{F, BW} packed integer arithmetic insns Jan Beulich
2018-09-25 13:38 ` [PATCH v4 20/44] x86emul: use simd_128 also for legacy vector shift insns Jan Beulich
2018-09-25 13:39 ` [PATCH v4 21/44] x86emul: support AVX512{F, BW} shift/rotate insns Jan Beulich
2018-09-25 13:40 ` [PATCH v4 22/44] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2018-09-25 13:40 ` [PATCH v4 23/44] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2018-09-25 13:41 ` [PATCH v4 24/44] x86emul: basic AVX512F testing Jan Beulich
2018-09-25 13:41 ` [PATCH v4 25/44] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2018-09-25 13:42 ` [PATCH v4 26/44] x86emul: basic AVX512VL testing Jan Beulich
2018-09-25 13:43 ` [PATCH v4 27/44] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2018-09-25 13:43 ` [PATCH v4 28/44] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2018-09-25 13:44 ` [PATCH v4 29/44] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2018-09-25 13:44 ` [PATCH v4 30/44] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2018-09-25 13:46 ` [PATCH v4 31/44] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2018-09-25 13:46 ` [PATCH v4 32/44] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2018-09-25 13:47 ` Jan Beulich [this message]
2018-09-25 13:48 ` [PATCH v4 34/44] x86emul: basic AVX512DQ testing Jan Beulich
2018-09-25 13:48 ` [PATCH v4 35/44] x86emul: support AVX512F move high/low insns Jan Beulich
2018-09-25 13:49 ` [PATCH v4 36/44] x86emul: support AVX512F move duplicate insns Jan Beulich
2018-09-25 13:49 ` [PATCH v4 37/44] x86emul: support AVX512{F, BW, VBMI} permute insns Jan Beulich
2018-09-25 13:50 ` [PATCH v4 38/44] x86emul: support AVX512BW pack insns Jan Beulich
2018-09-25 13:51 ` [PATCH v4 39/44] x86emul: support AVX512F floating-point conversion insns Jan Beulich
2018-09-25 13:52 ` [PATCH v4 40/44] x86emul: support AVX512F legacy-equivalent packed int/FP " Jan Beulich
2018-09-25 13:53 ` [PATCH v4 41/44] x86emul: support AVX512F legacy-equivalent scalar " Jan Beulich
2018-09-25 13:53 ` [PATCH v4 42/44] x86emul: support AVX512DQ packed quad-int/FP " Jan Beulich
2018-09-25 13:54 ` [PATCH v4 43/44] x86emul: support AVX512{F, DQ} uint-to-FP " Jan Beulich
2018-09-25 13:55 ` [PATCH v4 44/44] x86emul: support AVX512{F, DQ} FP-to-uint " Jan Beulich
2018-11-19 10:00 ` [PATCH v5 00/47] x86emul: fair parts of AVX512 support Jan Beulich
2018-11-19 10:13 ` [PATCH v5 01/47] x86emul: introduce IMPOSSIBLE() Jan Beulich
2018-11-19 18:11 ` Andrew Cooper
2018-11-20 8:12 ` Jan Beulich
2018-11-19 10:13 ` [PATCH v5 02/47] x86emul: support basic AVX512 moves Jan Beulich
2018-11-19 18:35 ` Andrew Cooper
2018-11-19 10:14 ` [PATCH v5 03/47] x86emul: test for correct EVEX Disp8 scaling Jan Beulich
2018-11-19 18:35 ` Andrew Cooper
2018-11-19 10:14 ` [PATCH v5 04/47] x86emul: also allow running the 32-bit harness on a 64-bit distro Jan Beulich
2018-11-19 18:40 ` Andrew Cooper
2018-11-19 10:15 ` [PATCH v5 05/47] x86emul: use AVX512 logic for emulating V{, P}MASKMOV* Jan Beulich
2018-11-19 10:16 ` [PATCH v5 06/47] x86emul: support AVX512F legacy-equivalent arithmetic FP insns Jan Beulich
2018-11-19 10:16 ` [PATCH v5 07/47] x86emul: support AVX512DQ logic " Jan Beulich
2018-11-19 10:17 ` [PATCH v5 08/47] x86emul: support basic AVX512F FP compare insns Jan Beulich
2018-11-19 10:17 ` [PATCH v5 09/47] x86emul: support AVX512F misc legacy-equivalent FP insns Jan Beulich
2018-11-19 10:18 ` [PATCH v5 10/47] x86emul: support AVX512F fused-multiply-add insns Jan Beulich
2018-11-19 10:18 ` [PATCH v5 11/47] x86emul: support AVX512F legacy-equivalent logic insns Jan Beulich
2018-11-19 10:19 ` [PATCH v5 12/47] x86emul: support AVX512{F, DQ} FP broadcast insns Jan Beulich
2018-11-19 18:44 ` Andrew Cooper
2018-11-19 10:20 ` [PATCH v5 13/47] x86emul: support AVX512F v{, u}comis{d, s} insns Jan Beulich
2018-11-19 10:21 ` [PATCH v5 14/47] x86emul: support AVX512{F, BW} packed integer compare insns Jan Beulich
2018-11-19 19:09 ` Andrew Cooper
2018-11-19 10:21 ` [PATCH v5 15/47] x86emul: support AVX512{F, BW} packed integer arithmetic insns Jan Beulich
2018-11-19 19:18 ` Andrew Cooper
2018-11-19 10:22 ` [PATCH v5 16/47] x86emul: use simd_128 also for legacy vector shift insns Jan Beulich
2018-11-19 19:21 ` Andrew Cooper
2018-11-19 10:22 ` [PATCH v5 17/47] x86emul: support AVX512{F, BW} shift/rotate insns Jan Beulich
2018-11-19 10:23 ` [PATCH v5 18/47] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2018-11-19 10:23 ` [PATCH v5 19/47] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2018-11-19 10:24 ` [PATCH v5 20/47] x86emul: basic AVX512F testing Jan Beulich
2018-11-19 10:25 ` [PATCH v5 21/47] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2018-11-19 10:25 ` [PATCH v5 22/47] x86emul: basic AVX512VL testing Jan Beulich
2018-11-19 10:26 ` [PATCH v5 23/47] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2018-11-19 10:26 ` [PATCH v5 24/47] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2018-11-19 10:28 ` [PATCH v5 25/47] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2018-11-19 10:28 ` [PATCH v5 26/47] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2018-11-19 10:29 ` [PATCH v5 27/47] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2018-11-19 10:30 ` [PATCH v5 28/47] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2018-11-19 10:30 ` [PATCH v5 29/47] x86emul: basic AVX512BW testing Jan Beulich
2018-11-19 10:31 ` [PATCH v5 30/47] x86emul: basic AVX512DQ testing Jan Beulich
2018-11-19 10:31 ` [PATCH v5 31/47] x86emul: support AVX512F move high/low insns Jan Beulich
2018-11-19 10:31 ` [PATCH v5 32/47] x86emul: support AVX512F move duplicate insns Jan Beulich
2018-11-19 10:32 ` [PATCH v5 33/47] x86emul: support AVX512{F, BW, VBMI} permute insns Jan Beulich
2018-11-19 10:33 ` [PATCH v5 34/47] x86emul: support AVX512BW pack insns Jan Beulich
2018-11-19 10:33 ` [PATCH v5 35/47] x86emul: support AVX512F floating-point conversion insns Jan Beulich
2018-11-19 10:34 ` [PATCH v5 36/47] x86emul: support AVX512F legacy-equivalent packed int/FP " Jan Beulich
2018-11-19 10:35 ` [PATCH v5 37/47] x86emul: support AVX512F legacy-equivalent scalar " Jan Beulich
2018-11-19 10:36 ` [PATCH v5 38/47] x86emul: support AVX512DQ packed quad-int/FP " Jan Beulich
2018-11-19 10:37 ` [PATCH v5 39/47] x86emul: support AVX512{F, DQ} uint-to-FP " Jan Beulich
2018-11-19 10:37 ` [PATCH v5 40/47] x86emul: support AVX512{F, DQ} FP-to-uint " Jan Beulich
2018-11-19 10:38 ` [PATCH v5 41/47] x86emul: support remaining AVX512F legacy-equivalent insns Jan Beulich
2018-11-19 10:38 ` [PATCH v5 42/47] x86emul: support remaining AVX512BW " Jan Beulich
2018-11-19 10:39 ` [PATCH v5 43/47] x86emul: support AVX512{F, ER} reciprocal insns Jan Beulich
2018-11-19 10:39 ` [PATCH v5 44/47] x86emul: support AVX512F floating point manipulation insns Jan Beulich
2018-11-19 10:40 ` [PATCH v5 45/47] x86emul: support AVX512DQ " Jan Beulich
2018-11-19 10:40 ` [PATCH v5 46/47] x86emul: support AVX512{F, _VBMI2} compress/expand insns Jan Beulich
2018-11-19 10:41 ` [PATCH v5 47/47] x86emul: support remaining misc AVX512{F, BW} insns Jan Beulich
2018-12-06 9:45 ` [PATCH v6 00/42] x86emul: fair parts of AVX512 support Jan Beulich
2018-12-06 9:51 ` [PATCH v6 01/42] x86emul: support AVX512{F, BW} shift/rotate insns Jan Beulich
2018-12-06 9:51 ` [PATCH v6 02/42] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2018-12-06 9:51 ` [PATCH v6 03/42] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2018-12-06 9:52 ` [PATCH v6 04/42] x86emul: basic AVX512F testing Jan Beulich
2018-12-06 9:53 ` [PATCH v6 05/42] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2018-12-06 9:53 ` [PATCH v6 06/42] x86emul: basic AVX512VL testing Jan Beulich
2018-12-06 9:53 ` [PATCH v6 07/42] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2018-12-06 9:54 ` [PATCH v6 08/42] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2018-12-06 9:54 ` [PATCH v6 09/42] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2018-12-06 9:55 ` [PATCH v6 10/42] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2018-12-06 9:55 ` [PATCH v6 11/42] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2018-12-06 9:55 ` [PATCH v6 12/42] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2018-12-06 9:56 ` [PATCH v6 13/42] x86emul: basic AVX512BW testing Jan Beulich
2018-12-06 9:57 ` [PATCH v6 14/42] x86emul: basic AVX512DQ testing Jan Beulich
2018-12-06 9:57 ` [PATCH v6 15/42] x86emul: support AVX512F move high/low insns Jan Beulich
2018-12-06 9:58 ` [PATCH v6 16/42] x86emul: support AVX512F move duplicate insns Jan Beulich
2018-12-06 9:59 ` [PATCH v6 17/42] x86emul: support AVX512{F, BW, _VBMI} permute insns Jan Beulich
2018-12-06 9:59 ` [PATCH v6 18/42] x86emul: support AVX512BW pack insns Jan Beulich
2018-12-06 10:00 ` [PATCH v6 19/42] x86emul: support AVX512F floating-point conversion insns Jan Beulich
2018-12-06 10:00 ` [PATCH v6 20/42] x86emul: support AVX512F legacy-equivalent packed int/FP " Jan Beulich
2018-12-06 10:01 ` [PATCH v6 21/42] x86emul: support AVX512F legacy-equivalent scalar " Jan Beulich
2018-12-06 10:01 ` [PATCH v6 22/42] x86emul: support AVX512DQ packed quad-int/FP " Jan Beulich
2018-12-06 10:02 ` [PATCH v6 23/42] x86emul: support AVX512{F, DQ} uint-to-FP " Jan Beulich
2018-12-06 10:02 ` [PATCH v6 24/42] x86emul: support AVX512{F, DQ} FP-to-uint " Jan Beulich
2018-12-06 10:04 ` [PATCH v6 25/42] x86emul: support remaining AVX512F legacy-equivalent insns Jan Beulich
2018-12-06 10:04 ` [PATCH v6 26/42] x86emul: support remaining AVX512BW " Jan Beulich
2018-12-06 10:04 ` [PATCH v6 27/42] x86emul: support AVX512{F, ER} reciprocal insns Jan Beulich
2018-12-06 10:05 ` [PATCH v6 28/42] x86emul: support AVX512F floating point manipulation insns Jan Beulich
2018-12-06 10:05 ` [PATCH v6 29/42] x86emul: support AVX512DQ " Jan Beulich
2018-12-06 10:06 ` [PATCH v6 30/42] x86emul: support AVX512{F, _VBMI2} compress/expand insns Jan Beulich
2018-12-06 10:07 ` [PATCH v6 31/42] x86emul: support remaining misc AVX512{F, BW} insns Jan Beulich
2018-12-06 10:07 ` [PATCH v6 32/42] x86emul: support AVX512F gather insns Jan Beulich
2018-12-06 10:08 ` [PATCH v6 33/42] x86emul: add high register S/G test cases Jan Beulich
2018-12-06 10:08 ` [PATCH v6 34/42] x86emul: support AVX512F scatter insns Jan Beulich
2018-12-06 10:09 ` [PATCH v6 35/42] x86emul: support AVX512PF insns Jan Beulich
2018-12-06 10:09 ` [PATCH v6 36/42] x86emul: support AVX512CD insns Jan Beulich
2018-12-06 10:10 ` [PATCH v6 37/42] x86emul: complete support of AVX512_VBMI insns Jan Beulich
2018-12-06 10:10 ` [PATCH v6 38/42] x86emul: support of AVX512* population count insns Jan Beulich
2018-12-06 10:11 ` [PATCH v6 39/42] x86emul: support of AVX512_IFMA insns Jan Beulich
2018-12-06 10:11 ` [PATCH v6 40/42] x86emul: support remaining AVX512_VBMI2 insns Jan Beulich
2018-12-06 10:12 ` [PATCH v6 41/42] x86emul: support AVX512_4FMAPS insns Jan Beulich
2018-12-06 10:12 ` [PATCH v6 42/42] x86emul: support AVX512_4VNNIW insns Jan Beulich
2018-12-19 14:17 ` [PATCH v7 00/49] x86emul: remaining AVX512 support Jan Beulich
2018-12-19 14:34 ` Jan Beulich
2018-12-19 14:35 ` [PATCH v7 01/49] x86emul: rename evex.br to evex.brs Jan Beulich
2018-12-19 15:14 ` Andrew Cooper
2018-12-19 14:36 ` [PATCH v7 02/49] x86emul: support AVX512{F, BW} shift/rotate insns Jan Beulich
2018-12-19 16:00 ` Andrew Cooper
2018-12-19 14:36 ` [PATCH v7 03/49] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2018-12-19 18:20 ` Andrew Cooper
2018-12-20 7:49 ` Jan Beulich
2018-12-19 14:37 ` [PATCH v7 04/49] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2019-03-14 15:35 ` Andrew Cooper
2018-12-19 14:37 ` [PATCH v7 05/49] x86emul: basic AVX512F testing Jan Beulich
2019-03-14 15:42 ` Andrew Cooper
2018-12-19 14:38 ` [PATCH v7 06/49] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2019-03-14 16:38 ` Andrew Cooper
2019-03-14 17:15 ` Jan Beulich
2019-03-15 16:39 ` Andrew Cooper
2019-03-18 9:45 ` Jan Beulich
2018-12-19 14:38 ` [PATCH v7 07/49] x86emul: basic AVX512VL testing Jan Beulich
2019-03-14 16:39 ` Andrew Cooper
2018-12-19 14:41 ` [PATCH v7 08/49] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2018-12-19 14:41 ` [PATCH v7 09/49] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2018-12-19 14:42 ` [PATCH v7 10/49] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2018-12-19 14:42 ` [PATCH v7 11/49] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2018-12-19 14:43 ` [PATCH v7 12/49] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2018-12-19 14:43 ` [PATCH v7 13/49] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2018-12-19 14:44 ` [PATCH v7 14/49] x86emul: basic AVX512BW testing Jan Beulich
2018-12-19 14:46 ` [PATCH v7 15/49] x86emul: basic AVX512DQ testing Jan Beulich
2018-12-19 14:46 ` [PATCH v7 16/49] x86emul: support AVX512F move high/low insns Jan Beulich
2018-12-19 14:47 ` [PATCH v7 17/49] x86emul: support AVX512F move duplicate insns Jan Beulich
2018-12-19 14:47 ` [PATCH v7 18/49] x86emul: support AVX512{F, BW, _VBMI} permute insns Jan Beulich
2018-12-19 14:48 ` [PATCH v7 19/49] x86emul: support AVX512BW pack insns Jan Beulich
2018-12-19 14:48 ` [PATCH v7 20/49] x86emul: support AVX512F floating-point conversion insns Jan Beulich
2018-12-19 14:48 ` [PATCH v7 21/49] x86emul: support AVX512F legacy-equivalent packed int/FP " Jan Beulich
2018-12-19 14:51 ` [PATCH v7 22/49] x86emul: support AVX512F legacy-equivalent scalar " Jan Beulich
2018-12-19 14:51 ` [PATCH v7 23/49] x86emul: support AVX512DQ packed quad-int/FP " Jan Beulich
2018-12-19 14:52 ` [PATCH v7 24/49] x86emul: support AVX512{F, DQ} uint-to-FP " Jan Beulich
2018-12-19 14:52 ` [PATCH v7 25/49] x86emul: support AVX512{F, DQ} FP-to-uint " Jan Beulich
2018-12-19 14:53 ` [PATCH v7 26/49] x86emul: support remaining AVX512F legacy-equivalent insns Jan Beulich
2018-12-19 14:53 ` [PATCH v7 27/49] x86emul: support remaining AVX512BW " Jan Beulich
2018-12-19 14:54 ` [PATCH v7 28/49] x86emul: support AVX512{F, ER} reciprocal insns Jan Beulich
2018-12-19 14:55 ` [PATCH v7 29/49] x86emul: support AVX512F floating point manipulation insns Jan Beulich
2018-12-19 14:55 ` [PATCH v7 30/49] x86emul: support AVX512DQ " Jan Beulich
2018-12-19 14:56 ` [PATCH v7 31/49] x86emul: support AVX512{F, _VBMI2} compress/expand insns Jan Beulich
2018-12-19 14:56 ` [PATCH v7 32/49] x86emul: support remaining misc AVX512{F, BW} insns Jan Beulich
2018-12-19 14:57 ` [PATCH v7 33/49] x86emul: support AVX512F gather insns Jan Beulich
2018-12-19 14:57 ` [PATCH v7 34/49] x86emul: add high register S/G test cases Jan Beulich
2018-12-19 14:58 ` [PATCH v7 35/49] x86emul: support AVX512F scatter insns Jan Beulich
2018-12-19 14:59 ` [PATCH v7 36/49] x86emul: support AVX512PF insns Jan Beulich
2018-12-19 14:59 ` [PATCH v7 37/49] x86emul: support AVX512CD insns Jan Beulich
2018-12-19 15:00 ` [PATCH v7 38/49] x86emul: complete support of AVX512_VBMI insns Jan Beulich
2018-12-19 15:00 ` [PATCH v7 39/49] x86emul: support of AVX512* population count insns Jan Beulich
2018-12-19 15:01 ` [PATCH v7 40/49] x86emul: support of AVX512_IFMA insns Jan Beulich
2018-12-19 15:01 ` [PATCH v7 42/49] x86emul: support remaining AVX512_VBMI2 insns Jan Beulich
2018-12-19 15:02 ` [PATCH v7 42/49] x86emul: support AVX512_4FMAPS insns Jan Beulich
2018-12-19 15:05 ` [PATCH v7 43/49] x86emul: support AVX512_4VNNIW insns Jan Beulich
2018-12-19 15:06 ` [PATCH v7 44/49] x86emul: support AVX512_VNNI insns Jan Beulich
2018-12-19 15:06 ` [PATCH v7 45/49] x86emul: support VPCLMULQDQ insns Jan Beulich
2018-12-19 15:07 ` [PATCH v7 46/49] x86emul: support VAES insns Jan Beulich
2018-12-19 15:07 ` [PATCH v7 47/49] x86emul: support GFNI insns Jan Beulich
2018-12-19 15:07 ` [PATCH v7 48/49] x86emul: restore ordering within main switch statement Jan Beulich
2018-12-19 15:08 ` [PATCH v7 49/49] tools: re-sync CPUID leaf 7 tables Jan Beulich
2019-03-14 11:07 ` Andrew Cooper
2019-03-15 10:30 ` [PATCH v8 00/50] x86emul: remaining AVX512 support Jan Beulich
2019-03-15 10:36 ` [PATCH v8 01/50] x86emul: no need to set fault_suppression to false for VMOVNT* Jan Beulich
2019-03-15 16:52 ` Andrew Cooper
2019-03-15 10:36 ` [PATCH v8 02/50] x86emul: support AVX512{F, BW, DQ} extract insns Jan Beulich
2019-03-15 17:51 ` Andrew Cooper
2019-03-15 10:37 ` [PATCH v8 03/50] x86emul: support AVX512{F, BW, DQ} insert insns Jan Beulich
2019-03-15 10:38 ` [PATCH v8 04/50] x86emul: basic AVX512F testing Jan Beulich
2019-03-15 10:39 ` [PATCH v8 05/50] x86emul: support AVX512{F, BW, DQ} integer broadcast insns Jan Beulich
2019-03-15 10:39 ` [PATCH v8 06/50] x86emul: basic AVX512VL testing Jan Beulich
2019-03-15 10:40 ` [PATCH v8 07/50] x86emul: support AVX512{F, BW} zero- and sign-extending moves Jan Beulich
2019-03-15 18:02 ` Andrew Cooper
2019-03-15 10:40 ` [PATCH v8 08/50] x86emul: support AVX512{F, BW} down conversion moves Jan Beulich
2019-03-15 18:10 ` Andrew Cooper
2019-03-15 10:41 ` [PATCH v8 09/50] x86emul: support AVX512{F, BW} integer unpack insns Jan Beulich
2019-03-15 18:21 ` Andrew Cooper
2019-03-18 9:55 ` Jan Beulich
2019-05-20 12:11 ` Andrew Cooper
2019-05-20 12:11 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:41 ` [PATCH v8 10/50] x86emul: support AVX512{F, BW, _VBMI} full permute insns Jan Beulich
2019-05-17 16:50 ` Andrew Cooper
2019-05-17 16:50 ` [Xen-devel] " Andrew Cooper
2019-05-20 6:55 ` Jan Beulich
2019-05-20 6:55 ` [Xen-devel] " Jan Beulich
2019-05-20 12:10 ` Andrew Cooper
2019-05-20 12:10 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:43 ` [PATCH v8 11/50] x86emul: support AVX512{F, BW} integer shuffle insns Jan Beulich
2019-05-17 17:01 ` Andrew Cooper
2019-05-17 17:01 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:43 ` [PATCH v8 12/50] x86emul: support AVX512{BW, DQ} mask move insns Jan Beulich
2019-05-17 17:02 ` Andrew Cooper
2019-05-17 17:02 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:43 ` [PATCH v8 13/50] x86emul: basic AVX512BW testing Jan Beulich
2019-05-17 17:03 ` Andrew Cooper
2019-05-17 17:03 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:44 ` [PATCH v8 14/50] x86emul: basic AVX512DQ testing Jan Beulich
2019-05-17 17:03 ` Andrew Cooper
2019-05-17 17:03 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:44 ` [PATCH v8 15/50] x86emul: support AVX512F move high/low insns Jan Beulich
2019-05-21 10:59 ` Andrew Cooper
2019-05-21 10:59 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:45 ` [PATCH v8 16/50] x86emul: support AVX512F move duplicate insns Jan Beulich
2019-05-21 11:09 ` Andrew Cooper
2019-05-21 11:09 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:46 ` [PATCH v8 17/50] x86emul: support AVX512{F, BW, _VBMI} permute insns Jan Beulich
2019-05-21 11:24 ` Andrew Cooper
2019-05-21 11:24 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:46 ` [PATCH v8 18/50] x86emul: support AVX512BW pack insns Jan Beulich
2019-05-21 11:26 ` Andrew Cooper
2019-05-21 11:26 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:47 ` [PATCH v8 19/50] x86emul: support AVX512F floating-point conversion insns Jan Beulich
2019-05-21 11:33 ` Andrew Cooper
2019-05-21 11:33 ` [Xen-devel] " Andrew Cooper
2019-05-21 15:46 ` Jan Beulich
2019-05-21 15:46 ` [Xen-devel] " Jan Beulich
2019-05-23 16:08 ` Andrew Cooper
2019-05-23 16:08 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:47 ` [PATCH v8 20/50] x86emul: support AVX512F legacy-equivalent packed int/FP " Jan Beulich
2019-05-21 11:37 ` Andrew Cooper
2019-05-21 11:37 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:52 ` [PATCH v8 21/50] x86emul: support AVX512F legacy-equivalent scalar " Jan Beulich
2019-05-21 11:44 ` Andrew Cooper
2019-05-21 11:44 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:52 ` [PATCH v8 22/50] x86emul: support AVX512DQ packed quad-int/FP " Jan Beulich
2019-05-21 11:53 ` Andrew Cooper
2019-05-21 11:53 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:53 ` [PATCH v8 23/50] x86emul: support AVX512{F, DQ} uint-to-FP " Jan Beulich
2019-05-21 11:58 ` Andrew Cooper
2019-05-21 11:58 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:54 ` [PATCH v8 24/50] x86emul: support AVX512{F, DQ} FP-to-uint " Jan Beulich
2019-05-21 12:09 ` Andrew Cooper
2019-05-21 12:09 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:54 ` [PATCH v8 25/50] x86emul: support remaining AVX512F legacy-equivalent insns Jan Beulich
2019-05-21 13:06 ` Andrew Cooper
2019-05-21 13:06 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:54 ` [PATCH v8 26/50] x86emul: support remaining AVX512BW " Jan Beulich
2019-05-21 13:08 ` Andrew Cooper
2019-05-21 13:08 ` [Xen-devel] " Andrew Cooper
2019-05-21 13:34 ` Jan Beulich
2019-05-21 13:34 ` [Xen-devel] " Jan Beulich
2019-05-23 16:10 ` Andrew Cooper
2019-05-23 16:10 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:55 ` [PATCH v8 27/50] x86emul: support AVX512{F, ER} reciprocal insns Jan Beulich
2019-05-23 16:15 ` Andrew Cooper
2019-05-23 16:15 ` [Xen-devel] " Andrew Cooper
2019-05-24 6:43 ` Jan Beulich
2019-05-24 6:43 ` [Xen-devel] " Jan Beulich
2019-05-24 20:48 ` Andrew Cooper
2019-05-24 20:48 ` [Xen-devel] " Andrew Cooper
2019-05-27 8:02 ` Jan Beulich
2019-05-27 8:02 ` [Xen-devel] " Jan Beulich
2019-05-29 10:00 ` Andrew Cooper
2019-05-29 10:00 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:56 ` [PATCH v8 28/50] x86emul: support AVX512F floating point manipulation insns Jan Beulich
2019-05-29 12:51 ` Andrew Cooper
2019-05-29 12:51 ` [Xen-devel] " Andrew Cooper
2019-05-29 13:15 ` Jan Beulich
2019-05-29 13:15 ` [Xen-devel] " Jan Beulich
2019-06-10 14:01 ` Andrew Cooper
2019-06-10 14:03 ` Andrew Cooper
2019-03-15 10:56 ` [PATCH v8 29/50] x86emul: support AVX512DQ " Jan Beulich
2019-06-10 14:06 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:56 ` [PATCH v8 30/50] x86emul: support AVX512{F, _VBMI2} compress/expand insns Jan Beulich
2019-06-10 14:51 ` [Xen-devel] " Andrew Cooper
2019-06-11 10:20 ` Jan Beulich
2019-06-18 16:24 ` Andrew Cooper
2019-06-19 6:38 ` Jan Beulich
2019-03-15 10:58 ` [PATCH v8 31/50] x86emul: support remaining misc AVX512{F, BW} insns Jan Beulich
2019-06-18 16:42 ` [Xen-devel] " Andrew Cooper
2019-06-19 6:44 ` Jan Beulich
2019-03-15 10:58 ` [PATCH v8 32/50] x86emul: support AVX512F gather insns Jan Beulich
2019-06-19 12:05 ` [Xen-devel] " Andrew Cooper
2019-06-19 12:43 ` Jan Beulich
2019-03-15 10:59 ` [PATCH v8 33/50] x86emul: add high register S/G test cases Jan Beulich
2019-06-19 12:07 ` [Xen-devel] " Andrew Cooper
2019-03-15 10:59 ` [PATCH v8 34/50] x86emul: support AVX512F scatter insns Jan Beulich
2019-03-15 11:00 ` [PATCH v8 35/50] x86emul: support AVX512PF insns Jan Beulich
2019-03-15 11:00 ` [PATCH v8 36/50] x86emul: support AVX512CD insns Jan Beulich
2019-06-19 12:13 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:01 ` [PATCH v8 37/50] x86emul: complete support of AVX512_VBMI insns Jan Beulich
2019-06-19 12:16 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:01 ` [PATCH v8 38/50] x86emul: support of AVX512* population count insns Jan Beulich
2019-06-19 12:22 ` [Xen-devel] " Andrew Cooper
2019-06-19 12:48 ` Jan Beulich
2019-03-15 11:02 ` [PATCH v8 39/50] x86emul: support of AVX512_IFMA insns Jan Beulich
2019-06-19 12:23 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:02 ` [PATCH v8 40/50] x86emul: support remaining AVX512_VBMI2 insns Jan Beulich
2019-06-19 12:25 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:04 ` [PATCH v8 41/50] x86emul: support AVX512_4FMAPS insns Jan Beulich
2019-06-19 14:58 ` [Xen-devel] " Andrew Cooper
2019-06-21 6:50 ` Jan Beulich
2019-03-15 11:04 ` [PATCH v8 42/50] x86emul: support AVX512_4VNNIW insns Jan Beulich
2019-06-19 14:58 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:04 ` [PATCH v8 43/50] x86emul: support AVX512_VNNI insns Jan Beulich
2019-06-19 15:01 ` [Xen-devel] " Andrew Cooper
2019-06-21 6:55 ` Jan Beulich
2019-03-15 11:05 ` [PATCH v8 44/50] x86emul: support VPCLMULQDQ insns Jan Beulich
2019-06-21 12:52 ` [Xen-devel] " Andrew Cooper
2019-06-21 13:44 ` Jan Beulich
2019-03-15 11:06 ` [PATCH v8 45/50] x86emul: support VAES insns Jan Beulich
2019-06-21 12:57 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:06 ` [PATCH v8 46/50] x86emul: support GFNI insns Jan Beulich
2019-06-21 13:19 ` [Xen-devel] " Andrew Cooper
2019-06-21 13:33 ` Andrew Cooper
2019-06-21 14:00 ` Jan Beulich
2019-06-21 14:20 ` Andrew Cooper
2019-06-21 15:02 ` Jan Beulich
2019-06-25 6:48 ` Jan Beulich
2019-03-15 11:07 ` [PATCH v8 47/50] x86emul: restore ordering within main switch statement Jan Beulich
2019-06-21 13:20 ` [Xen-devel] " Andrew Cooper
2019-03-15 11:07 ` [PATCH v8 48/50] x86emul: add an AES/VAES test case to the harness Jan Beulich
2019-06-21 13:36 ` [Xen-devel] " Andrew Cooper
2019-06-21 14:04 ` Jan Beulich
2019-06-21 14:20 ` Andrew Cooper
2019-03-15 11:08 ` [PATCH v8 49/50] x86emul: add a SHA " Jan Beulich
2019-06-21 13:51 ` [Xen-devel] " Andrew Cooper
2019-06-21 14:10 ` Jan Beulich
2019-06-21 14:23 ` Andrew Cooper
2019-03-15 11:08 ` [PATCH v8 50/50] x86emul: add a PCLMUL/VPCLMUL " Jan Beulich
2019-06-21 13:58 ` [Xen-devel] " Andrew Cooper
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5BAA3C7602000078001EBB19@prv1-mh.provo.novell.com \
--to=jbeulich@suse.com \
--cc=George.Dunlap@eu.citrix.com \
--cc=andrew.cooper3@citrix.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).