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>
Subject: [PATCH v3 05/25] x86emul: support FMA insns
Date: Thu, 07 Dec 2017 07:02:01 -0700 [thread overview]
Message-ID: <5A2957E9020000780019589D@prv-mh.provo.novell.com> (raw)
In-Reply-To: <5A29550C020000780019585B@prv-mh.provo.novell.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
--- a/tools/tests/x86_emulator/Makefile
+++ b/tools/tests/x86_emulator/Makefile
@@ -12,7 +12,7 @@ run: $(TARGET)
./$(TARGET)
SIMD := sse sse2 sse4 avx
-FMA := fma4
+FMA := fma4 fma
TESTCASES := blowfish $(SIMD) sse2-avx sse4-avx $(FMA)
blowfish-cflags := ""
@@ -33,6 +33,9 @@ avx-flts := 4 8
fma4-vecs := $(avx-vecs)
fma4-ints :=
fma4-flts := $(avx-flts)
+fma-vecs := $(avx-vecs)
+fma-ints :=
+fma-flts := $(avx-flts)
# When converting SSE to AVX, have the compiler avoid XMM0 to widen
# coverage of the VEX.vvvv checks in the emulator. We must not do this,
--- a/tools/tests/x86_emulator/simd-fma.c
+++ b/tools/tests/x86_emulator/simd-fma.c
@@ -21,24 +21,24 @@ ENTRY(fma_test);
#if VEC_SIZE == 16
# if FLOAT_SIZE == 4
# define addsub(x, y) __builtin_ia32_addsubps(x, y)
-# if defined(__FMA4__)
+# if defined(__FMA4__) || defined(__FMA__)
# define fmaddsub(x, y, z) __builtin_ia32_vfmaddsubps(x, y, z)
# endif
# elif FLOAT_SIZE == 8
# define addsub(x, y) __builtin_ia32_addsubpd(x, y)
-# if defined(__FMA4__)
+# if defined(__FMA4__) || defined(__FMA__)
# define fmaddsub(x, y, z) __builtin_ia32_vfmaddsubpd(x, y, z)
# endif
# endif
#elif VEC_SIZE == 32
# if FLOAT_SIZE == 4
# define addsub(x, y) __builtin_ia32_addsubps256(x, y)
-# if defined(__FMA4__)
+# if defined(__FMA4__) || defined(__FMA__)
# define fmaddsub(x, y, z) __builtin_ia32_vfmaddsubps256(x, y, z)
# endif
# elif FLOAT_SIZE == 8
# define addsub(x, y) __builtin_ia32_addsubpd256(x, y)
-# if defined(__FMA4__)
+# if defined(__FMA4__) || defined(__FMA__)
# define fmaddsub(x, y, z) __builtin_ia32_vfmaddsubpd256(x, y, z)
# endif
# endif
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -12,6 +12,7 @@
#include "sse4-avx.h"
#include "avx.h"
#include "fma4.h"
+#include "fma.h"
#define verbose false /* Switch to true for far more logging. */
@@ -53,6 +54,11 @@ static bool simd_check_fma4(void)
return cpu_has_fma4;
}
+static bool simd_check_fma(void)
+{
+ return cpu_has_fma;
+}
+
static void simd_set_regs(struct cpu_user_regs *regs)
{
if ( cpu_has_mmx )
@@ -155,6 +161,12 @@ static const struct {
SIMD(FMA4 scalar double, fma4, f8),
SIMD(FMA4 128bit double, fma4, 16f8),
SIMD(FMA4 256bit double, fma4, 32f8),
+ SIMD(FMA scalar single, fma, f4),
+ SIMD(FMA 128bit single, fma, 16f4),
+ SIMD(FMA 256bit single, fma, 32f4),
+ SIMD(FMA scalar double, fma, f8),
+ SIMD(FMA 128bit double, fma, 16f8),
+ SIMD(FMA 256bit double, fma, 32f8),
#undef SIMD_
#undef SIMD
};
--- a/tools/tests/x86_emulator/x86-emulate.h
+++ b/tools/tests/x86_emulator/x86-emulate.h
@@ -99,6 +99,14 @@ static inline uint64_t xgetbv(uint32_t x
(res.c & (1U << 0)) != 0; \
})
+#define cpu_has_fma ({ \
+ struct cpuid_leaf res; \
+ emul_test_cpuid(1, 0, &res, NULL); \
+ if ( !(res.c & (1U << 27)) || ((xgetbv(0) & 6) != 6) ) \
+ res.c = 0; \
+ (res.c & (1U << 12)) != 0; \
+})
+
#define cpu_has_sse4_1 ({ \
struct cpuid_leaf res; \
emul_test_cpuid(1, 0, &res, NULL); \
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -385,6 +385,9 @@ static const struct {
[0x37 ... 0x3f] = { .simd_size = simd_packed_int },
[0x40] = { .simd_size = simd_packed_int },
[0x41] = { .simd_size = simd_packed_int, .two_op = 1 },
+ [0x96 ... 0x9f] = { .simd_size = simd_packed_fp },
+ [0xa6 ... 0xaf] = { .simd_size = simd_packed_fp },
+ [0xb6 ... 0xbf] = { .simd_size = simd_packed_fp },
[0xc8 ... 0xcd] = { .simd_size = simd_other },
[0xdb] = { .simd_size = simd_packed_int, .two_op = 1 },
[0xdc ... 0xdf] = { .simd_size = simd_packed_int },
@@ -1606,6 +1609,7 @@ static bool vcpu_has(
#define vcpu_has_sse3() vcpu_has( 1, ECX, 0, ctxt, ops)
#define vcpu_has_pclmulqdq() vcpu_has( 1, ECX, 1, ctxt, ops)
#define vcpu_has_ssse3() vcpu_has( 1, ECX, 9, ctxt, ops)
+#define vcpu_has_fma() vcpu_has( 1, ECX, 12, ctxt, ops)
#define vcpu_has_cx16() vcpu_has( 1, ECX, 13, ctxt, ops)
#define vcpu_has_sse4_1() vcpu_has( 1, ECX, 19, ctxt, ops)
#define vcpu_has_sse4_2() vcpu_has( 1, ECX, 20, ctxt, ops)
@@ -7366,6 +7370,39 @@ x86_emulate(
generate_exception_if(vex.l, EXC_UD);
goto simd_0f_avx;
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x96): /* vfmaddsub132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x97): /* vfmsubadd132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x98): /* vfmadd132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x99): /* vfmadd132s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9a): /* vfmsub132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9b): /* vfmsub132s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9c): /* vfnmadd132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9d): /* vfnmadd132s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9e): /* vfnmsub132p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0x9f): /* vfnmsub132s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xa6): /* vfmaddsub213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xa7): /* vfmsubadd213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xa8): /* vfmadd213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xa9): /* vfmadd213s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xaa): /* vfmsub213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xab): /* vfmsub213s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xac): /* vfnmadd213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xad): /* vfnmadd213s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xae): /* vfnmsub213p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xaf): /* vfnmsub213s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xb6): /* vfmaddsub231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xb7): /* vfmsubadd231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xb8): /* vfmadd231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xb9): /* vfmadd231s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xba): /* vfmsub231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xbb): /* vfmsub231s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xbc): /* vfnmadd231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xbd): /* vfnmadd231s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xbe): /* vfnmsub231p{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ case X86EMUL_OPC_VEX_66(0x0f38, 0xbf): /* vfnmsub231s{s,d} {x,y}mm/mem,{x,y}mm,{x,y}mm */
+ host_and_vcpu_must_have(fma);
+ goto simd_0f_ymm;
+
case X86EMUL_OPC(0x0f38, 0xc8): /* sha1nexte xmm/m128,xmm */
case X86EMUL_OPC(0x0f38, 0xc9): /* sha1msg1 xmm/m128,xmm */
case X86EMUL_OPC(0x0f38, 0xca): /* sha1msg2 xmm/m128,xmm */
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -50,6 +50,7 @@
#define cpu_has_vmx boot_cpu_has(X86_FEATURE_VMX)
#define cpu_has_eist boot_cpu_has(X86_FEATURE_EIST)
#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3)
+#define cpu_has_fma boot_cpu_has(X86_FEATURE_FMA)
#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16)
#define cpu_has_pdcm boot_cpu_has(X86_FEATURE_PDCM)
#define cpu_has_pcid boot_cpu_has(X86_FEATURE_PCID)
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2017-12-07 14:02 UTC|newest]
Thread overview: 85+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-07 13:49 [PATCH v3 00/25] x86: emulator enhancements Jan Beulich
2017-12-07 13:58 ` [PATCH v3 01/25] x86emul: make decode_register() return unsigned long * Jan Beulich
2017-12-07 18:32 ` Andrew Cooper
2017-12-08 7:44 ` Jan Beulich
2017-12-07 13:59 ` [PATCH v3 02/25] x86emul: build SIMD tests with -Os Jan Beulich
2017-12-07 18:32 ` Andrew Cooper
2017-12-07 14:00 ` [PATCH v3 03/25] x86emul: support F16C insns Jan Beulich
2018-01-31 18:58 ` Andrew Cooper
2017-12-07 14:01 ` [PATCH v3 04/25] x86emul: support FMA4 insns Jan Beulich
2018-01-31 19:51 ` Andrew Cooper
2017-12-07 14:02 ` Jan Beulich [this message]
2018-02-01 16:15 ` [PATCH v3 05/25] x86emul: support FMA insns Andrew Cooper
2017-12-07 14:03 ` [PATCH v3 06/25] x86emul: support most remaining AVX2 insns Jan Beulich
2018-02-01 19:45 ` Andrew Cooper
2018-02-02 9:29 ` Jan Beulich
2017-12-07 14:03 ` [PATCH v3 07/25] x86emul: support AVX2 gather insns Jan Beulich
2018-02-01 20:53 ` Andrew Cooper
2018-02-02 9:44 ` Jan Beulich
2017-12-07 14:04 ` [PATCH v3 08/25] x86emul: add tables for XOP 08 and 09 extension spaces Jan Beulich
2018-02-02 11:43 ` Andrew Cooper
2018-02-02 15:15 ` Jan Beulich
2018-02-02 16:02 ` Andrew Cooper
2017-12-07 14:04 ` [PATCH v3 09/25] x86emul: support XOP insns Jan Beulich
2018-02-02 12:03 ` Andrew Cooper
2018-02-02 15:17 ` Jan Beulich
2018-02-05 13:01 ` Andrew Cooper
2017-12-07 14:05 ` [PATCH v3 10/25] x86emul: support 3DNow! insns Jan Beulich
2018-02-02 13:02 ` Andrew Cooper
2018-02-02 15:22 ` Jan Beulich
2018-02-02 16:04 ` Andrew Cooper
2017-12-07 14:06 ` [PATCH v3 11/25] x86emul: place test blobs in executable section Jan Beulich
2018-02-02 13:03 ` Andrew Cooper
2018-02-02 15:27 ` Jan Beulich
2018-02-05 13:11 ` Andrew Cooper
2018-02-05 13:55 ` Jan Beulich
2017-12-07 14:07 ` [PATCH v3 12/25] x86emul: abstract out XCRn accesses Jan Beulich
2018-02-02 13:29 ` Andrew Cooper
2018-02-02 17:05 ` Jan Beulich
2017-12-07 14:08 ` [PATCH v3 13/25] x86emul: adjust_bnd() should check XCR0 Jan Beulich
2018-02-02 13:30 ` Andrew Cooper
2018-02-02 16:19 ` Jan Beulich
2018-02-02 16:28 ` Andrew Cooper
2017-12-07 14:09 ` [PATCH v3 14/25] x86emul: make all FPU emulation use the stub Jan Beulich
2018-02-02 13:37 ` Andrew Cooper
2017-12-07 14:10 ` [PATCH v3 15/25] x86/HVM: eliminate custom #MF/#XM handling Jan Beulich
2018-02-02 13:38 ` Andrew Cooper
2017-12-07 14:11 ` [PATCH v3 16/25] x86emul: support SWAPGS Jan Beulich
2018-02-02 13:41 ` Andrew Cooper
2018-02-02 16:24 ` Jan Beulich
2017-12-07 14:11 ` [PATCH v3 17/25] x86emul: emulate {MONITOR, MWAIT}{, X} as no-op Jan Beulich
2018-02-02 14:05 ` Andrew Cooper
2017-12-07 14:12 ` [PATCH v3 18/25] x86emul: add missing suffixes in test harness Jan Beulich
2018-02-02 14:13 ` Andrew Cooper
2017-12-07 14:14 ` [PATCH v3 19/25] x86emul: tell cmpxchg hook whether LOCK is in effect Jan Beulich
2017-12-08 10:58 ` Paul Durrant
2018-02-02 14:13 ` Andrew Cooper
2017-12-07 14:15 ` [PATCH v3 20/25] x86emul: correctly handle CMPXCHG* comparison failures Jan Beulich
2018-02-02 14:49 ` Andrew Cooper
2018-02-05 8:07 ` Jan Beulich
2018-02-05 13:38 ` Andrew Cooper
2017-12-07 14:16 ` [PATCH v3 21/25] x86emul: add read-modify-write hook Jan Beulich
2018-02-02 16:13 ` Andrew Cooper
2018-02-05 8:22 ` Jan Beulich
2018-02-05 14:21 ` Andrew Cooper
2018-02-05 14:56 ` Jan Beulich
2017-12-07 14:16 ` [PATCH v3 22/25] x86/HVM: do actual CMPXCHG in hvmemul_cmpxchg() Jan Beulich
2017-12-07 14:38 ` Razvan Cojocaru
2017-12-08 10:38 ` Paul Durrant
2018-02-02 16:36 ` Andrew Cooper
2018-02-05 8:32 ` Jan Beulich
2018-02-05 16:09 ` Andrew Cooper
2018-02-05 16:49 ` Jan Beulich
2018-02-05 16:57 ` Andrew Cooper
2018-02-05 17:05 ` Jan Beulich
2017-12-07 14:17 ` [PATCH v3 23/25] x86/HVM: make use of new read-modify-write emulator hook Jan Beulich
2017-12-08 10:41 ` Paul Durrant
2018-02-02 16:37 ` Andrew Cooper
2018-02-05 8:34 ` Jan Beulich
2018-02-05 16:15 ` Andrew Cooper
2017-12-07 14:18 ` [PATCH v3 24/25] x86/shadow: fully move unmap-dest into common code Jan Beulich
2018-02-02 16:46 ` Andrew Cooper
2017-12-07 14:19 ` [PATCH v3 25/25] x86/shadow: fold sh_x86_emulate_{write, cmpxchg}() into their only callers Jan Beulich
2018-02-02 16:52 ` Andrew Cooper
2018-02-05 8:42 ` Jan Beulich
2018-02-05 12:16 ` Tim Deegan
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=5A2957E9020000780019589D@prv-mh.provo.novell.com \
--to=jbeulich@suse.com \
--cc=George.Dunlap@eu.citrix.com \
--cc=andrew.cooper3@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.