nowresult.csv

into	Latency	7.65	0.19
bound	Latency	12.74	0.0
pushad	Latency	15.62	0.0
aam_throughput	Latency	8.42	0.0
enter 4, 1	Latency	50.72	0.24
aam_latency	Latency	29.6	0.0
enter 4, 4	Latency	68.59	0.0
enter 4, 0	Latency	20.0	0.0
daa	Latency	23.37	0.0
enter 4, 2	Latency	63.99	0.0
enter 4, 3	Latency	69.15	0.0
das	Latency	25.5	0.0
aad	Latency	18.63	0.0
sahf	Latency	1.16	0.0
aaa	Latency	38.16	0.0
lahf_sahf	Latency	1.17	0.0
salc	Latency	5.88	0.0
leave	Latency	4.82	0.0
salc_inc_al	Latency	5.43	0.0
popad	Latency	12.22	0.02
aas	Latency	35.22	0.0
lahf	Latency	0.98	0.0
Case 1: Consecutive single loops	Latency	6.15	nan
Case 5: Loop with one branch having simple repetitive pattern of period count2 inside	Latency	0.74	0.15
Case 8: Loop with alternating indirect branch inside	Latency	1.18	0.23
Case 6: Loop with one branch having complex repetitive pattern of period count2 inside	Latency	1.92	0.2
Case 4: Loop with 2 alternating branches inside	Latency	3.68	2.86
Case 2: Nested loops	Latency	7.33	3.3
Case 3: Loop with 1 alternating branch inside	Latency	4.52	4.15
Case 7: Loop with one 0011 branch and one 00011 branch inside	Latency	0.75	0.28
Case 9: Loop with 3-way indirect branch inside	Latency	1.88	0.47
Case 1: Consecutive single loops	Latency	4.45	nan
Case 11: One loop with multiple branches inside	Latency	0.28	0.13
Case 8: Loop with alternating indirect branch inside	Latency	1.37	0.23
Case 6: Loop with one branch having complex repetitive pattern of period count2 inside	Latency	0.73	0.19
Case 4: Loop with 2 alternating branches inside	Latency	3.67	1.71
Case 2: Nested loops	Latency	7.35	3.33
Case 3: Loop with 1 alternating branch inside	Latency	4.24	3.41
Case 7: Loop with one 0011 branch and one 00011 branch inside	Latency	0.8	2.38
Case 10: One loop with multiple loops inside	Latency	-2.01	2.09
Case 9: Loop with 3-way indirect branch inside	Latency	1.77	0.37
Case 5: Loop with one branch having simple repetitive pattern of period count2 inside	Latency	1.9	0.21
stride1 = 4096, stride2 = 64	Latency	1.89	0.01
stride1 = 512, stride2 = 32	Latency	1.81	0.0
stride1 = 4096, stride2 = 512	Latency	1.81	0.0
stride1 = 256, stride2 = 32	Latency	1.96	0.0
stride1 = 2048, stride2 = 0	Latency	1.22	0.19
stride1 = 1024, stride2 = 8	Latency	0.99	0.0
stride1 = 2048, stride2 = 8	Latency	1.1	0.11
stride1 = 1024, stride2 = 0	Latency	0.99	0.0
stride1 = 4096, stride2 = 0	Latency	8.94	0.16
stride1 = 16384, stride2 = 0	Latency	9.7	0.22
stride1 = 128, stride2 = 64	Latency	1.81	0.0
stride1 = 4096, stride2 = 8	Latency	1.22	0.19
stride1 = 256, stride2 = 64	Latency	1.88	0.01
stride1 = 2048, stride2 = 32	Latency	1.96	0.0
stride1 = 1024, stride2 = 128	Latency	1.96	0.0
stride1 = 2048, stride2 = 1024	Latency	1.96	0.0
stride1 = 1024, stride2 = 64	Latency	1.88	0.01
stride1 = 2048, stride2 = 64	Latency	1.89	0.01
stride1 = 16384, stride2 = 8	Latency	1.13	0.17
stride1 = 4096, stride2 = 32	Latency	1.81	0.0
stride1 = 2048, stride2 = 512	Latency	1.89	0.01
stride1 = 1024, stride2 = 512	Latency	1.81	0.0
stride1 = 2048, stride2 = 256	Latency	1.88	0.01
stride1 = 2048, stride2 = 128	Latency	1.88	0.01
stride1 = 4096, stride2 = 128	Latency	1.96	0.0
stride1 = 512, stride2 = 64	Latency	1.96	0.0
stride1 = 256, stride2 = 128	Latency	1.81	0.0
stride1 = 64, stride2 = 32	Latency	1.88	0.01
stride1 = 1024, stride2 = 32	Latency	1.81	0.0
stride1 = 8192, stride2 = 0	Latency	8.96	0.19
stride1 = 1024, stride2 = 256	Latency	1.81	0.0
stride1 = 4096, stride2 = 1024	Latency	1.88	0.01
stride1 = 128, stride2 = 32	Latency	1.95	0.0
stride1 = 512, stride2 = 256	Latency	1.96	0.0
stride1 = 8192, stride2 = 8	Latency	1.21	0.18
stride1 = 512, stride2 = 128	Latency	1.88	0.01
stride1 = 4096, stride2 = 256	Latency	1.89	0.01
cvtpi2ps xmm, mmx / cvtps2pi mmx, xmm / POR mmx,mmx	Latency	4.31	0.0
cvtsi2sd xmm, r64 / cvtsd2si r64, xmm	Latency	12.87	0.0
movd xmm,m32	Throughput	1.32	0.0
movq xmm,r64	Throughput	1.0	0.0
cvtsi2ss xmm,r32	Throughput	5.96	0.0
movntpd m128, xmm / movaps xmm, m128	Latency	126.36	5.43
mov r8, m8	Throughput	1.19	0.0
movdqa m128, xmm	Throughput	1.8	0.0
movq2dq xmm, mmx	Throughput	1.07	0.0
cvtsd2si r64, xmm / cvtsi2sd xmm, r64 / MAXPD xmm,xmm	Latency	7.32	0.01
pextrb m8,xmm,1	Throughput	1.72	0.0
cvtsd2ss xmm,xmm	Latency	14.85	0.0
movlps m64,xmm	Throughput	1.66	0.0
movups m128,xmm	Throughput	1.66	0.0
movd xmm, m32 / movd m32, xmm	Latency	2.15	0.0
movntdqa xmm, m / movdqa m, xmm	Latency	2.15	0.0
cvtpd2ps xmm,[m128]	Throughput	1.42	0.0
mov r8h, m8	Throughput	1.29	0.0
cvtss2si r64, xmm	Throughput	0.99	0.0
cvtps2pi mmx, xmm	Throughput	1.07	0.0
cvtdq2ps xmm,xmm	Latency	14.85	0.0
movd mmx, r32 / movd r32, mmx	Latency	3.75	0.0
mov m32,r32	Throughput	1.8	0.0
mov m64,r64	Throughput	1.66	0.0
pextrq r64, xmm,1 / movq xmm, r64	Latency	3.47	0.0
mov r8h,r8	Throughput	0.97	0.0
cvtsi2sd xmm,r64	Throughput	1.98	0.0
mov r8h,r8h	Latency	0.99	0.0
movhps m64,xmm	Throughput	1.55	0.0
movntdqa xmm,m	Throughput	1.32	0.0
movsd m64, xmm / movsd xmm, m64	Latency	2.22	0.04
movntps m128,xmm	Throughput	1.67	0.0
mov m16,r16	Throughput	1.66	0.0
cvtps2pi mmx, xmm / cvtpi2ps xmm, mmx / POR xmm,xmm	Latency	3.97	0.0
cvtpd2dq xmm,[m128]	Throughput	1.42	0.0
cvtpi2pd xmm, mmx / cvtpd2pi mmx, xmm / POR mmx,mmx	Latency	4.65	0.0
cvtpi2pd xmm,[m]	Throughput	1.34	0.0
pextrw r32,xmm,1	Throughput	1.08	0.0
cvtsi2ss xmm,[m32]	Throughput	6.41	0.17
cvtsd2si r32, xmm	Throughput	0.99	0.0
cvtss2sd xmm, xmm	Latency	16.09	0.0
movq r64, xmm	Throughput	1.08	0.0
mov m16, r16 / mov r16, m16	Latency	2.48	0.0
cvtsd2si r64,[m64]	Throughput	1.24	0.0
mov m8, r8h / mov r8h, m8	Latency	15.02	0.0
movlpd xmm, m	Throughput	1.42	0.0
cvtpi2ps xmm,[m]	Throughput	1.34	0.0
movd xmm, r32	Throughput	1.08	0.0
pinsrq xmm,r64,1	Throughput	1.0	0.0
movdqa m128, xmm / movdqa xmm, m128	Latency	2.04	0.03
movq mmx, r64 / movq r64, mmx	Latency	3.75	0.0
movsd xmm,xmm	Latency	1.16	0.0
cvtdq2ps xmm, xmm / cvtps2dq xmm, xmm	Latency	2.68	0.0
cvtpi2pd xmm, mmx / cvtpd2pi mmx, xmm	Latency	4.68	0.0
movapd m128, xmm / movapd xmm, m128	Latency	2.15	0.0
movss xmm, xmm	Latency	1.22	0.03
pextrw r32,mmx,1	Throughput	0.99	0.0
cvtpd2dq xmm, xmm	Latency	5.96	0.0
movlhps xmm,xmm	Latency	1.16	0.0
movapd xmm, m128	Throughput	1.43	0.0
cvtps2pi mmx,[m]	Throughput	1.24	0.0
pinsrw xmm,r32,1	Throughput	1.08	0.0
pinsrw xmm, r32,1 / movd r32, xmm	Latency	4.29	0.0
cvtsd2si r64, xmm / cvtsi2sd xmm, r64 / POR xmm,xmm	Latency	8.25	0.0
cvtsd2ss xmm, xmm / cvtss2sd xmm, xmm / MAXPD xmm,xmm	Latency	1.99	0.0
mov m8, r8 / mov r8, m8	Latency	2.68	0.0
movdqu xmm, m128	Throughput	1.32	0.0
cvtpi2ps xmm, mmx / cvtps2pi mmx, xmm	Latency	4.83	0.0
movq xmm, m64	Throughput	1.43	0.0
pinsrb xmm,r32,1	Throughput	1.0	0.0
cvtsi2sd xmm, r64 / cvtsd2si r64, xmm / OR r64,r64	Latency	8.28	0.0
cvtsi2sd xmm,r32	Throughput	6.46	0.0
movdqa xmm, xmm / movdqa xmm, xmm / POR xmm,xmm	Latency	1.0	0.0
movd m32, xmm	Throughput	1.66	0.0
movaps xmm, xmm / movaps xmm, xmm / POR xmm,xmm	Latency	2.53	0.0
mov r8h, m8 / mov m8, r8h	Latency	15.02	0.0
pmovmskb r32,xmm	Throughput	0.99	0.0
cvtsi2ss xmm, r64 / cvtss2si r64, xmm	Latency	12.93	0.03
cvtss2si r32,[m32]	Throughput	1.24	0.0
mov r8h,m8	Throughput	1.28	0.0
movaps xmm, m128	Throughput	1.32	0.0
pinsrw xmm,m16,1	Throughput	0.99	0.0
pinsrd xmm, r32,1 / movd r32, xmm	Latency	4.29	0.0
movntpd m128,xmm	Throughput	1.55	0.0
pextrw m16,xmm,1	Throughput	1.72	0.0
movmskps r32, xmm / movd xmm, r32	Latency	3.75	0.0
cvtsd2si r64, xmm	Throughput	1.08	0.0
movq m64, xmm / movq xmm, m64	Latency	1.98	0.0
movq mmx, m64	Throughput	1.43	0.0
pextrd r32,xmm,1	Throughput	1.0	0.0
movdqa m, xmm	Throughput	1.66	0.0
cvtsi2sd xmm, r32 / cvtsd2si r32, xmm / OR r32,r32	Latency	3.36	0.02
movq m64,mmx	Throughput	1.66	0.0
pextrq m64,xmm,1	Throughput	1.72	0.0
cvtpd2pi mmx, xmm	Throughput	1.57	0.0
movlpd m, xmm / movlpd xmm, m	Latency	4.29	0.0
movmskpd r32,xmm	Throughput	1.17	0.0
mov r8h, r8h	Latency	1.07	0.0
movdqa xmm, xmm / movdqa xmm, xmm / MAXPS xmm,xmm	Latency	2.69	0.02
pextrd r32, xmm,1 / movd xmm, r32	Latency	3.76	0.0
pextrb r32,xmm,1	Throughput	1.0	0.0
movaps m128,xmm	Throughput	1.8	0.0
movlhps xmm, xmm	Latency	1.15	0.0
movdq2q mmx, xmm / movq2dq xmm, mmx	Latency	1.08	0.0
mov m8,r8h	Throughput	1.66	0.0
pinsrd xmm,m32,1	Throughput	1.1	0.08
cvtsd2si r32, xmm / cvtsi2sd xmm, r32 / POR xmm,xmm	Latency	4.68	0.01
movd mmx,r32	Throughput	1.0	0.0
cvtsd2si r32,[m64]	Throughput	1.24	0.0
movq m64,xmm	Throughput	1.8	0.0
cvtdq2pd xmm, xmm / cvtpd2dq xmm, xmm / MAXPD xmm,xmm	Latency	4.52	0.0
movaps m128, xmm / movups xmm, m128	Latency	1.98	0.0
movd r32, xmm	Throughput	1.08	0.0
pinsrb xmm,m8,1	Throughput	1.08	0.0
movlps m64, xmm / movlps xmm, m64	Latency	3.96	0.0
movq mmx,r64	Throughput	1.08	0.0
movsd m64,xmm	Throughput	1.66	0.0
cvtps2pi mmx, xmm / cvtpi2ps xmm, mmx / MAXPS xmm,xmm	Latency	3.69	0.02
movss xmm, xmm / movss xmm, xmm	Latency	1.16	0.0
pinsrw mmx, r32,1 / movd r32, mmx	Latency	4.29	0.0
movhps xmm, m64	Throughput	1.42	0.0
cvtpd2ps xmm,xmm	Latency	6.06	0.34
movss m32,xmm	Throughput	1.66	0.0
movdqu m128,xmm	Throughput	1.66	0.0
movsd xmm, xmm / movsd xmm, xmm	Latency	1.16	0.0
movq r64, mmx	Throughput	0.99	0.0
cvtdq2pd xmm, xmm / cvtpd2dq xmm, xmm / POR xmm,xmm	Latency	4.69	0.02
movlps xmm, m64	Throughput	1.31	0.0
movhps m64, xmm / movhps xmm, m64	Latency	5.49	0.03
cvtsi2ss xmm,r64	Throughput	1.98	0.0
mov r64, m64	Throughput	1.56	0.27
movaps xmm, xmm / movaps xmm, xmm / MAXPS xmm,xmm	Latency	2.13	0.0
movdqa m128,xmm	Throughput	1.8	0.0
movdqa xmm, m128	Throughput	1.43	0.0
movq xmm, m64 / movq m64, xmm	Latency	2.15	0.0
movss xmm,xmm	Latency	1.16	0.0
lddqu xmm,m128	Throughput	1.32	0.0
cvtpi2pd xmm,mmx	Throughput	0.99	0.0
movd xmm,r32	Throughput	1.05	0.02
mov r16, m16	Throughput	1.29	0.0
movapd m128,xmm	Throughput	1.66	0.0
cvtps2dq xmm,[m]	Throughput	1.24	0.0
movss xmm, m32	Throughput	1.43	0.0
cvtsd2si r32, xmm / cvtsi2sd xmm, r32 / MAXPD xmm,xmm	Latency	3.64	0.0
mov r8h, r8 / mov r8, r8h	Latency	0.99	0.0
mov m8,r8	Throughput	1.66	0.0
cvtsd2ss xmm, xmm / cvtss2sd xmm, xmm / POR xmm,xmm	Latency	2.98	0.0
cvtsi2sd xmm, r32 / cvtsd2si r32, xmm	Latency	4.83	0.0
pextrd m32,xmm,1	Throughput	1.72	0.0
cvtps2pd xmm,[m64]	Throughput	1.43	0.0
pinsrd xmm,r32,1	Throughput	1.04	0.0
lddqu xmm, m128 / movdqa m128, xmm	Latency	2.15	0.0
mov m8, r8h	Throughput	1.8	0.0
cvtsd2ss xmm, xmm / cvtss2sd xmm, xmm	Latency	1.98	0.0
movd r32, mmx	Throughput	1.07	0.0
pinsrq xmm,m64,1	Throughput	1.0	0.0
cvtdq2pd xmm,xmm	Latency	5.96	0.0
cvtss2sd xmm,m32	Throughput	6.33	0.03
movntq m64, mmx / movq mmx, m64	Latency	127.23	5.09
movaps m128, xmm / movaps xmm, m128	Latency	1.98	0.0
movq m64, mmx / movq mmx, m64	Latency	2.15	0.0
movmskps r32,xmm	Throughput	0.99	0.0
mov r8h, r8h / mov r8h, r8h	Latency	0.99	0.0
cvtps2pd xmm, xmm	Latency	5.5	0.0
movlhps xmm, xmm / movlhps xmm, xmm	Latency	1.16	0.0
cvtdq2ps xmm,[m]	Throughput	1.24	0.0
cvtdq2pd xmm,[m64]	Throughput	1.45	0.0
cvtsd2ss xmm,m64	Throughput	6.34	0.04
movq xmm, r64	Throughput	1.0	0.0
pinsrb xmm, r32,1 / movd r32, xmm	Latency	4.35	0.03
cvtsi2sd xmm,[m64]	Throughput	1.98	0.0
cvtss2si r32, xmm / cvtsi2ss xmm, r32 / MAXPS xmm,xmm	Latency	3.69	0.02
pextrb r32, xmm,1 / movd xmm, r32	Latency	3.47	0.0
pmovmskb r32, xmm / movd xmm, r32	Latency	3.81	0.03
movdqu m128, xmm / movdqu xmm, m128	Latency	2.33	0.27
movq m64, xmm	Throughput	1.66	0.0
cvtps2dq xmm, xmm	Latency	18.3	0.04
movnti m32,r32	Throughput	1.54	0.0
cvtpd2pi mmx,[m]	Throughput	1.42	0.0
movmskpd r32, xmm / movd xmm, r32	Latency	3.47	0.0
pextrw r32, xmm,1 / movd xmm, r32	Latency	3.47	0.0
movd mmx, r32	Throughput	1.08	0.0
movnti m32, r32 / mov r32, m32	Latency	127.19	4.57
movups xmm, m128	Throughput	1.32	0.0
cvtdq2pd xmm, xmm / cvtpd2dq xmm, xmm	Latency	4.75	0.04
cvtss2si r32, xmm	Throughput	0.99	0.0
pinsrq xmm, r64,1 / movq r64, xmm	Latency	4.29	0.0
pinsrw mmx,r32,1	Throughput	1.08	0.0
cvtpd2ps xmm, xmm / cvtps2pd xmm, xmm	Latency	4.68	0.0
cvtsi2ss xmm, r32 / cvtss2si r32, xmm / OR r32,r32	Latency	3.36	0.02
movups m128, xmm / movaps xmm, m128	Latency	2.15	0.0
movsd xmm, xmm	Latency	1.16	0.0
cvtdq2ps xmm, xmm / cvtps2dq xmm, xmm / POR xmm,xmm	Latency	3.02	0.01
cvtss2si r32, xmm / cvtsi2ss xmm, r32 / POR xmm,xmm	Latency	4.68	0.02
movd xmm, r32 / movd r32, xmm	Latency	3.47	0.0
cvtpi2ps xmm,mmx	Throughput	1.4	0.0
movss m32, xmm / movss xmm, m32	Latency	2.15	0.0
mov r8, r8h	Throughput	0.97	0.0
movq xmm,m64	Throughput	1.32	0.0
cvtsi2sd xmm,[m32]	Throughput	6.27	0.0
movdq2q mmx,xmm	Throughput	0.99	0.0
movntdq m128, xmm / movdqa xmm, m128	Latency	124.95	0.48
movlpd m,xmm	Throughput	1.66	0.0
movntq m64,mmx	Throughput	1.82	0.0
mov m64, r64 / mov r64, m64	Latency	1.98	0.0
pextrq r64,xmm,1	Throughput	1.0	0.0
mov r32, m32	Throughput	1.43	0.0
movntdq m128,xmm	Throughput	1.67	0.0
movq xmm, r64 / movq r64, xmm	Latency	3.47	0.0
cvtdq2ps xmm, xmm / cvtps2dq xmm, xmm / MAXPS xmm,xmm	Latency	11.84	0.0
mov m32, r32 / mov r32, m32	Latency	1.98	0.0
cvtpd2pi mmx, xmm / cvtpi2pd xmm, mmx / POR xmm,xmm	Latency	4.64	0.0
cvtpd2pi mmx, xmm / cvtpi2pd xmm, mmx / MAXPD xmm,xmm	Latency	3.69	0.02
cvtsi2ss xmm, r32 / cvtss2si r32, xmm	Latency	4.83	0.0
movntps m128, xmm / movaps xmm, m128	Latency	124.78	0.39
movsd xmm, m64	Throughput	1.43	0.0
pextrw r32, mmx,1 / movd mmx, r32	Latency	3.76	0.0
Case 1: SSE2	Latency	0.74	0.0
div , registersize 32, 1 / 1	Throughput	4.97	0.0
idiv , registersize 32	Throughput	7.22	0.01
idiv , registersize 16	Throughput	7.61	0.0
idiv , registersize 32, 1 / 1	Throughput	4.64	0.0
idiv , registersize 64, 1 / 1	Throughput	61.34	4.37
Throughput with memory operand: idiv , registersize 8, 1 / 1	Throughput	6.99	0.01
idiv , registersize 8, 1 / 1	Throughput	6.99	0.01
Throughput with memory operand: div , registersize 32, 1 / 1	Throughput	4.97	0.0
div , registersize 8	Throughput	4.97	0.0
Throughput with memory operand: div , registersize 8, 1 / 1	Throughput	4.97	0.0
div , registersize 16	Throughput	5.96	0.0
div , registersize 16, 1 / 1	Throughput	5.96	0.0
idiv , registersize 8	Throughput	6.95	0.0
Throughput with memory operand: idiv , registersize 32, 1 / 1	Throughput	5.06	0.01
div , registersize 32	Throughput	6.99	0.01
idiv , registersize 64	Throughput	66.91	0.51
idiv , registersize 16, 1 / 1	Throughput	7.62	0.0
div , registersize 64, 1 / 1	Throughput	50.36	3.88
Throughput with memory operand: idiv , registersize 64, 1 / 1	Throughput	61.55	3.96
div , registersize 8, 1 / 1	Throughput	4.97	0.0
Throughput with memory operand: div , registersize 64, 1 / 1	Throughput	52.04	0.03
Throughput with memory operand: div , registersize 16, 1 / 1	Throughput	5.96	0.0
Throughput with memory operand: idiv , registersize 16, 1 / 1	Throughput	7.66	0.02
div , registersize 64	Throughput	54.97	1.9
cvtpd2ps xmm,xmm + maxps xmm,xmm	Latency	10.69	0.0
dppd xmm,xmm + por xmm,xmm	Latency	7.15	0.03
pshufd xmm,xmm	Latency	0.99	0.0
cvtps2dq xmm,xmm + maxps xmm,xmm	Latency	9.65	0.0
insertps xmm,xmm + por xmm,xmm	Latency	3.09	0.0
sqrtps xmm,xmm + por xmm,xmm	Latency	12.87	0.0
movsldup xmm,xmm + por xmm,xmm	Latency	3.36	0.0
movss xmm,xmm + por xmm,xmm	Latency	3.1	0.0
shufps xmm,xmm + addps xmm,xmm	Latency	2.98	0.0
maxpd xmm,xmm	Latency	2.15	0.0
cvtps2dq xmm,xmm + por xmm,xmm	Latency	3.75	0.0
pshufd xmm,xmm + por xmm,xmm	Latency	1.08	0.0
pshufd xmm,xmm + addps xmm,xmm	Latency	3.76	0.0
cvtps2pd xmm,xmm + maxps xmm,xmm	Latency	9.86	0.0
andps xmm,xmm + por xmm,xmm	Latency	3.34	0.0
dppd + maxpd + por xmm,xmm	Latency	5.96	0.0
movhlps xmm,xmm	Latency	1.16	0.0
paddw xmm,xmm + por xmm,xmm	Latency	1.07	0.0
dpps xmm,xmm + por xmm,xmm	Latency	11.46	0.03
blendps xmm,xmm + por xmm,xmm	Latency	3.76	0.0
mulps xmm,xmm	Latency	3.22	0.0
orps xmm,xmm + por xmm,xmm	Latency	3.08	0.0
maxps xmm,xmm + paddw xmm,xmm	Latency	3.76	0.0
shufps xmm,xmm + por xmm,xmm	Latency	3.36	0.0
cvtps2dq + por + maxps xmm,xmm	Latency	2.98	0.0
roundps xmm,xmm + maxps xmm,xmm	Latency	3.22	0.0
movddup xmm,xmm + maxpd xmm,xmm	Latency	2.75	0.0
dpps + por + maxps xmm,xmm	Latency	7.95	0.0
movsldup xmm,xmm + maxps xmm,xmm	Latency	2.75	0.0
pblendw xmm,xmm + maxpd xmm,xmm	Latency	3.75	0.0
movsd xmm,xmm	Latency	1.16	0.0
pblendw xmm,xmm	Latency	0.99	0.0
movdqa xmm,xmm	Latency	0.99	0.0
dpps + maxps + por xmm,xmm	Latency	8.97	0.0
pblendw xmm,xmm + por xmm,xmm	Latency	0.99	0.0
cvtdq2ps xmm,xmm + maxps xmm,xmm	Latency	8.91	0.0
shufps xmm,xmm + maxps xmm,xmm	Latency	2.98	0.0
maxps xmm,xmm	Latency	1.98	0.0
maxps xmm,xmm + por xmm,xmm	Latency	3.47	0.0
movdqa xmm,xmm + maxps xmm,xmm	Latency	3.75	0.0
addps xmm,xmm	Latency	1.98	0.0
pshufd xmm,xmm + maxpd xmm,xmm	Latency	3.76	0.0
haddps + por + maxps xmm,xmm	Latency	3.97	0.0
movsd xmm,xmm + maxpd xmm,xmm	Latency	2.75	0.0
sqrtps xmm,xmm + maxps xmm,xmm	Latency	13.55	0.19
haddps xmm,xmm + por xmm,xmm	Latency	4.83	0.0
addpd xmm,xmm + por xmm,xmm	Latency	3.47	0.0
mulps xmm,xmm + maxps xmm,xmm	Latency	2.97	0.0
addps xmm,xmm + por xmm,xmm	Latency	3.47	0.0
por xmm,xmm	Latency	0.99	0.0
haddps xmm,xmm	Latency	5.42	0.34
cvtdq2ps + por + maxps xmm,xmm	Latency	7.33	0.02
cvtps2pd xmm,xmm	Latency	5.5	0.0
haddps xmm,xmm + maxps xmm,xmm	Latency	3.47	0.0
addps xmm,xmm + maxps xmm,xmm	Latency	2.15	0.0
insertps xmm,xmm	Latency	1.16	0.0
sqrtps xmm,xmm	Latency	21.85	0.04
addpd xmm,xmm	Latency	2.15	0.0
roundps xmm,xmm + por xmm,xmm	Latency	4.46	0.0
shufpd xmm,xmm + maxpd xmm,xmm	Latency	2.75	0.0
dppd xmm,xmm + maxpd xmm,xmm	Latency	6.76	0.0
cvtps2pd xmm,xmm + por xmm,xmm	Latency	5.36	0.0
maxps xmm,xmm + orps xmm,xmm	Latency	2.98	0.0
movddup xmm,xmm	Latency	1.26	0.0
movaps xmm,xmm + por xmm,xmm	Latency	3.08	0.0
cvtpd2ps xmm,xmm	Latency	5.5	0.0
orps xmm,xmm + maxps xmm,xmm	Latency	2.98	0.0
dpps xmm,xmm	Latency	15.68	0.2
movdqa xmm,xmm + por xmm,xmm	Latency	1.08	0.0
blendps xmm,xmm	Latency	1.08	0.0
unpcklps xmm,xmm + por xmm,xmm	Latency	3.34	0.0
roundps xmm,xmm	Latency	3.96	0.0
movss xmm,xmm	Latency	1.16	0.0
movss xmm,xmm + maxps xmm,xmm	Latency	2.98	0.0
cvtdq2ps xmm,xmm + por xmm,xmm	Latency	3.75	0.0
cvtdq2ps xmm,xmm	Latency	16.09	0.0
shufpd xmm,xmm	Latency	1.25	0.0
haddps + maxps + por xmm,xmm	Latency	3.64	0.0
movsldup xmm,xmm	Latency	1.16	0.0
addps xmm,xmm + maxpd xmm,xmm	Latency	16.09	0.0
shufps xmm,xmm	Latency	1.16	0.0
shufpd xmm,xmm + por xmm,xmm	Latency	3.09	0.0
cvtps2dq + maxps + por xmm,xmm	Latency	7.62	0.0
movddup xmm,xmm + por xmm,xmm	Latency	3.36	0.0
andps xmm,xmm	Latency	1.16	0.0
movaps xmm,xmm + maxps xmm,xmm	Latency	2.75	0.0
paddw xmm,xmm + orps xmm,xmm	Latency	3.09	0.0
movsd xmm,xmm + por xmm,xmm	Latency	3.16	0.03
movhlps xmm,xmm + maxps xmm,xmm	Latency	2.75	0.0
cvtdq2ps + maxps + por xmm,xmm	Latency	2.98	0.0
pshufd xmm,xmm + paddd xmm,xmm	Latency	1.08	0.0
blendps xmm,xmm + maxps xmm,xmm	Latency	1.98	0.0
orps xmm,xmm	Latency	1.25	0.0
maxpd xmm,xmm + por xmm,xmm	Latency	3.75	0.0
movaps xmm,xmm	Latency	1.15	0.0
addpd xmm,xmm + orpd xmm,xmm	Latency	2.75	0.0
insertps xmm,xmm + maxps xmm,xmm	Latency	2.98	0.0
cvtps2dq xmm,xmm	Latency	16.83	0.0
addps xmm,xmm + addpd xmm,xmm	Latency	16.09	0.0
maxpd xmm,xmm + orpd xmm,xmm	Latency	2.75	0.0
addps xmm,xmm + addps xmm,xmm	Latency	1.98	0.0
unpcklps xmm,xmm	Latency	1.16	0.0
mulps xmm,xmm + por xmm,xmm	Latency	3.04	0.04
shufps xmm,xmm + paddd xmm,xmm	Latency	3.1	0.0
movhlps xmm,xmm + por xmm,xmm	Latency	3.34	0.0
cvtpd2ps xmm,xmm + por xmm,xmm	Latency	4.46	0.0
unpcklps xmm,xmm + maxps xmm,xmm	Latency	3.05	0.04
dppd xmm,xmm	Latency	9.31	0.0
dpps xmm,xmm + maxps xmm,xmm	Latency	11.14	0.04
maxps xmm,xmm + maxps xmm,xmm	Latency	1.98	0.0
dppd + por + maxpd xmm,xmm	Latency	5.89	0.6
paddw xmm,xmm	Latency	0.99	0.0
andps xmm,xmm + maxps xmm,xmm	Latency	2.75	0.0
shufpd r128,r128,i	Throughput	0.54	0.0
mulpd r128,r128	Throughput	2.12	0.0
orpd r128,[m]	Throughput	1.3	0.0
movshdup r128,r128	Throughput	0.57	0.0
dpps r128,[m128],i	Throughput	9.55	0.0
cvttps2dq r128,[m]	Throughput	1.23	0.0
mulps r128,r128	Throughput	1.06	0.0
comiss r128,[m]	Throughput	1.23	0.0
andps r128,[m]	Throughput	1.41	0.0
minps r128,[m]	Throughput	1.23	0.0
unpcklpd r128,r128	Throughput	0.57	0.0
minsd r128,r128	Throughput	0.98	0.0
comiss r128,r128	Throughput	0.98	0.0
divss r128,r128 (best case)	Latency	13.11	0.3
maxss r128,[m]	Throughput	1.23	0.0
Throughput with memory operand: sqrtpd r128,[m128] (worst case)	Throughput	119.92	0.03
cmpeqss r128,r128	Throughput	0.98	0.0
divsd r128,r128 (best case)	Latency	15.25	0.0
cmpeqps r128,r128	Throughput	0.98	0.0
Throughput with memory operand: sqrtsd r128,[m128] (best case)	Throughput	60.92	0.01
divpd r128,r128 (best case)	Latency	24.64	0.01
Throughput with memory operand: sqrtpd r128,[m128] (best case)	Throughput	119.94	0.03
dppd r128,r128,i	Throughput	6.37	0.0
rcpss r128,r128	Latency	5.29	0.0
sqrtsd r128,r128 (worst case)	Latency	61.16	2.86
cmpeqps r128,[m]	Throughput	1.23	0.0
andps r128,r128	Throughput	0.54	0.0
Throughput with memory operand: sqrtsd r128,[m128] (worst case)	Throughput	61.07	0.09
mulss r128,r128	Throughput	0.98	0.0
roundpd r128,[m128],i	Throughput	1.96	0.0
roundpd r128,r128,i	Throughput	2.13	0.0
mulsd r128,[m]	Throughput	1.96	0.0
orpd r128,r128	Throughput	0.52	0.0
Throughput with memory operand: sqrtss r128,[m128] (worst case)	Throughput	32.93	1.09
movapd r128,[m]	Throughput	1.41	0.0
movshdup r128,[m]	Throughput	1.31	0.0
ucomisd r128,[m]	Throughput	1.23	0.0
roundsd r128,[m128],i	Throughput	1.97	0.0
sqrtpd r128,r128 (worst case)	Latency	119.53	4.96
Throughput with memory operand: rcpss r128,[m128]	Throughput	4.9	0.0
unpckhps r128,[m]	Throughput	1.3	0.0
cmpltpd r128,r128	Throughput	0.98	0.0
movapd r128,r128	Throughput	0.57	0.0
cvtps2pd r128,[m]	Throughput	1.31	0.0
blendps r128,[m128],i	Throughput	0.99	0.0
rsqrtss r128,r128	Latency	5.3	0.0
haddps r128,r128	Throughput	2.94	0.0
roundps r128,r128,i	Throughput	1.96	0.0
ucomisd r128,r128	Throughput	0.98	0.0
Throughput with memory operand: rsqrtss r128,[m128]	Throughput	5.31	0.0
cvtdq2ps r128,r128	Throughput	1.06	0.0
shufps r128,r128,i	Throughput	0.54	0.0
rsqrtps r128,r128	Latency	13.7	0.04
addss r128,[m]	Throughput	1.33	0.0
Throughput with memory operand: sqrtps r128,[m128] (best case)	Throughput	62.88	0.01
movups r128,r128	Throughput	0.54	0.0
maxpd r128,[m]	Throughput	1.23	0.0
shufps r128,[m128],i	Throughput	1.41	0.0
shufpd r128,[m128],i	Throughput	1.41	0.0
hsubpd r128,[m]	Throughput	4.9	0.0
movupd r128,[m]	Throughput	1.3	0.0
movaps r128,r128	Throughput	0.54	0.0
haddps r128,[m]	Throughput	4.9	0.0
roundps r128,[m128],i	Throughput	2.13	0.0
roundss r128,[m128],i	Throughput	1.96	0.0
sqrtss r128,r128 (best case)	Latency	32.97	1.59
subsd r128,r128	Throughput	0.98	0.0
movupd r128,r128	Throughput	0.57	0.0
movddup r128,[m]	Throughput	1.3	0.0
dpps r128,r128,i	Throughput	8.81	0.0
movddup r128,r128	Throughput	0.53	0.0
hsubpd r128,r128	Throughput	2.94	0.0
unpcklpd r128,[m]	Throughput	1.3	0.0
blendpd r128,r128,i	Throughput	0.98	0.0
mulps r128,[m]	Throughput	1.23	0.0
cvtpd2ps r128,[m]	Throughput	1.41	0.0
cvtdq2ps r128,[m]	Throughput	1.23	0.0
addps r128,[m]	Throughput	1.23	0.0
cvtpd2ps r128,r128	Throughput	1.43	0.0
divpd r128,r128 (worst case)	Latency	19.56	116.23
movaps r128,[m]	Throughput	1.41	0.0
maxss r128,r128	Throughput	0.98	0.0
cmpeqss r128,[m]	Throughput	1.23	0.0
addss r128,r128	Throughput	0.98	0.0
Throughput with memory operand: sqrtps r128,[m128] (worst case)	Throughput	63.07	0.31
rcpps r128,r128	Latency	13.7	0.04
blendpd r128,[m128],i	Throughput	0.99	0.0
movups r128,[m]	Throughput	1.3	0.0
minsd r128,[m]	Throughput	1.23	0.0
Throughput with memory operand: sqrtss r128,[m128] (best case)	Throughput	32.42	0.01
roundsd r128,r128,i	Throughput	1.96	0.0
mulsd r128,r128	Throughput	1.96	0.0
cmpltpd r128,[m]	Throughput	1.24	0.0
subpd r128,r128	Throughput	0.98	0.0
sqrtps r128,r128 (best case)	Latency	63.15	3.16
movsldup r128,r128	Throughput	0.53	0.0
sqrtsd r128,r128 (best case)	Latency	61.15	2.46
sqrtpd r128,r128 (best case)	Latency	118.95	0.66
minps r128,r128	Throughput	0.98	0.0
sqrtps r128,r128 (worst case)	Latency	62.37	0.03
Throughput with memory operand: rcpps r128,[m128]	Throughput	22.29	0.72
cvtpd2dq r128,[m]	Throughput	1.53	0.0
divps r128,r128 (worst case)	Latency	14.33	28.79
Throughput with memory operand: rsqrtps r128,[m128]	Throughput	22.08	0.55
blendps r128,r128,i	Throughput	0.99	0.0
cvtps2pd r128,r128	Throughput	1.06	0.0
mulss r128,[m]	Throughput	1.23	0.0
cvtdq2pd r128,[m]	Throughput	1.33	0.0
subpd r128,[m]	Throughput	1.23	0.0
divps r128,r128 (best case)	Latency	23.38	0.01
addsubps r128,r128	Throughput	0.98	0.0
sqrtss r128,r128 (worst case)	Latency	32.34	0.34
movsldup r128,[m]	Throughput	1.75	1.03
subsd r128,[m]	Throughput	1.23	0.0
cvttps2dq r128,r128	Throughput	1.06	0.0
cvtdq2pd r128,r128	Throughput	0.99	0.0
divsd r128,r128 (worst case)	Latency	10.69	28.59
addps r128,r128	Throughput	0.98	0.0
unpckhps r128,r128	Throughput	0.54	0.0
addsubps r128,[m]	Throughput	1.24	0.0
cvtpd2dq r128,r128	Throughput	1.43	0.0
dppd r128,[m128],i	Throughput	5.88	0.0
divss r128,r128 (worst case)	Latency	7.9	11.3
maxpd r128,r128	Throughput	0.98	0.0
mulpd r128,[m]	Throughput	1.96	0.0
roundss r128,r128,i	Throughput	1.96	0.0
Throughput with memory source operand: cmp r64,[m64]	Throughput	1.07	0.0
Latency with memory destination operand: cmp [m64],r64	Latency	0.98	0.0
Throughput with memory destination operand: xchg [m32],r32	Throughput	17.85	1.81
Latency with memory destination operand: add [m64],r64	Latency	4.9	0.0
inc r64	Throughput	0.59	0.0
xchg r32,r32	Throughput	1.5	0.0
Throughput with memory destination operand: xor [m16],r16	Throughput	1.91	0.0
Latency with memory destination operand: test [m64],r64	Latency	0.98	0.0
Throughput with memory destination operand: add [m32],r32	Throughput	1.92	0.0
Latency with memory operand: sub [m32], i	Latency	5.31	0.0
mov r8, i	Throughput	0.64	0.0
dec r32	Throughput	0.64	0.0
Throughput with memory destination operand: or [m16],r16	Throughput	1.92	0.0
cdq	Latency	0.5	0.0
xor r8,r8	Throughput	0.54	0.0
Latency with memory operand: not [m32]	Latency	4.9	0.0
adc r32, i	Throughput	0.98	0.0
or r8,r8	Throughput	0.5	0.0
Latency with memory destination operand: and [m64],r64	Latency	4.9	0.0
neg r8high	Throughput	0.99	0.0
mov r8,r8	Throughput	0.5	0.0
Latency with memory destination operand: and [m8],r8	Latency	5.31	0.0
Latency with memory destination operand: add [m16],r16	Latency	4.9	0.0
pause	Latency	5.88	0.0
xor eax,eax / cdqe	Throughput	0.5	0.0
Throughput with memory operand: cmp [m32], i	Throughput	0.99	0.0
cld	Latency	3.18	0.0
adc r32,r32	Throughput	1.06	0.0
Latency with memory operand: cmp [m32], i	Latency	1.15	0.17
Throughput with RIP address mode: mov r32, [m32]	Throughput	1.41	0.0
Throughput with memory source operand: sub r64,[m64]	Throughput	1.07	0.0
cmp r8high, i	Throughput	0.5	0.0
clc	Latency	3.03	0.0
or r8, i	Throughput	0.64	0.0
popcnt r32,r32	Throughput	0.98	0.0
dec r8high	Throughput	0.64	0.0
Throughput with memory source operand: xchg r16,[m16]	Throughput	16.77	0.15
inc r8high	Throughput	0.59	0.0
Throughput with memory destination operand: sub [m32],r32	Throughput	1.77	0.0
Latency with memory destination operand: add [m8],r8	Latency	5.31	0.0
Throughput with memory destination operand: and [m64],r64	Throughput	1.77	0.0
Throughput with memory source operand: sub r32,[m32]	Throughput	1.24	0.17
xor eax,eax / cwd	Throughput	0.5	0.0
dec r8	Throughput	0.59	0.0
mov r16,r16	Throughput	0.5	0.0
add r8,r8	Throughput	0.5	0.0
Throughput with memory source operand: add r16,[m16]	Throughput	1.07	0.0
not r16	Throughput	0.64	0.0
sub r8high, i	Throughput	0.64	0.0
Throughput with memory source operand: or r64,[m64]	Throughput	0.98	0.0
add r16, i	Throughput	0.59	0.0
Latency with memory destination operand: xchg [m8],r8	Latency	18.14	0.11
Throughput with memory source operand: imul	Throughput	1.22	0.0
sfence	Latency	15.86	0.0
Throughput with memory destination operand: test [m32],r32	Throughput	0.98	0.0
neg r32	Throughput	0.64	0.0
Throughput with memory source operand: adc r16,[m16]	Throughput	0.98	0.0
xor eax,eax / cdq	Throughput	0.54	0.0
adc r8high, i	Throughput	1.06	0.0
nop	Latency	0.64	0.0
Latency with memory destination operand: add [m32],r32	Latency	4.9	0.0
xor r8high, i	Throughput	0.59	0.0
Latency with memory destination operand: adc [m8],r8	Latency	5.44	1.06
Latency with memory destination operand: sbb [m16],r16	Latency	5.62	0.89
Throughput with memory source operand: sbb r64,[m64]	Throughput	1.07	0.0
Latency with memory operand: adc [m32], i	Latency	5.31	0.0
Throughput with memory source operand: add r8,[m8]	Throughput	1.09	0.0
add r16,r16	Throughput	0.5	0.0
adc r8,r8	Throughput	1.06	0.0
adc r16,r16	Throughput	1.06	0.0
cmp r32,r32	Throughput	0.54	0.0
cmc	Latency	3.03	0.0
Throughput with memory source operand: adc r32,[m32]	Throughput	0.98	0.0
Throughput with memory operand: mov [m32], i	Throughput	1.98	0.15
Throughput with ABS64 address mode: mov r32, [m32]	Throughput	1.32	0.0
Throughput with memory operand: test [m32], i	Throughput	1.07	0.0
Latency with memory destination operand: adc [m16],r16	Latency	4.9	0.0
adc r16, i	Throughput	1.06	0.0
Latency with memory operand: add [m32], i	Latency	4.9	0.0
Throughput with memory source operand: or r8,[m8]	Throughput	1.07	0.0
Throughput with memory destination operand: or [m32],r32	Throughput	1.92	0.0
imul r16,r16	Throughput	1.12	0.0
xor eax,eax / cwde	Throughput	0.5	0.0
adc r8, i	Throughput	1.07	0.0
not r8high	Throughput	0.64	0.0
Throughput with memory destination operand: xor [m32],r32	Throughput	1.77	0.0
neg r8	Throughput	1.07	0.0
Throughput with memory source operand: xchg r64,[m64]	Throughput	16.65	0.0
Throughput with memory source operand: add r32,[m32]	Throughput	1.09	0.0
bswap r32	Throughput	1.07	0.0
and r16,r16	Throughput	0.54	0.0
Latency with memory destination operand: xchg [m32],r32	Latency	18.03	0.0
sbb r32,r32	Throughput	1.06	0.0
Throughput with memory source operand: xchg r32,[m32]	Throughput	18.68	3.77
Latency with memory destination operand: or [m8],r8	Latency	5.31	0.0
add r32,r32	Throughput	0.5	0.0
Throughput with memory destination operand: xchg [m16],r16	Throughput	18.03	0.0
Throughput with memory operand: add [m32], i	Throughput	1.96	0.0
Throughput with memory operand: neg [m32]	Throughput	2.13	0.0
cmp r64, i	Throughput	0.51	0.0
dec r16	Throughput	0.64	0.0
Latency with memory operand: test [m32], i	Latency	1.07	0.0
Latency with memory destination operand: test [m32],r32	Latency	0.98	0.0
popcnt r64,r64	Throughput	0.98	0.0
Latency with memory destination operand: sbb [m32],r32	Latency	4.9	0.0
Throughput with memory source operand: test r8,[m8]	Throughput	1.07	0.0
test r8,r8	Throughput	0.52	0.0
Throughput with memory source operand: adc r8,[m8]	Throughput	1.0	0.0
Latency with memory destination operand: xchg [m64],r64	Latency	17.62	2.59
mov r64,r64	Throughput	0.5	0.0
cmp r8, i	Throughput	0.5	0.0
or r8high, i	Throughput	0.64	0.0
Latency with memory destination operand: or [m32],r32	Latency	5.31	0.0
Throughput with memory source operand: sbb r8,[m8]	Throughput	0.98	0.0
Latency with memory operand: mov [m32], i	Latency	1.84	0.0
Throughput with memory destination operand: cmp [m16],r16	Throughput	0.98	0.0
and r64, i	Throughput	0.59	0.0
Throughput with memory source operand: cmp r16,[m16]	Throughput	0.98	0.0
xor r16,r16	Throughput	0.54	0.0
xor r8, i	Throughput	0.59	0.0
Latency with memory destination operand: xor [m16],r16	Latency	5.43	0.15
cwd	Latency	0.5	0.0
Throughput with memory source operand: bsf	Throughput	2.13	0.23
test r32,r32	Throughput	0.5	0.0
and r32, i	Throughput	0.59	0.0
Latency with memory operand: sbb [m32], i	Latency	5.31	0.0
Throughput with memory operand: or [m32], i	Throughput	2.13	0.0
xor eax,eax / cqo	Throughput	0.54	0.0
Throughput with memory source operand: xor r8,[m8]	Throughput	0.98	0.0
popcnt r16,r16	Throughput	1.07	0.0
Throughput with memory source operand: popcnt	Throughput	0.99	0.0
add r64,r64	Throughput	0.54	0.0
xchg r64,r64	Throughput	1.48	0.0
Throughput with memory source operand: sub r16,[m16]	Throughput	0.98	0.0
cmp r64,r64	Throughput	0.5	0.0
bsr r32,r32	Throughput	1.96	0.0
prefetcht2 [m]	Throughput	1.3	0.0
and r16, i	Throughput	0.59	0.0
or r64, i	Throughput	0.59	0.0
Latency with memory destination operand: xchg [m16],r16	Latency	18.03	0.0
Latency with memory destination operand: test [m8],r8	Latency	0.98	0.0
Throughput with memory operand: xor [m32], i	Throughput	1.97	0.0
Latency with memory destination operand: cmp [m32],r32	Latency	0.98	0.0
lfence	Latency	15.85	0.0
Throughput with INDIR address mode: mov [m32], r32	Throughput	1.65	0.0
Throughput with memory source operand: add r64,[m64]	Throughput	0.99	0.0
Latency with memory destination operand: cmp [m16],r16	Latency	0.98	0.0
cmove r16,r16	Throughput	0.51	0.0
Throughput with memory source operand: xor r64,[m64]	Throughput	0.99	0.0
test r8, i	Throughput	0.5	0.0
Throughput with memory destination operand: mov [m64],r64	Throughput	1.79	0.0
dec r64	Throughput	0.64	0.0
Latency with memory destination operand: sbb [m64],r64	Latency	4.9	0.0
Latency with memory destination operand: mov [m8],r8	Latency	1.65	0.0
Throughput with memory source operand: and r8,[m8]	Throughput	1.07	0.0
sub r8, i	Throughput	0.59	0.0
sub r64, i	Throughput	0.59	0.0
xor r16, i	Throughput	0.59	0.0
bsr r16,r16	Throughput	1.96	0.0
Throughput with RIP address mode: mov [m32], r32	Throughput	1.79	0.0
sete r8 / neg r8	Latency	1.62	0.0
imul r64,r64	Throughput	2.12	0.0
sbb r8, i	Throughput	1.06	0.0
Throughput with memory destination operand: cmp [m32],r32	Throughput	0.98	0.0
mov r32,r32	Throughput	0.5	0.0
xor r64, i	Throughput	0.64	0.0
Throughput with memory source operand: and r16,[m16]	Throughput	0.98	0.0
Throughput with memory destination operand: adc [m64],r64	Throughput	1.76	0.0
xor r64,r64	Throughput	0.54	0.0
test r64,r64	Throughput	0.5	0.0
sub r32, i	Throughput	0.59	0.0
not r64	Throughput	0.64	0.0
Throughput with memory source operand: test r64,[m64]	Throughput	1.06	0.0
prefetchnta [m]	Throughput	1.3	0.0
Throughput with memory source operand: xor r16,[m16]	Throughput	0.98	0.0
add r64, i	Throughput	0.64	0.0
Latency with memory destination operand: or [m16],r16	Latency	5.31	0.0
Throughput with memory operand: sbb [m32], i	Throughput	1.96	0.0
Latency with memory destination operand: cmp [m8],r8	Latency	0.98	0.0
Throughput with memory destination operand: mov [m16],r16	Throughput	1.79	0.0
neg r64	Throughput	0.64	0.0
Throughput with memory destination operand: and [m8],r8	Throughput	1.96	0.0
Throughput with memory operand: sub [m32], i	Throughput	1.96	0.0
Latency with memory operand: neg [m32]	Latency	5.3	0.0
cmp r8,r8	Throughput	0.54	0.0
Throughput with memory destination operand: adc [m32],r32	Throughput	1.92	0.0
cqo	Latency	0.54	0.0
Throughput with memory source operand: mov r32,[m32]	Throughput	1.41	0.0
sbb r16, i	Throughput	0.98	0.0
and r8high, i	Throughput	0.59	0.0
and r8,r8	Throughput	0.5	0.0
Throughput with memory source operand: and r32,[m32]	Throughput	0.98	0.0
Throughput with memory destination operand: test [m64],r64	Throughput	0.99	0.0
test r64, i	Throughput	0.55	0.0
Latency with memory destination operand: sub [m16],r16	Latency	4.9	0.0
Throughput with memory source operand: test r16,[m16]	Throughput	1.07	0.0
xchg r16,r16	Throughput	1.9	0.0
Throughput with memory source operand: or r32,[m32]	Throughput	0.98	0.0
Throughput with memory operand: inc [m32]	Throughput	1.97	0.0
Throughput with memory destination operand: xor [m64],r64	Throughput	1.64	0.0
test r16,r16	Throughput	0.5	0.0
Throughput with memory source operand: sub r8,[m8]	Throughput	0.98	0.0
cmp r32, i	Throughput	0.5	0.0
Throughput with memory destination operand: sbb [m32],r32	Throughput	1.92	0.0
Latency with memory operand: or [m32], i	Latency	5.31	0.0
add r8, i	Throughput	0.64	0.0
add r32, i	Throughput	0.64	0.0
Latency with memory destination operand: xor [m64],r64	Latency	5.31	0.0
Throughput with memory destination operand: sbb [m16],r16	Throughput	1.91	0.0
Throughput with memory destination operand: or [m64],r64	Throughput	1.77	0.0
sub r64,r64	Throughput	0.5	0.0
Throughput with memory operand: adc [m32], i	Throughput	2.13	0.0
Throughput with memory destination operand: sub [m64],r64	Throughput	1.63	0.0
Throughput with memory source operand: and r64,[m64]	Throughput	0.98	0.0
sete r8	Throughput	0.98	0.0
or r32, i	Throughput	0.59	0.0
Latency with memory destination operand: mov [m16],r16	Latency	2.12	0.99
Throughput with memory operand: not [m32]	Throughput	1.96	0.0
sbb r32, i	Throughput	0.98	0.0
Throughput with memory source operand: or r16,[m16]	Throughput	0.98	0.0
Throughput with memory destination operand: xchg [m8],r8	Throughput	18.04	0.0
Throughput with memory destination operand: add [m64],r64	Throughput	1.77	0.0
sub r16,r16	Throughput	0.54	0.0
Latency with memory destination operand: xor [m32],r32	Latency	5.3	0.0
Throughput with memory destination operand: sbb [m64],r64	Throughput	1.77	0.0
not r8	Throughput	0.64	0.0
inc r32	Throughput	0.59	0.0
std	Latency	3.18	0.0
Latency with memory destination operand: adc [m64],r64	Latency	4.9	0.0
bsr r64,r64	Throughput	2.13	0.0
test r16, i	Throughput	1.29	0.0
sub r16, i	Throughput	0.59	0.0
mfence	Latency	15.85	0.0
stc	Latency	3.03	0.0
or r16, i	Throughput	0.64	0.0
sbb r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: test r32,[m32]	Throughput	1.09	0.01
cmove r32,r32	Throughput	0.5	0.0
test r8high, i	Throughput	0.5	0.0
Throughput with memory source operand: xchg r8,[m8]	Throughput	16.64	0.0
adc r64,r64	Throughput	0.98	0.0
Latency with memory operand: xor [m32], i	Latency	5.31	0.0
Throughput with memory destination operand: and [m32],r32	Throughput	1.92	0.0
Throughput with memory source operand: mov r16,[m16]	Throughput	1.07	0.0
Throughput with memory destination operand: mov [m8],r8	Throughput	1.66	0.0
Throughput with memory destination operand: add [m16],r16	Throughput	1.91	0.0
Throughput with memory destination operand: sub [m16],r16	Throughput	1.77	0.0
Throughput with memory source operand: sbb r32,[m32]	Throughput	0.98	0.0
Throughput with memory destination operand: xchg [m64],r64	Throughput	16.65	0.0
Throughput with memory destination operand: adc [m8],r8	Throughput	2.12	0.0
xor r32,r32	Throughput	0.54	0.0
mov r8high, i	Throughput	0.64	0.0
Throughput with memory source operand: sbb r16,[m16]	Throughput	0.98	0.0
sbb r8,r8	Throughput	1.06	0.0
Throughput with memory operand: and [m32], i	Throughput	1.97	0.0
Throughput with memory destination operand: add [m8],r8	Throughput	1.96	0.0
imul r32,r32	Throughput	1.12	0.0
sub r8,r8	Throughput	0.55	0.0
mov r16, i	Throughput	1.34	0.0
Throughput with ABS32 address mode: mov r32, [m32]	Throughput	1.3	0.0
bsf r16,r16	Throughput	2.36	0.49
sete r8h	Throughput	1.06	0.0
Latency with memory destination operand: test [m16],r16	Latency	0.98	0.0
Throughput with memory destination operand: xor [m8],r8	Throughput	1.96	0.0
Latency with memory destination operand: mov [m32],r32	Latency	1.74	0.01
cbw	Latency	1.06	0.0
Throughput with memory source operand: cmp r32,[m32]	Throughput	1.09	0.0
Throughput with ABS32 address mode: mov [m32], r32	Throughput	1.72	0.04
mov r64, i	Throughput	0.59	0.0
prefetcht0 [m]	Throughput	1.3	0.0
Throughput with memory destination operand: test [m16],r16	Throughput	1.07	0.0
Throughput with memory source operand: mov r8,[m8]	Throughput	1.07	0.0
Throughput with memory destination operand: test [m8],r8	Throughput	1.06	0.0
or r64,r64	Throughput	0.54	0.0
cmp r16, i	Throughput	0.5	0.0
cdqe	Latency	0.98	0.0
and r32,r32	Throughput	0.5	0.0
Throughput with memory destination operand: and [m16],r16	Throughput	1.77	0.0
or r16,r16	Throughput	0.54	0.0
Latency with memory destination operand: adc [m32],r32	Latency	5.46	1.64
Latency with memory operand: and [m32], i	Latency	4.9	0.0
Throughput with memory destination operand: cmp [m8],r8	Throughput	1.07	0.0
and r8, i	Throughput	0.59	0.0
Latency with memory destination operand: mov [m64],r64	Latency	1.65	0.0
Throughput with INDIR address mode: mov r32, [m32]	Throughput	1.41	0.0
mov r32, i	Throughput	0.59	0.0
cmp r16,r16	Throughput	0.54	0.0
inc r8	Throughput	0.59	0.0
xor r32, i	Throughput	0.59	0.0
Throughput with memory source operand: cmove	Throughput	0.98	0.0
sbb r8high, i	Throughput	0.98	0.0
Throughput with memory destination operand: sbb [m8],r8	Throughput	2.12	0.0
bsf r32,r32	Throughput	1.96	0.0
inc r16	Throughput	0.59	0.0
adc r64, i	Throughput	0.98	0.0
bswap r64	Throughput	1.07	0.0
Latency with memory destination operand: sub [m64],r64	Latency	4.9	0.0
not r32	Throughput	0.59	0.0
xchg r8,r8	Throughput	2.6	0.0
sete, [m8]	Throughput	1.69	0.0
Throughput with memory operand: dec [m32]	Throughput	1.96	0.0
cmove r64,r64	Throughput	0.51	0.0
Throughput with ABS64 address mode: mov [m32], r32	Throughput	1.65	0.0
Latency with memory destination operand: sub [m8],r8	Latency	4.9	0.0
Latency with memory operand: inc [m32]	Latency	4.9	0.0
Throughput with memory destination operand: sub [m8],r8	Throughput	2.13	0.0
xor eax,eax / cbw	Throughput	0.5	0.0
Throughput with memory source operand: mov r64,[m64]	Throughput	1.3	0.0
or r32,r32	Throughput	0.54	0.0
Latency with memory destination operand: and [m32],r32	Latency	5.3	0.0
cwde	Latency	0.98	0.0
sbb r16,r16	Throughput	1.07	0.0
Throughput with memory source operand: adc r64,[m64]	Throughput	1.07	0.0
Latency with memory destination operand: sbb [m8],r8	Latency	5.61	0.82
bsf r64,r64	Throughput	1.96	0.0
Latency with memory destination operand: xor [m8],r8	Latency	5.01	0.11
Throughput with memory source operand: cmp r8,[m8]	Throughput	0.98	0.0
neg r16	Throughput	0.99	0.0
Latency with memory destination operand: or [m64],r64	Latency	5.31	0.0
sbb r64, i	Throughput	0.98	0.0
test r32, i	Throughput	0.5	0.0
Latency with memory operand: dec [m32]	Latency	4.9	0.0
Throughput with memory destination operand: cmp [m64],r64	Throughput	0.98	0.0
Latency with memory destination operand: and [m16],r16	Latency	5.31	0.0
Latency with memory destination operand: sub [m32],r32	Latency	4.9	0.0
Throughput with memory destination operand: or [m8],r8	Throughput	1.96	0.0
and r64,r64	Throughput	0.54	0.0
add r8high, i	Throughput	0.64	0.0
Throughput with memory destination operand: adc [m16],r16	Throughput	1.91	0.0
Throughput with memory destination operand: mov [m32],r32	Throughput	1.79	0.0
prefetcht1 [m]	Throughput	1.3	0.0
sub r32,r32	Throughput	0.5	0.0
Throughput with memory source operand: bsr	Throughput	1.96	0.0
Throughput with memory source operand: xor r32,[m32]	Throughput	0.98	0.0
Throughput with memory source operand: pmovzxwd r128,[m128]	Throughput	0.99	0.0
punpcklqdq r128,r128	Throughput	0.98	0.0
pshufw r64,r64,i	Throughput	0.98	0.0
Throughput with memory source operand: palignr r64,[m64],i	Throughput	1.07	0.0
psrad r128,i	Throughput	1.07	0.0
Throughput with memory source operand: punpckldq r64,[m64]	Throughput	0.99	0.0
punpckldq r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: packuswb r64,[m64]	Throughput	0.98	0.0
paddd r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pmovsxbw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pavgb r64,[m64]	Throughput	1.2	0.1
Throughput with memory source operand: pmaddwd r128,[m128]	Throughput	1.96	0.0
Throughput with memory source operand: packssdw r128,[m128]	Throughput	0.99	0.0
pcmpgtd r64,r64	Throughput	0.98	0.0
paddusb r128,r128	Throughput	0.98	0.0
packssdw r64,r64	Throughput	1.16	0.0
psllq r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pmullw r128,[m128]	Throughput	1.23	0.0
Throughput with memory source operand: pand r64,[m64]	Throughput	0.98	0.0
pcmpgtw r64,r64	Throughput	1.06	0.0
psllw r64,i	Throughput	1.06	0.0
Throughput with memory source operand: psllw r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pmulhuw r128,[m128]	Throughput	1.23	0.0
Throughput with memory source operand: pcmpgtd r64,[m64]	Throughput	0.98	0.0
pminub r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pmovsxdq r128,[m128]	Throughput	1.07	0.0
pmaxsw r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pshuflw  r128,[m128]	Throughput	1.07	0.0
pandn r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: phsubd r128,[m128]	Throughput	4.9	0.0
pmaddwd r64,r64	Throughput	1.96	0.0
pmaddubsw r64,r64	Throughput	7.83	0.0
mpsadbw r128,r128	Throughput	0.99	0.0
Throughput with memory source operand: punpckhwd r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: psraw r128,[m128]	Throughput	1.07	0.0
pavgw r128,r128	Throughput	1.06	0.0
pblendw r128,r128	Throughput	0.98	0.0
pshufb r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: mpsadbw  r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: psllq r64,[m64]	Throughput	0.99	0.0
Throughput with memory source operand: pshufhw  r128,[m128]	Throughput	1.21	0.1
Throughput with memory source operand: pmuldq r128,[m128]	Throughput	1.23	0.0
pcmpeqw r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pandn r128,[m128]	Throughput	1.07	0.0
pminub r128,r128	Throughput	1.41	1.06
Throughput with memory source operand: pmaxuw r128,[m128]	Throughput	1.07	0.0
Throughput with memory source operand: pmuludq r128,[m128]	Throughput	1.23	0.0
Throughput with memory source operand: movdqa r128,[m128]	Throughput	1.41	0.0
pabsb r64,r64	Throughput	0.98	0.0
psignw r64,r64	Throughput	0.98	0.0
movdqa r128,r128	Throughput	1.07	0.0
phaddsw r128,r128	Throughput	3.18	0.0
pmullw r128,r128	Throughput	0.98	0.0
psadbw r64,r64	Throughput	1.07	0.0
Throughput with memory source operand: psignw r64,[m64]	Throughput	0.99	0.0
Throughput with memory source operand: paddw r128,[m128]	Throughput	1.07	0.0
punpckhdq r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: pminsb r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pminub r64,[m64]	Throughput	0.98	0.0
pmuludq r128,r128	Throughput	1.06	0.0
psllq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: palignr  r128,[m128]	Throughput	0.99	0.0
pmaxud r128,r128	Throughput	1.07	0.0
pmuldq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: paddusb r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: punpcklqdq r128,[m128]	Throughput	1.55	1.15
psrad r64,i	Throughput	1.06	0.0
pavgw r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: paddd r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pcmpeqb r128,[m128]	Throughput	1.07	0.0
Throughput with memory source operand: pmaddubsw r64,[m64]	Throughput	8.81	0.0
pmuludq r64,r64	Throughput	0.99	0.0
punpckhwd r64,r64	Throughput	0.98	0.0
pcmpeqd r128,r128	Throughput	1.06	0.0
Throughput with memory source operand: pshufb r128,[m128]	Throughput	1.07	0.0
pmovzxwd r128,r128	Throughput	0.98	0.0
pmaxsw r64,r64	Throughput	0.98	0.0
psrlq r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: psllq r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: punpckhdq r64,[m64]	Throughput	0.98	0.0
pabsb r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: psllw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: paddq r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pblendw  r128,[m128]	Throughput	0.99	0.0
pmaddubsw r128,r128	Throughput	8.62	0.15
Throughput with memory source operand: pcmpeqw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pmaddubsw r128,[m128]	Throughput	9.54	0.0
Throughput with memory source operand: punpckhdq r128,[m128]	Throughput	0.99	0.0
paddw r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pcmpgtd r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pabsb r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: psignw r128,[m128]	Throughput	0.99	0.0
psrlq r128,i	Throughput	1.07	0.0
psadbw r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: paddq r128,[m128]	Throughput	0.99	0.0
packssdw r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: pcmpeqq r128,[m128]	Throughput	1.07	0.0
punpckhwd r128,r128	Throughput	0.98	0.0
psraw r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: pcmpeqb r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pmaxsw r128,[m128]	Throughput	0.99	0.0
pmullw r64,r64	Throughput	1.06	0.0
paddw r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pandn r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: punpckhqdq r128,[m128]	Throughput	0.99	0.0
pand r64,r64	Throughput	0.98	0.0
pshufb r128,r128	Throughput	0.99	0.0
Throughput with memory source operand: paddd r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pcmpgtw r64,[m64]	Throughput	0.99	0.0
Throughput with memory source operand: pabsd r64,[m64]	Throughput	0.99	0.0
paddq r64,r64	Throughput	0.98	0.0
pmaxuw r128,r128	Throughput	0.98	0.0
palignr r64,r64,i	Throughput	1.07	0.0
punpckhdq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pmaddwd r64,[m64]	Throughput	1.97	0.0
Throughput with memory source operand: movq r64,[m64]	Throughput	1.3	0.0
Throughput with memory source operand: pavgw r64,[m64]	Throughput	1.07	0.0
packuswb r128,r128	Throughput	0.98	0.0
pavgb r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pmullw r64,[m64]	Throughput	1.23	0.0
psraw r64,i	Throughput	0.98	0.0
Throughput with memory source operand: phaddw r64,[m64]	Throughput	4.9	0.0
pshufhw r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: pmovzxbd r128,[m128]	Throughput	0.99	0.0
pslldq r128,i	Throughput	1.07	0.0
Throughput with memory source operand: movq r128,[m128]	Throughput	1.3	0.0
movdqu r128,r128	Throughput	1.06	0.0
pslld r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: psrlq r128,[m128]	Throughput	1.07	0.0
Throughput with memory source operand: pmulhrsw r128,[m128]	Throughput	1.23	0.0
Throughput with memory source operand: phminposuw r128,[m128]	Throughput	1.18	0.16
pmovzxbd r128,r128	Throughput	0.98	0.0
pmulld r128,r128	Throughput	0.98	0.0
pcmpeqq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pcmpeqd r64,[m64]	Throughput	1.07	0.0
Throughput with memory source operand: pslld r64,[m64]	Throughput	0.98	0.0
psllw r128,r128	Throughput	0.98	0.0
phsubd r64,r64	Throughput	3.18	0.0
Throughput with memory source operand: paddusb r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: packssdw r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: packusdw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: punpckhbw r128,[m128]	Throughput	0.98	0.0
packuswb r64,r64	Throughput	1.02	0.0
phaddw r128,r128	Throughput	3.18	0.0
psllw r64,r64	Throughput	0.98	0.0
punpckhbw r128,r128	Throughput	0.98	0.0
phsubd r128,r128	Throughput	3.18	0.0
psllw r128,i	Throughput	1.07	0.0
punpckhbw r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: pshufb r64,[m64]	Throughput	1.07	0.0
Throughput with memory source operand: pcmpeqw r64,[m64]	Throughput	0.98	0.0
pshufd r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pmulhrsw r64,[m64]	Throughput	1.23	0.0
psraw r128,i	Throughput	0.98	0.0
Throughput with memory source operand: punpckhbw r64,[m64]	Throughput	0.99	0.0
psraw r128,r128	Throughput	1.06	0.0
paddq r128,r128	Throughput	0.99	0.0
Throughput with memory source operand: paddw r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: ptest r128,[m128]	Throughput	1.07	0.0
phaddw r64,r64	Throughput	2.94	0.0
Throughput with memory source operand: pcmpgtw r128,[m128]	Throughput	0.98	0.0
Throughput with memory source operand: pabsd r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pmovsxbq r128,[m128]	Throughput	0.98	0.0
psignw r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: phaddsw r128,[m128]	Throughput	4.9	0.0
Throughput with memory source operand: psraw r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pmuludq r64,[m64]	Throughput	1.33	0.0
Throughput with memory source operand: pabsb r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: pshufw r64,[m64],i	Throughput	1.07	0.0
paddusb r64,r64	Throughput	0.98	0.0
pshuflw r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pand r128,[m128]	Throughput	1.06	0.0
Throughput with memory source operand: psrlq r64,[m64]	Throughput	1.07	0.0
phaddsw r64,r64	Throughput	2.94	0.0
pabsd r64,r64	Throughput	0.98	0.0
ptest r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: phaddw r128,[m128]	Throughput	4.9	0.0
Throughput with memory source operand: pmaxsw r64,[m64]	Throughput	0.98	0.0
pcmpgtd r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: packsswb r128,[m128]	Throughput	0.99	0.0
pminsb r128,r128	Throughput	0.98	0.0
pmovsxbq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: packuswb r128,[m128]	Throughput	0.98	0.0
Throughput with memory source operand: pshufd  r128,[m128]	Throughput	0.99	0.0
paddd r128,r128	Throughput	0.98	0.0
movq r64,r64	Throughput	1.06	0.0
psrlq r64,i	Throughput	1.07	0.0
punpckhqdq r128,r128	Throughput	0.98	0.0
Throughput with memory source operand: pavgb r128,[m128]	Throughput	1.07	0.0
Throughput with memory source operand: pmulhuw r64,[m64]	Throughput	1.23	0.0
pcmpeqd r64,r64	Throughput	1.06	0.0
Throughput with memory source operand: pcmpeqd r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pmulld r128,[m128]	Throughput	1.23	0.0
Throughput with memory source operand: phsubd r64,[m64]	Throughput	4.9	0.0
pcmpgtw r128,r128	Throughput	1.06	0.0
palignr r128,r128	Throughput	1.07	0.0
packsswb r128,r128	Throughput	0.98	0.0
pcmpeqb r64,r64	Throughput	1.06	0.0
punpckldq r128,r128	Throughput	0.98	0.0
phminposuw r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: psadbw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: punpckhwd r64,[m64]	Throughput	0.98	0.0
packsswb r64,r64	Throughput	0.98	0.0
pavgb r128,r128	Throughput	1.06	0.0
psrlq r128,r128	Throughput	1.06	0.0
pmovsxdq r128,r128	Throughput	0.98	0.0
pandn r128,r128	Throughput	0.98	0.0
pslld r128,r128	Throughput	0.98	0.0
packusdw r128,r128	Throughput	0.99	0.0
pcmpeqb r128,r128	Throughput	1.06	0.0
Throughput with memory source operand: phaddsw r64,[m64]	Throughput	4.9	0.0
Throughput with memory source operand: pavgw r128,[m128]	Throughput	0.99	0.0
Throughput with memory source operand: pslld r128,[m128]	Throughput	1.41	0.95
Throughput with memory source operand: movdqu r128,[m128]	Throughput	1.31	0.0
psrldq r128,i	Throughput	1.07	0.0
Throughput with memory source operand: punpckldq r128,[m128]	Throughput	0.98	0.0
pmulhuw r128,r128	Throughput	0.98	0.0
pmulhrsw r64,r64	Throughput	0.99	0.0
movq r128,r128	Throughput	0.98	0.0
pcmpeqw r128,r128	Throughput	0.98	0.0
pand r128,r128	Throughput	0.98	0.0
pmaddwd r128,r128	Throughput	2.32	0.0
pabsd r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: pmaxud r128,[m128]	Throughput	1.07	0.0
pmulhuw r64,r64	Throughput	0.98	0.0
Throughput with memory source operand: psadbw r64,[m64]	Throughput	0.98	0.0
Throughput with memory source operand: packsswb r64,[m64]	Throughput	0.99	0.0
pmulhrsw r128,r128	Throughput	1.07	0.0
Throughput with memory source operand: pminub r128,[m128]	Throughput	0.98	0.0
pmovsxbw r128,r128	Throughput	1.07	0.0
jmp (5 per 16 bytes), 64 bit	Latency	7.91	0.01
jmp (2 per 16 bytes), 64 bit	Latency	3.13	0.05
jmp (3 per 16 bytes), 64 bit	Latency	4.89	0.0
jmp (8 per 16 bytes), 64 bit	Latency	2.44	8.13
jmp (6 per 16 bytes), 64 bit	Latency	7.91	0.0
jmp (4 per 16 bytes), 64 bit	Latency	6.12	0.0
jmp (1 per 16 bytes), 64 bit	Latency	2.97	0.0
Case 5: lea with address size prefix	Latency	1.03	0.0
Case 2: add register,constant	Latency	0.87	0.06
Case 3: test register,constant	Latency	0.86	0.06
Case 4: neg or not register (bogus length-changing prefix)	Latency	0.76	0.03
Case 1: mov register,constant	Latency	1.05	0.08
Number of NOPs = 25, noptype = 2, nopsize = 12, total size = 305	Latency	1.69	0.0
Number of NOPs = 1500, noptype = 2, nopsize = 12, total size = 18005	Latency	0.76	0.0
Number of NOPs = 31, noptype = 2, nopsize = 12, total size = 377	Latency	0.85	0.0
Number of NOPs = 4000, noptype = 2, nopsize = 12, total size = 48005	Latency	0.76	0.0
Number of NOPs = 33, noptype = 3, nopsize = 12, total size = 401	Latency	0.8	0.0
Number of NOPs = 2, noptype = 2, nopsize = 12, total size = 29	Latency	5.74	0.0
Number of NOPs = 40, noptype = 3, nopsize = 12, total size = 485	Latency	0.79	0.0
Number of NOPs = 30, noptype = 3, nopsize = 12, total size = 365	Latency	0.81	0.0
Number of NOPs = 100, noptype = 2, nopsize = 12, total size = 1205	Latency	0.0	0.0
Number of NOPs = 30, noptype = 2, nopsize = 12, total size = 365	Latency	1.44	0.0
Number of NOPs = 4000, noptype = 3, nopsize = 12, total size = 48005	Latency	0.76	0.0
Number of NOPs = 1500, noptype = 3, nopsize = 12, total size = 18005	Latency	0.76	0.0
Number of NOPs = 1000, noptype = 2, nopsize = 12, total size = 12005	Latency	0.0	0.0
Number of NOPs = 100, noptype = 3, nopsize = 12, total size = 1205	Latency	0.9	0.0
Number of NOPs = 32, noptype = 3, nopsize = 12, total size = 389	Latency	0.8	0.0
Number of NOPs = 50, noptype = 3, nopsize = 12, total size = 605	Latency	0.86	0.0
Number of NOPs = 10, noptype = 2, nopsize = 12, total size = 125	Latency	2.5	0.0
Number of NOPs = 5, noptype = 3, nopsize = 12, total size = 65	Latency	1.0	0.0
Number of NOPs = 5, noptype = 2, nopsize = 12, total size = 65	Latency	3.86	0.0
Number of NOPs = 100000, noptype = 2, nopsize = 12, total size = 1200005	Latency	0.0	0.0
Number of NOPs = 31, noptype = 3, nopsize = 12, total size = 377	Latency	1.48	0.0
Number of NOPs = 20000, noptype = 2, nopsize = 12, total size = 240005	Latency	6.84	0.0
Number of NOPs = 50, noptype = 2, nopsize = 12, total size = 605	Latency	1.17	0.0
Number of NOPs = 40, noptype = 2, nopsize = 12, total size = 485	Latency	0.79	0.0
Number of NOPs = 10000, noptype = 3, nopsize = 12, total size = 120005	Latency	6.84	0.0
Number of NOPs = 2, noptype = 3, nopsize = 12, total size = 29	Latency	5.74	0.0
Number of NOPs = 25, noptype = 3, nopsize = 12, total size = 305	Latency	0.82	0.0
Number of NOPs = 32, noptype = 2, nopsize = 12, total size = 389	Latency	0.8	0.0
Number of NOPs = 20, noptype = 3, nopsize = 12, total size = 245	Latency	0.82	0.0
Number of NOPs = 10, noptype = 3, nopsize = 12, total size = 125	Latency	2.42	0.0
Number of NOPs = 20, noptype = 2, nopsize = 12, total size = 245	Latency	0.82	0.0
Number of NOPs = 10000, noptype = 2, nopsize = 12, total size = 120005	Latency	0.0	0.0
Number of NOPs = 1000, noptype = 3, nopsize = 12, total size = 12005	Latency	0.8	0.0
Number of NOPs = 20000, noptype = 3, nopsize = 12, total size = 240005	Latency	6.84	0.0
Number of NOPs = 33, noptype = 2, nopsize = 12, total size = 401	Latency	1.49	0.0
Number of instructions = 32, total size = 296	Latency	0.71	0.0
Number of instructions = 1000, nopsize = 8, total size = 8008	Latency	0.0	0.0
Number of instructions = 1000, total size = 9988	Latency	1.43	0.0
Number of instructions = 32, nopsize = 4, total size = 136	Latency	0.54	0.0
Number of instructions = 50, nopsize = 1, total size = 54	Latency	0.41	0.0
Number of instructions = 10, total size = 72	Latency	0.93	0.0
Number of instructions = 20, nopsize = 1, total size = 24	Latency	0.4	0.0
Number of instructions = 1000, total size = 9976	Latency	0.63	0.0
Number of instructions = 32, nopsize = 8, total size = 264	Latency	0.0	0.0
Number of instructions = 1000, total size = 2004	Latency	0.38	0.0
Number of instructions = 40, nopsize = 8, total size = 328	Latency	0.0	0.0
Number of instructions = 56, nopsize = 8, total size = 456	Latency	0.0	0.0
Number of instructions = 10000, total size = 99988	Latency	5.7	0.0
Number of instructions = 6, total size = 44	Latency	4.65	0.0
Number of instructions = 4, nopsize = 1, total size = 8	Latency	0.75	0.0
Number of instructions = 40, nopsize = 1, total size = 44	Latency	0.38	0.0
Number of instructions = 100, total size = 976	Latency	0.72	0.0
Number of instructions = 16, nopsize = 8, total size = 136	Latency	0.0	0.0
Number of instructions = 33, nopsize = 1, total size = 37	Latency	0.39	0.0
Number of instructions = 6, nopsize = 1, total size = 10	Latency	4.15	0.0
Number of instructions = 100, nopsize = 1, total size = 104	Latency	0.38	0.0
Number of instructions = 12, nopsize = 8, total size = 100	Latency	0.67	0.0
Number of instructions = 32, total size = 64	Latency	0.42	0.01
Number of instructions = 100, total size = 498	Latency	0.54	0.0
Number of instructions = 48, nopsize = 8, total size = 392	Latency	0.0	0.0
Number of instructions = 100, nopsize = 4, total size = 408	Latency	0.5	0.0
Number of instructions = 10000, nopsize = 8, total size = 80008	Latency	0.0	0.0
Number of instructions = 1000, nopsize = 1, total size = 1008	Latency	0.41	0.0
Number of instructions = 100, total size = 204	Latency	0.41	0.0
Number of instructions = 4, total size = 8	Latency	0.82	0.0
Number of instructions = 10, nopsize = 4, total size = 44	Latency	0.55	0.0
Number of instructions = 3, total size = 6	Latency	1.01	0.0
Number of instructions = 6, total size = 24	Latency	0.73	0.0
Number of instructions = 10000, nopsize = 1, total size = 10008	Latency	0.38	0.0
Number of instructions = 100, nopsize = 8, total size = 808	Latency	0.0	0.0
Number of instructions = 6, total size = 12	Latency	0.74	0.0
Number of instructions = 4000, nopsize = 1, total size = 4008	Latency	0.38	0.0
Number of instructions = 10, total size = 84	Latency	1.2	0.0
Number of instructions = 2000, nopsize = 1, total size = 2008	Latency	0.4	0.0
Number of instructions = 1000, total size = 4998	Latency	0.54	0.0
Number of instructions = 10, nopsize = 1, total size = 14	Latency	0.44	0.0
Number of instructions = 6, total size = 32	Latency	1.0	0.0
Number of instructions = 20000, nopsize = 1, total size = 20008	Latency	0.38	0.0
Number of instructions = 4, nopsize = 8, total size = 36	Latency	0.0	0.0
Number of instructions = 36, nopsize = 8, total size = 296	Latency	0.0	0.0
Number of instructions = 100, total size = 988	Latency	1.53	0.0
Number of instructions = 31, nopsize = 1, total size = 35	Latency	1.13	0.0
Number of instructions = 25, nopsize = 1, total size = 29	Latency	1.2	0.0
Number of instructions = 64, nopsize = 8, total size = 520	Latency	0.0	0.0
Number of instructions = 32, total size = 308	Latency	1.38	0.0
Number of instructions = 32, nopsize = 1, total size = 36	Latency	0.38	0.0
Number of instructions = 32, total size = 158	Latency	0.54	0.0
Number of instructions = 1000, nopsize = 4, total size = 4008	Latency	0.5	0.0
Number of instructions = 2, nopsize = 1, total size = 6	Latency	1.51	0.0
Number of instructions = 10, total size = 44	Latency	0.5	0.0
Number of instructions = 10, total size = 20	Latency	0.57	0.0
Number of instructions = 8, nopsize = 8, total size = 68	Latency	0.0	0.0
lock cmpxchg [m8], r8	Latency	27.44	0.0
movzx r64,[m16]	Throughput	1.32	0.0
loop, taken=alternate, 2 per 16 bytes, 64 bit mode	Latency	1.05	0.17
movzx r16,[m8] / mov [m8],r8	Latency	2.48	0.0
xadd [m16], r16	Latency	5.31	0.0
movzx r32,[m8]	Throughput	1.43	0.0
movsx r64,r16	Latency	1.07	0.0
movzx r16,[m8]	Throughput	1.19	0.0
movzx r16,r8	Latency	1.0	0.0
lock cmpxchg16b [m]	Latency	72.75	0.23
jmp (2 per 16 bytes), 64 bit	Latency	3.16	0.08
Throughput prefetcht0 [m]	Throughput	1.41	0.0
xadd [m32], r32	Latency	5.32	0.0
movsxd r64,[m32]	Throughput	1.11	0.0
jmp (8 per 16 bytes), 64 bit	Latency	8.3	0.12
movsx r16,[m8] / mov [m8],r8	Latency	2.48	0.0
add [m]	Latency	4.9	0.0
movsx r32,r16	Latency	0.99	0.0
xadd [m64], r64	Latency	4.9	0.0
movsx r32,[m16] / mov [m16],r16	Latency	2.69	0.0
lock cmpxchg [m32], r32	Latency	31.97	0.12
Throughput prefetcht1 [m]	Throughput	1.41	0.0
movzx r32,r8	Latency	0.99	0.0
lock xadd [m32], r32	Latency	26.01	2.49
jmp (5 per 16 bytes), 64 bit	Latency	7.9	0.0
movzx r32,[m8] / mov [m8],r8	Latency	1.98	0.0
jmp memory + lea + mov, 64 bit	Latency	1.92	4.77
jmp (3 per 16 bytes), 64 bit	Latency	4.88	0.0
movsx r16,r8	Latency	0.99	0.0
jmp (1 per 16 bytes), 64 bit	Latency	3.03	0.01
cmpxchg [m32], r32	Latency	11.68	0.0
movsx r16,[m8]	Throughput	1.19	0.0
lock add [m]	Latency	24.72	2.54
movsxd r64,[m32] / mov [m32],r32	Latency	3.61	7.75
cmpxchg16b [m]	Latency	64.88	0.14
movsx r32,[m8] / mov [m8],r8	Latency	2.64	0.01
movzx r64,[m16] / mov [m16],r16	Latency	1.99	0.0
movzx r64,r8	Latency	0.99	0.0
lock xadd [m8], r8	Latency	25.48	0.0
movsx r64,[m16] / mov [m16],r16	Latency	2.69	0.0
loope, alternate, 2 per 16 bytes, 64 bit mode	Latency	5.78	26.8
movzx r32,[m16] / mov [m16],r16	Latency	2.15	0.0
cmpxchg [m16], r16	Latency	8.82	0.0
movzx r64,r16	Latency	0.99	0.0
cmpxchg8b [m]	Latency	12.74	0.0
movsx r32,r8	Latency	1.07	0.0
movsxd r64,r32	Latency	1.0	0.0
Throughput prefetchnta [m]	Throughput	1.3	0.0
Throughput prefetcht2 [m]	Throughput	1.3	0.0
movsx r64,[m8]	Throughput	1.28	0.0
lock xadd [m64], r64	Latency	23.52	0.0
xadd [m8], r8	Latency	5.31	0.0
lock cmpxchg8b [m]	Latency	34.07	0.0
jmp (4 per 16 bytes), 64 bit	Latency	6.13	0.0
movzx r32,r16	Latency	1.07	0.0
movzx r64,[m8] / mov [m8],r8	Latency	2.15	0.0
lock xadd [m16], r16	Latency	25.6	0.13
jmp register + lea, 64 bit	Latency	1.5	0.0
movsx r64,[m16]	Throughput	1.19	0.0
movsx r64,r8	Latency	0.99	0.0
loop, taken=10, 2 per 16 bytes, 64 bit mode	Latency	2.41	0.01
lock cmpxchg [m16], r16	Latency	29.86	0.16
xlat / xor eax,eax	Throughput	1.4	nan
loopne, alternate, 2 per 16 bytes, 64 bit mode	Latency	1.88	9.69
lock cmpxchg [m64], r64	Latency	29.86	0.16
movzx r32,[m16]	Throughput	1.43	0.0
movsx r32,[m8]	Throughput	1.29	0.0
movsx r32,[m16]	Throughput	1.19	0.0
xlat	Latency	5.89	0.0
jmp (6 per 16 bytes), 64 bit	Latency	8.56	0.0
cmpxchg [m8], r8	Latency	8.82	0.0
movsx r64,[m8] / mov [m8],r8	Latency	2.49	0.0
cmpxchg [m64], r64	Latency	9.56	0.0
movzx r64,[m8]	Throughput	1.32	0.0
maskmovdqu r,r (pattern 0xff) + movq/dqa (x)mm,[mem]	Latency	124.74	0.49
maskmovq r,r (pattern 0x00)	Throughput	1.93	0.0
Throughput emms (64 bit mode)	Throughput	0.98	0.0
blendvps r128,r128,xmm0	Throughput	1.96	0.0
Throughput unaligned write movups [m],xmm	Throughput	1.83	0.0
maskmovq r,r (pattern 0x02)	Throughput	1.93	0.0
maskmovdqu r,r (pattern 0x33) + movq/dqa (x)mm,[mem]	Latency	138.44	0.56
pblendvb r128,r128,xmm0	Throughput	2.13	0.0
Latency with memory operand extractps  / movss	Latency	3.96	0.0
Latency with memory operand insertps  / movss	Latency	3.96	0.0
maskmovq r,r (pattern 0xff) + movq/dqa (x)mm,[mem]	Latency	133.15	2.79
Throughput unaligned write movupd [m],xmm	Throughput	1.8	0.0
maskmovdqu r,r (pattern 0xff)	Throughput	1.93	0.0
stmxcsr m	Throughput	12.75	0.0
maskmovdqu r,r (pattern 0x02)	Throughput	1.78	0.0
maskmovq r,r (pattern 0x55)	Throughput	1.93	0.0
Throughput extractps xmm,	Throughput	1.17	0.45
Throughput unaligned write movdqu [m],xmm	Throughput	1.66	0.0
Latency ptest xmm,xmm / sbb / movd	Latency	2.87	0.0
Latency unaligned write+read movdqu [m],xmm / movdqu xmm,[m]	Latency	2.04	0.03
blendps r128,r128,i	Throughput	0.98	0.0
maskmovq r,r (pattern 0x33) + movq/dqa (x)mm,[mem]	Latency	130.69	16.94
blendpd r128,r128,i	Throughput	0.99	0.0
maskmovdqu r,r (pattern 0x55) + movq/dqa (x)mm,[mem]	Latency	139.57	4.18
Throughput insertps xmm,	Throughput	1.14	0.07
Latency unaligned write+read movupd [m],xmm / movupd xmm,[m]	Latency	2.15	0.0
maskmovdqu r,r (pattern 0x00)	Throughput	1.78	0.0
maskmovdqu r,r (pattern 0x33)	Throughput	1.94	0.0
maskmovdqu r,r (pattern 0x02) + movq/dqa (x)mm,[mem]	Latency	124.93	0.64
Throughput unaligned read movups xmm,[m]	Throughput	1.3	0.0
maskmovq r,r (pattern 0x55) + movq/dqa (x)mm,[mem]	Latency	133.52	0.43
ldmxcsr + stmccsr	Latency	32.25	0.05
Throughput emms (32 bit mode)	Throughput	1.06	0.0
Latency unaligned write+read movups [m],xmm / movups xmm,[m]	Latency	1.98	0.0
blendps r128,[m128],i	Throughput	1.07	0.0
maskmovq r,r (pattern 0xff)	Throughput	1.93	0.0
Throughput unaligned read movdqu xmm,[m]	Throughput	1.3	0.0
maskmovdqu r,r (pattern 0x55)	Throughput	1.93	0.0
blendvps r128,[m128],xmm0	Throughput	2.13	0.0
Throughput ptest xmm,xmm	Throughput	0.99	0.0
maskmovq r,r (pattern 0x00) + movq/dqa (x)mm,[mem]	Latency	1.67	0.0
Latency insertps xmm,xmm,i	Latency	1.15	0.0
blendpd r128,[m128],i	Throughput	0.99	0.0
maskmovq r,r (pattern 0x33)	Throughput	1.93	0.0
maskmovdqu r,r (pattern 0x00) + movq/dqa (x)mm,[mem]	Latency	1.67	0.0
ldmxcsr m	Throughput	30.77	0.0
maskmovq r,r (pattern 0x02) + movq/dqa (x)mm,[mem]	Latency	133.04	2.28
pblendvb r128,[m128],xmm0	Throughput	2.13	0.0
Throughput unaligned read movupd xmm,[m]	Throughput	1.41	0.0
register mmx, ADD interspearced by 1 MOVes	Latency	0.99	0.0
register xmm, ADD interspearced by 1 MOVes	Latency	0.99	0.0
register r8, ADD interspearced by 0 MOVes	Latency	1.06	0.0
register mmx, ADD interspearced by 3 MOVes	Latency	1.08	0.0
register xmm, ADD interspearced by 3 MOVes	Latency	1.0	0.0
register mmx, known to be zero	Latency	0.98	0.0
register r64, known to be zero	Latency	1.06	0.0
register r16, ADD interspearced by 1 MOVes	Latency	0.99	0.0
register r64, ADD interspearced by 3 MOVes	Latency	0.75	0.0
register r32, ADD interspearced by 2 MOVes	Latency	0.99	0.0
register r32, known to be zero	Latency	1.08	0.0
register xmm, ADD interspearced by 4 MOVes	Latency	1.08	0.0
register r16, ADD interspearced by 4 MOVes	Latency	1.02	0.0
register r64, ADD interspearced by 4 MOVes	Latency	0.91	0.0
register r64, ADD interspearced by 1 MOVes	Latency	0.81	0.0
register r8, ADD interspearced by 3 MOVes	Latency	1.08	0.0
register xmm, ADD interspearced by 0 MOVes	Latency	0.98	0.0
register r8, ADD interspearced by 1 MOVes	Latency	1.05	0.01
register r32, ADD interspearced by 4 MOVes	Latency	0.98	0.0
register xmm, known to be zero	Latency	1.35	0.04
register r64, ADD interspearced by 2 MOVes	Latency	1.08	0.0
register r16, ADD interspearced by 2 MOVes	Latency	1.08	0.0
register r32, ADD interspearced by 3 MOVes	Latency	0.82	0.0
register r16, known to be zero	Latency	0.98	0.0
register r8, ADD interspearced by 2 MOVes	Latency	0.99	0.0
register mmx, ADD interspearced by 4 MOVes	Latency	1.0	0.0
register r32, ADD interspearced by 0 MOVes	Latency	0.98	0.0
register mmx, ADD interspearced by 0 MOVes	Latency	0.98	0.0
register r16, ADD interspearced by 3 MOVes	Latency	1.0	0.0
register xmm, ADD interspearced by 2 MOVes	Latency	1.08	0.0
register r8, ADD interspearced by 4 MOVes	Latency	1.0	0.0
register r32, ADD interspearced by 1 MOVes	Latency	0.75	0.0
register r16, ADD interspearced by 0 MOVes	Latency	0.98	0.0
register mmx, ADD interspearced by 2 MOVes	Latency	1.0	0.0
register r8, known to be zero	Latency	1.06	0.0
register r64, ADD interspearced by 0 MOVes	Latency	0.98	0.0
imul , regsize 32, numop 2	Throughput	1.22	0.0
imul , regsize 32, numop 3	Throughput	1.33	0.0
Throughput with memory operand: mul , registersize 32 (subtract 1 uop)	Throughput	2.74	0.03
mul , registersize 32 (subtract 1 uop)	Throughput	1.06	0.0
imul , registersize 8	Latency	1.97	0.0
mul , registersize 64 (subtract 1 uop)	Throughput	1.28	0.0
imul , registersize 8 (subtract 1 uop)	Throughput	0.61	0.0
imul , registersize 32	Latency	2.94	0.0
imul , registersize 16	Latency	2.94	0.0
Throughput with memory operand: mul , registersize 8 (subtract 1 uop)	Throughput	0.55	0.0
imul , registersize 16 (subtract 1 uop)	Throughput	1.14	0.0
Throughput with memory operand: imul , regsize 32, numop 2	Throughput	1.21	0.0
Throughput with memory operand: imul , regsize 32, numop 3	Throughput	1.31	0.0
mul , registersize 16 (subtract 1 uop)	Throughput	1.06	0.0
Throughput with memory operand: imul , registersize 16 (subtract 1 uop)	Throughput	2.48	0.0
mul , registersize 32	Latency	3.19	0.0
Throughput with memory operand: mul , registersize 64 (subtract 1 uop)	Throughput	3.22	0.0
mul , registersize 16	Latency	3.19	0.0
Throughput with memory operand: imul , registersize 32 (subtract 1 uop)	Throughput	2.47	0.0
imul , regsize 16, numop 2	Throughput	1.12	0.0
imul , regsize 16, numop 3	Throughput	1.12	0.0
Throughput with memory operand: imul , registersize 8 (subtract 1 uop)	Throughput	0.55	0.0
imul , regsize 64, numop 3	Throughput	1.96	0.0
Throughput with memory operand: imul , regsize 16, numop 2	Throughput	1.31	0.0
Throughput with memory operand: imul , regsize 16, numop 3	Throughput	1.21	0.0
mul , registersize 8 (subtract 1 uop)	Throughput	0.57	0.0
Throughput with memory operand: imul , registersize 64 (subtract 1 uop)	Throughput	3.03	0.03
imul , regsize 64, numop 2	Throughput	1.97	0.0
imul , registersize 64	Latency	8.48	0.0
mul , registersize 8	Latency	2.13	0.0
imul , registersize 64 (subtract 1 uop)	Throughput	1.28	0.0
Throughput with memory operand: mul , registersize 16 (subtract 1 uop)	Throughput	2.68	0.0
Throughput with memory operand: imul , regsize 64, numop 3	Throughput	2.13	0.0
Throughput with memory operand: imul , regsize 64, numop 2	Throughput	1.96	0.0
mul , registersize 64	Latency	7.83	0.0
imul , registersize 32 (subtract 1 uop)	Throughput	1.14	0.0
Case 1: integer add, chainlength = 1000	Latency	0.99	0.0
Case 2: integer mul, chainlength = 1000000	Latency	2.01	0.01
Case 3: floating point add, chainlength = 100	Latency	1.82	0.0
Case 4: floating point mul, chainlength = 1000000	Latency	2.96	0.0
Case 2: integer mul, chainlength = 1000	Latency	1.99	0.0
Case 1: integer add, chainlength = 1000000	Latency	0.99	0.0
Case 1: integer add, chainlength = 10	Latency	0.51	0.0
Case 4: floating point mul, chainlength = 1000	Latency	2.99	0.0
Case 3: floating point add, chainlength = 1000000	Latency	2.03	0.01
Case 4: floating point mul, chainlength = 10	Latency	1.44	0.0
Case 3: floating point add, chainlength = 1000	Latency	2.08	0.01
Case 4: floating point mul, chainlength = 100	Latency	2.81	0.0
Case 3: floating point add, chainlength = 10	Latency	0.92	0.0
Case 1: integer add, chainlength = 100	Latency	0.96	0.0
Case 2: integer mul, chainlength = 10	Latency	1.02	0.0
Case 2: integer mul, chainlength = 100	Latency	1.85	0.0
pop , operand: SP	Throughput	3.11	0.0
pop , operand: M	Throughput	2.04	0.0
push , operand: R	Throughput	1.72	0.0
pop , operand: F	Throughput	1.17	0.0
push , operand: M	Throughput	1.7	0.0
push , operand: SP	Throughput	1.72	0.0
push , operand: I	Throughput	1.69	0.03
push , operand: F	Throughput	1.49	0.0
pop , operand: R	Throughput	1.17	0.0
rcr , 4 regsize 16	Throughput	40.88	3.62
ror , cl regsize 8	Throughput	1.61	0.3
shrd , 1 regsize 64	Throughput	33.38	1.58
shl , 4 regsize 8	Throughput	1.42	0.76
rcr , 1 regsize 8	Throughput	1.53	0.21
shl , 4 regsize 64	Throughput	1.38	0.55
Throughput with memory operand: shrd , 1 regsize 16	Throughput	5.3	0.0
ror , 1 regsize 16	Throughput	1.61	0.3
btr r16, cx	Throughput	2.13	0.0
sar , 4 regsize 16	Throughput	1.3	0.44
bts r32, 5	Latency	1.97	0.0
shr , 4 regsize 16	Throughput	1.36	0.59
shl , 1 regsize 64	Throughput	1.3	0.44
shld , 1 regsize 32	Latency	2.05	0.0
sar , cl regsize 16	Throughput	1.36	0.59
shr , cl regsize 16	Throughput	1.3	0.44
rol , cl regsize 64	Throughput	1.61	0.29
shld , cl regsize 32	Latency	2.22	0.0
rcl , 1 regsize 32	Throughput	1.66	0.25
rcr , 1 regsize 16	Throughput	1.53	0.21
rol , 1 regsize 16	Throughput	1.61	0.29
btc r32, ecx	Throughput	2.14	0.0
rcl , 1 regsize 8	Throughput	1.66	0.25
rol , 4 regsize 8	Throughput	1.61	0.3
rcr , cl regsize 16	Throughput	43.98	3.29
bts r32, ecx	Throughput	1.97	0.0
rcr , 4 regsize 8	Throughput	40.87	4.09
ror , 4 regsize 32	Throughput	1.61	0.3
btr r32, 5	Latency	1.97	0.0
sar , 1 regsize 32	Throughput	1.3	0.44
sar , cl regsize 64	Throughput	1.36	0.59
rol , cl regsize 16	Throughput	1.61	0.29
shr , 1 regsize 32	Throughput	1.36	0.59
bts r64, rcx	Throughput	6.72	14.3
sar , cl regsize 8	Throughput	1.33	0.61
Throughput with memory operand: shrd , 6 regsize 64	Throughput	30.96	0.12
rcr , 1 regsize 32	Throughput	1.59	0.34
Throughput with memory operand: shld , cl regsize 64	Throughput	32.43	0.13
sar , 4 regsize 64	Throughput	1.28	0.47
rcl , cl regsize 64	Throughput	45.94	1.49
Throughput with memory operand: shld , 1 regsize 64	Throughput	35.12	0.14
ror , 4 regsize 8	Throughput	1.61	0.3
rcr , 4 regsize 32	Throughput	39.61	1.45
rcl , 1 regsize 64	Throughput	1.61	0.3
btc r32, 5	Latency	1.97	0.0
shr , cl regsize 64	Throughput	1.3	0.44
shl , 1 regsize 32	Throughput	1.3	0.44
shrd , 6 regsize 16	Latency	2.22	0.0
btc r64, 5	Latency	2.14	0.0
Throughput with memory operand: shrd , cl regsize 64	Throughput	33.53	0.14
ror , cl regsize 64	Throughput	1.66	0.25
Throughput with memory operand: shld , cl regsize 16	Throughput	5.3	0.0
shr , 4 regsize 8	Throughput	1.36	0.59
shld , 6 regsize 32	Latency	2.05	0.0
shl , cl regsize 8	Throughput	1.36	0.59
shld , cl regsize 16	Latency	2.22	0.0
bt r32, 5	Latency	1.07	0.0
rol , 1 regsize 8	Throughput	1.61	0.3
rcl , 1 regsize 16	Throughput	1.66	0.25
bts r16, 5	Latency	2.14	0.0
shrd , 1 regsize 32	Latency	2.05	0.0
shl , 4 regsize 16	Throughput	1.36	0.59
bts r16, cx	Throughput	2.13	0.0
btr r64, 5	Latency	1.97	0.0
shr , cl regsize 8	Throughput	1.38	0.55
Throughput with memory operand: shld , 6 regsize 64	Throughput	32.42	0.14
Throughput with memory operand: shld , 6 regsize 32	Throughput	5.62	0.89
shr , 4 regsize 32	Throughput	1.36	0.58
ror , 1 regsize 32	Throughput	1.61	0.3
rcl , 4 regsize 32	Throughput	42.54	0.13
shrd , 6 regsize 32	Latency	2.05	0.0
shl , cl regsize 64	Throughput	1.36	0.59
btr r64, rcx	Throughput	6.57	12.08
rcl , cl regsize 8	Throughput	44.43	4.16
shl , 1 regsize 8	Throughput	1.36	0.59
rol , cl regsize 32	Throughput	1.61	0.3
shr , 1 regsize 8	Throughput	1.36	0.59
rcl , cl regsize 16	Throughput	43.91	2.92
bt r16, 5	Latency	1.16	0.0
rol , 1 regsize 64	Throughput	1.61	0.3
ror , 1 regsize 8	Throughput	1.61	0.3
sar , 1 regsize 8	Throughput	1.3	0.44
sar , 1 regsize 64	Throughput	1.3	0.44
rcr , cl regsize 64	Throughput	45.22	1.98
shl , 1 regsize 16	Throughput	1.28	0.47
shld , 1 regsize 64	Throughput	33.5	3.09
shl , cl regsize 16	Throughput	1.36	0.58
shrd , cl regsize 64	Throughput	33.28	1.58
shld , 6 regsize 64	Throughput	33.93	0.0
Throughput with memory operand: shld , cl regsize 32	Throughput	5.31	0.0
Throughput with memory operand: shrd , 6 regsize 16	Throughput	5.31	0.0
ror , 1 regsize 64	Throughput	1.61	0.3
Throughput with memory operand: shld , 1 regsize 32	Throughput	4.9	0.0
shrd , 1 regsize 16	Latency	2.22	0.0
rcr , cl regsize 8	Throughput	43.96	3.2
shrd , 6 regsize 64	Throughput	33.35	1.52
shld , 1 regsize 16	Latency	2.05	0.0
sar , cl regsize 32	Throughput	1.36	0.59
shr , cl regsize 32	Throughput	1.28	0.47
shl , 4 regsize 32	Throughput	1.36	0.59
ror , 4 regsize 64	Throughput	1.61	0.3
btc r16, 5	Latency	1.97	0.0
rol , 4 regsize 32	Throughput	1.61	0.3
shld , cl regsize 64	Throughput	34.05	0.13
rcl , 4 regsize 16	Throughput	40.84	2.91
shrd , cl regsize 16	Latency	2.22	0.0
Throughput with memory operand: shrd , cl regsize 32	Throughput	5.6	0.97
ror , cl regsize 32	Throughput	1.66	0.25
rcl , cl regsize 32	Throughput	42.89	2.28
rcr , 4 regsize 64	Throughput	41.81	2.85
bt r32, ecx	Throughput	1.07	0.0
Throughput with memory operand: shrd , 1 regsize 64	Throughput	30.96	0.14
bt r16, cx	Throughput	1.07	0.0
btc r16, cx	Throughput	2.14	0.0
btr r16, 5	Latency	2.13	0.0
sar , 4 regsize 32	Throughput	1.3	0.44
Throughput with memory operand: shld , 6 regsize 16	Throughput	5.31	0.0
rcl , 4 regsize 8	Throughput	40.84	2.92
shr , 1 regsize 64	Throughput	1.36	0.59
rcl , 4 regsize 64	Throughput	39.34	0.39
shl , cl regsize 32	Throughput	1.36	0.59
shr , 4 regsize 64	Throughput	1.3	0.44
bt r64, 5	Latency	1.07	0.0
bt r64, rcx	Throughput	3.75	13.31
shld , 6 regsize 16	Latency	2.22	0.0
btr r32, ecx	Throughput	1.97	0.0
btc r64, rcx	Throughput	6.48	12.5
rol , 1 regsize 32	Throughput	1.61	0.3
Throughput with memory operand: shld , 1 regsize 16	Throughput	5.3	0.0
rcr , 1 regsize 64	Throughput	1.53	0.21
rcr , cl regsize 32	Throughput	43.68	3.38
ror , 4 regsize 16	Throughput	1.61	0.3
rol , 4 regsize 64	Throughput	1.61	0.29
rol , cl regsize 8	Throughput	1.61	0.3
shr , 1 regsize 16	Throughput	1.36	0.59
Throughput with memory operand: shrd , 1 regsize 32	Throughput	5.31	0.0
rol , 4 regsize 16	Throughput	1.61	0.3
sar , 1 regsize 16	Throughput	1.3	0.44
bts r64, 5	Latency	1.97	0.0
sar , 4 regsize 8	Throughput	1.28	0.47
shrd , cl regsize 32	Latency	2.05	0.0
Throughput with memory operand: shrd , cl regsize 16	Throughput	5.31	0.0
Throughput with memory operand: shrd , 6 regsize 32	Throughput	5.31	0.0
ror , cl regsize 16	Throughput	1.61	0.29
Case 6: call_and_ret_and_add_rsp,const	Latency	0.97	0.02
Case 4: call_and_ret	Latency	0.99	0.03
Case 2: added_mov_r,[rsp]	Latency	1.08	0.08
Case 5: call_and_ret_imm	Latency	1.46	0.04
Case 3: further_added_mov_r,rsp	Latency	1.05	0.36
Case 1: Push_and_pop_only	Latency	0.94	0.0
register read/write size 16 bits, crossing 128 bytes boundary	Latency	30.83	0.78
register read/write size 128 bits, read offset by 8 bytes	Latency	5.34	16.3
register read/write size 32 bits, read offset by 2 bytes	Latency	17.87	0.5
register read/write size 16 bits, read offset by 1 bytes	Latency	16.21	0.04
register read/write size 16 bits, crossing 0 bytes boundary	Latency	2.48	0.0
register read/write size 128 bits, crossing 64 bytes boundary	Latency	30.8	0.05
register read/write size 128 bits, crossing 32 bytes boundary	Latency	2.15	0.0
register read/write size 128 bits, read offset by 0 bytes	Latency	1.99	0.0
register read/write size 128 bits, crossing 4 bytes boundary	Latency	30.81	0.01
register read/write size 64 bits, crossing 128 bytes boundary	Latency	30.87	0.2
register read/write size 32 bits, crossing 64 bytes boundary	Latency	31.09	0.7
register read/write size 32 bits, crossing 8 bytes boundary	Latency	2.0	0.0
register read/write size 64 bits, read offset by 4 bytes	Latency	17.33	0.01
register read/write size 16 bits, crossing 8 bytes boundary	Latency	2.49	0.0
register read/write size 32 bits, crossing 0 bytes boundary	Latency	2.17	0.0
register read/write size 64 bits, crossing 16 bytes boundary	Latency	2.0	0.0
register read/write size 16 bits, crossing 16 bytes boundary	Latency	2.72	0.01
register read/write size 32 bits, crossing 16 bytes boundary	Latency	2.03	0.03
register read/write size 32 bits, read offset by 0 bytes	Latency	1.99	0.0
register read/write size 32 bits, crossing 32 bytes boundary	Latency	2.0	0.0
register read/write size 16 bits, read offset by 0 bytes	Latency	2.61	0.02
register read/write size 128 bits, crossing 0 bytes boundary	Latency	2.0	0.0
register read/write size 64 bits, crossing 64 bytes boundary	Latency	31.09	0.75
register read/write size 64 bits, crossing 32 bytes boundary	Latency	2.0	0.0
register read/write size 32 bits, crossing 4 bytes boundary	Latency	2.0	0.0
register read/write size 128 bits, crossing 16 bytes boundary	Latency	2.17	0.0
register read/write size 16 bits, crossing 4 bytes boundary	Latency	2.52	0.02
register read/write size 16 bits, crossing 32 bytes boundary	Latency	2.5	0.0
register read/write size 128 bits, crossing 8 bytes boundary	Latency	2.0	0.0
register read/write size 16 bits, crossing 64 bytes boundary	Latency	30.83	0.74
register read/write size 64 bits, crossing 0 bytes boundary	Latency	2.01	0.0
register read/write size 128 bits, crossing 128 bytes boundary	Latency	30.75	0.0
register read/write size 64 bits, crossing 8 bytes boundary	Latency	2.15	0.0
register read/write size 32 bits, crossing 128 bytes boundary	Latency	30.86	0.17
register read/write size 64 bits, read offset by 0 bytes	Latency	2.12	0.01
register read/write size 64 bits, crossing 4 bytes boundary	Latency	1.99	0.0
rep movsd, count = 1000	Latency	149.45	485.83
rep stosb, count = 10000	Latency	365.76	2636.46
repe cmpsb, count = 1000, misalign = 0	Latency	580.37	9.1
repe cmpsb, count = 1000, misalign = 4	Latency	622.52	1262.5
repe scasb, count = 1000, misalign = 0	Latency	603.06	84.17
rep stosd, count = 1000, misalign = 4	Latency	148.48	455.33
rep lodsd, count = 10000	Latency	7468.46	6047.47
rep stosd, count = 1000, misalign = 0	Latency	160.68	1196.43
scasw	Latency	1.5	1.45
rep stosb, count = 100	Latency	52.34	0.0
scasq	Latency	2.16	10.04
rep lodsb, count = 1000	Latency	762.04	0.11
rep movsq, count = 10000	Latency	6182.07	27694.92
scasd	Latency	1.98	7.16
rep stosw, count = 10000	Latency	686.65	4568.82
scasb	Latency	1.27	0.29
rep movsb, count = 1000	Latency	60.78	0.14
repe scasq, count = 1000, misalign = 4	Latency	1114.04	3.58
repe cmpsd, count = 1000, misalign = 0	Latency	583.76	123.66
repe scasq, count = 1000, misalign = 0	Latency	391.21	4.68
rep movsd, count = 1000, misalign = 16	Latency	150.81	569.76
rep lodsb, count = 100	Latency	100.9	0.02
rep stosw, count = 1000	Latency	101.68	508.89
repe scasb, count = 100, misalign = 0	Latency	66.06	0.05
repe scasd, count = 1000, misalign = 0	Latency	215.35	0.52
rep stosb, count = 1000	Latency	60.45	0.03
repe cmpsd, count = 1000, misalign = 4	Latency	579.75	5.42
repe scasb, count = 1000, misalign = 4	Latency	557.06	95.11
repe cmpsq, count = 10000, misalign = 4	Latency	14935.85	3266.1
rep stosd, count = 100, misalign = 16	Latency	48.38	0.08
repe scasd, count = 10000, misalign = 4	Latency	2002.83	567.5
rep stosd, count = 10000, misalign = 16	Latency	1472.85	11316.52
repe scasd, count = 10000, misalign = 0	Latency	1980.76	478.78
rep movsd, count = 1000, misalign = 0	Latency	162.18	608.58
rep movsd, count = 1000, misalign = 4	Latency	165.03	518.0
repe cmpsw, count = 100, misalign = 0	Latency	64.26	0.18
repe cmpsw, count = 100, misalign = 4	Latency	69.6	0.16
repe cmpsb, count = 10000, misalign = 4	Latency	5781.75	1428.61
repe cmpsb, count = 10000, misalign = 0	Latency	5955.39	53968.08
repe scasw, count = 10000, misalign = 4	Latency	952.72	21.32
repe scasw, count = 10000, misalign = 0	Latency	933.33	135.19
rep stosq, count = 100	Latency	48.39	0.11
rep movsq, count = 100, misalign = 4	Latency	189.53	0.21
rep movsd, count = 10000	Latency	1474.3	11445.05
rep movsq, count = 100, misalign = 0	Latency	49.03	0.56
rep movsq, count = 1000	Latency	284.42	965.77
rep movsd, count = 100, misalign = 16	Latency	49.84	0.94
rep movsq, count = 1000, misalign = 4	Latency	1955.95	906.95
rep movsd, count = 10000, misalign = 4	Latency	1485.19	11558.97
rep stosd, count = 1000, misalign = 16	Latency	147.32	621.33
rep movsd, count = 10000, misalign = 0	Latency	1480.21	15018.02
repe scasd, count = 100, misalign = 0	Latency	63.35	53.56
repe cmpsb, count = 100, misalign = 4	Latency	69.52	0.02
rep stosq, count = 100, misalign = 16	Latency	52.42	0.09
repe cmpsb, count = 100, misalign = 0	Latency	69.53	0.03
movsd	Latency	3.7	22.06
movsb	Latency	2.36	0.49
rep movsb, count = 10000	Latency	393.48	1614.57
repe cmpsw, count = 1000, misalign = 4	Latency	580.31	7.08
rep stosq, count = 100, misalign = 4	Latency	205.44	0.0
repe cmpsw, count = 1000, misalign = 0	Latency	628.79	10.25
rep stosq, count = 100, misalign = 0	Latency	52.43	0.13
movsw	Latency	2.73	2.98
rep stosq, count = 1000, misalign = 16	Latency	281.71	877.81
repe cmpsw, count = 10000, misalign = 0	Latency	5843.51	13111.4
movsq	Latency	3.73	22.53
rep movsq, count = 10000, misalign = 4	Latency	19269.38	5019.09
rep movsq, count = 10000, misalign = 0	Latency	6151.01	5524.15
repe scasq, count = 100, misalign = 0	Latency	66.35	1.17
rep lodsw, count = 10000	Latency	7657.23	77800.39
repe scasq, count = 100, misalign = 4	Latency	103.98	0.0
rep lodsq, count = 100	Latency	89.13	0.0
rep lodsd, count = 100	Latency	87.58	0.18
repe scasd, count = 100, misalign = 4	Latency	66.19	0.37
rep movsb, count = 100	Latency	50.57	0.03
rep stosq, count = 10000	Latency	5217.63	64138.51
rep movsq, count = 1000, misalign = 16	Latency	309.11	1060.35
rep stosq, count = 10000, misalign = 4	Latency	19497.86	62889.64
rep movsw, count = 10000	Latency	760.59	5551.08
rep stosq, count = 10000, misalign = 0	Latency	5075.26	7541.71
rep stosd, count = 10000, misalign = 0	Latency	1467.96	12551.46
rep stosd, count = 10000, misalign = 4	Latency	1473.85	10134.99
rep stosd, count = 100, misalign = 0	Latency	52.42	0.09
rep stosw, count = 100	Latency	52.35	0.01
rep stosd, count = 100, misalign = 4	Latency	48.31	0.01
rep movsd, count = 100	Latency	49.82	0.8
rep movsw, count = 1000	Latency	94.63	407.39
repe cmpsq, count = 100, misalign = 0	Latency	69.87	1.4
repe cmpsq, count = 100, misalign = 4	Latency	149.3	2.45
repe cmpsd, count = 100, misalign = 0	Latency	69.74	0.65
rep lodsb, count = 10000	Latency	7454.48	188.43
repe cmpsq, count = 1000, misalign = 4	Latency	1616.72	97.09
repe cmpsq, count = 1000, misalign = 0	Latency	628.52	15.26
repe scasd, count = 1000, misalign = 4	Latency	258.83	0.89
repe cmpsq, count = 10000, misalign = 0	Latency	10635.68	1557.37
repe cmpsd, count = 10000, misalign = 4	Latency	6017.19	77619.3
rep movsq, count = 10000, misalign = 16	Latency	6150.66	6702.36
rep movsd, count = 100, misalign = 4	Latency	49.86	1.04
rep movsd, count = 100, misalign = 0	Latency	54.13	2.0
rep movsq, count = 1000, misalign = 0	Latency	308.44	1195.75
rep lodsw, count = 1000	Latency	815.44	1273.12
rep stosq, count = 1000	Latency	280.61	947.6
repe scasb, count = 10000, misalign = 4	Latency	5591.74	34474.94
rep movsq, count = 100, misalign = 16	Latency	53.14	0.74
repe scasb, count = 10000, misalign = 0	Latency	5460.94	1272.12
rep movsq, count = 100	Latency	53.22	1.21
rep stosq, count = 10000, misalign = 16	Latency	5068.24	8224.37
rep movsw, count = 100	Latency	51.66	0.25
rep movsd, count = 10000, misalign = 16	Latency	1482.51	11725.13
cmpsq	Latency	7.98	22.41
rep stosd, count = 1000	Latency	156.18	429.83
cmpsw	Latency	7.13	4.81
rep lodsq, count = 1000	Latency	784.79	2099.26
cmpsb	Latency	6.56	0.31
cmpsd	Latency	7.24	6.75
repe scasw, count = 1000, misalign = 4	Latency	148.77	0.52
repe scasw, count = 1000, misalign = 0	Latency	140.38	88.98
stosd	Latency	2.08	0.85
repe scasb, count = 100, misalign = 4	Latency	60.95	0.02
stosb	Latency	1.92	0.22
rep lodsd, count = 1000	Latency	815.6	120.67
stosw	Latency	1.76	0.05
stosq	Latency	2.5	4.5
rep stosd, count = 100	Latency	52.38	0.04
repe scasw, count = 100, misalign = 4	Latency	61.0	0.08
rep lodsq, count = 10000	Latency	7470.42	923.37
repe scasw, count = 100, misalign = 0	Latency	61.0	0.07
lodsq	Latency	1.25	0.36
rep lodsw, count = 100	Latency	88.82	0.16
repe cmpsd, count = 10000, misalign = 0	Latency	5858.76	32823.01
repe cmpsd, count = 100, misalign = 4	Latency	69.77	0.77
lodsw	Latency	1.55	1.83
rep stosq, count = 1000, misalign = 0	Latency	303.12	942.69
rep stosq, count = 1000, misalign = 4	Latency	2162.01	4277.26
rep stosd, count = 10000	Latency	1469.16	10036.92
lodsb	Latency	1.11	0.06
lodsd	Latency	1.13	0.12
repe scasq, count = 10000, misalign = 0	Latency	4513.5	36721.02
repe cmpsw, count = 10000, misalign = 4	Latency	5795.25	2644.84
repe scasq, count = 10000, misalign = 4	Latency	10098.82	1452.74
Case 3: normal + subnormal = subnormal	Latency	2.75	0.0
Case 29: normal / 0 = INF	Latency	7.92	0.0
Case 25: normal / normal = underflow	Latency	7.92	0.0
Case 8: normal + INF = INF	Latency	2.98	0.0
Case 16: normal * normal = underflow	Latency	2.68	0.0
Case 14: normal * subnormal = subnormal	Latency	2.68	0.0
Case 24: subnormal / normal = subnormal	Latency	8.85	0.69
Case 27: normal / NAN = NAN	Latency	7.92	0.0
Case 17: normal * normal = overflow	Latency	2.48	0.0
Case 9: INF + INF = INF	Latency	2.75	0.0
Case 1: normal + normal = subnormal	Latency	9.4	0.0
Case 4: subnormal + subnormal = normal	Latency	2.98	0.0
Case 19: normal * INF = INF	Latency	2.68	0.0
Case 28: normal / INF = 0	Latency	8.58	0.0
Case 18: normal * NAN = NAN	Latency	2.68	0.0
Case 23: normal / subnormal = normal	Latency	8.58	0.0
Case 7: normal + NAN = NAN	Latency	2.75	0.0
Case 15: subnormal * subnormal = underflow	Latency	2.48	0.0
Case 10: INF - INF = NAN	Latency	3.04	0.03
Case 21: normal / normal = normal	Latency	7.92	0.0
Case 5: subnormal + subnormal = subnormal	Latency	2.98	0.0
Case 22: normal / normal = subnormal	Latency	7.92	0.0
Case 30: 0 / 0 = NAN	Latency	7.92	0.0
Case 12: normal * normal = subnormal	Latency	2.48	0.0
Case 13: normal * subnormal = normal	Latency	2.48	0.0
Case 11: normal * normal = normal	Latency	2.69	0.0
Case 26: normal / normal = overflow	Latency	8.58	0.0
Case 2: normal + subnormal = normal	Latency	2.98	0.0
Case 0: normal + normal = normal	Latency	2.75	0.0
Case 6: normal + normal = overflow	Latency	6.93	0.0
Case 20: 0 * INF = NAN	Latency	2.48	0.0
Case 1: SSE2, 4 terms per iteration, 320 terms	Latency	0.8	0.0
Case 1: SSE2, 4 terms per iteration, 16 terms	Latency	0.77	0.0
Case 1: SSE2, 4 terms per iteration, 160 terms	Latency	0.84	0.0
Numbers are source offset and time	Latency	0.0	0.04
Case 20: cmp [basep+o32small], i16,  L-L-L-S, 200 blocks	Latency	630.61	6235.3
Case 47: mov [basep], i32small,  L-S-S-S, 200 blocks	Latency	306.54	nan
Case 29: cmp [basep+s*index], i32,  L-L-L-S,  100 blocks	Latency	467.72	nan
Case 40: cmp [rip small], i16,  L-L-L-S, 200 blocks	Latency	1054.46	nan
Case 31: cmp [basep+s*index+o8], i8,  L-L-L-S,  100 blocks	Latency	697.5	nan
Case 48: mov [basep], i32,  L-S-S-S, 200 blocks	Latency	302.64	nan
Case 10: cmp [abs32+p],i8,  L-L-L-S, 200 blocks	Latency	678.72	2920.35
Case 35: cmp [basep+s*index+o32small], i8,  L-L-L-S,  100 blocks	Latency	1266.77	nan
Case 34: cmp [basep+s*index+o32small], reg,  L-L-L-S,  100 blocks	Latency	385.85	396.72
Case 22: cmp [basep+o32small], i32,  L-L-L-S, 200 blocks	Latency	395.94	601.69
Case 2: mov reg64,i64, S-L-L-L, 100 blocks	Latency	1326.21	3152799.53
Case 54: cmp [rip], i32,  L-S-S-S, 200 blocks	Latency	393.32	nan
Case 50: mov [basep+s*index], i32,  L-S-S-S, 100 blocks	Latency	278.51	nan
Case 57: cmp FS:[o32small], i16,  L-L-S-S, 200 blocks	Latency	1163.03	319204.39
Case 17: cmp [basep+o8], i16,  L-L-L-S, 200 blocks	Latency	1031.55	1678241.8
Case 23: cmp [basep+o32], i8,  L-L-L-S, 200 blocks	Latency	714.33	nan
Case 53: cmp [rip], i16,  L-S-S-S, 100 blocks	Latency	513.77	1866.1
Case 12: mov [abs64],  L-L-L-S, 200 blocks	Latency	369.22	nan
Case 65: cmp [basep+s*index+o32], reg,  L-L-L-S, 100 blocks	Latency	533.49	nan
Case 15: cmp [basep], i32,  L-L-L-S, 100 blocks	Latency	483.52	nan
Case 18: cmp [basep+o8], i32,  L-L-L-S, 100 blocks	Latency	426.11	5327.33
Case 2: mov reg64,i64, S-L-L-L, 200 blocks	Latency	873.28	nan
Case 69: cmp r,r / jc o32small;  L-L-S-S, 200 blocks	Latency	751.73	199078.86
Case 19: cmp [basep+o32small], i8,  L-L-L-S, 200 blocks	Latency	590.29	156334.43
Case 64: mov r,[abs64],  L-S-S-S, 200 blocks	Latency	352.07	nan
Case 64: mov r,[abs64],  L-S-S-S, 100 blocks	Latency	476.2	49247.2
Case 27: cmp [basep+s*index], i8,  L-L-L-S,  200 blocks	Latency	712.6	nan
Case 51: cmp [rip], 0,  L-L-L-S, 100 blocks	Latency	422.28	372.31
Case 16: cmp [basep+o8], i8,  L-L-L-S, 200 blocks	Latency	712.47	227176.82
Case 30: cmp [basep+s*index+o8], reg,  L-L-L-S,  100 blocks	Latency	212.64	261613.52
Case 51: cmp [rip], 0,  L-L-L-S, 200 blocks	Latency	682.64	158980.27
Case 20: cmp [basep+o32small], i16,  L-L-L-S, 100 blocks	Latency	1473.49	5347818.88
Case 16: cmp [basep+o8], i8,  L-L-L-S, 100 blocks	Latency	395.69	7858.82
Case 65: cmp [basep+s*index+o32], reg,  L-L-L-S, 200 blocks	Latency	528.62	2047.99
Case 14: cmp [basep], i16,  L-L-L-S, 100 blocks	Latency	1092.34	384.94
Case 70: cmp [basep+o32], r / jc o32small;  L-L-S-S, 100 blocks	Latency	317.97	nan
Case 30: cmp [basep+s*index+o8], reg,  L-L-L-S,  200 blocks	Latency	520.25	3930.5
Case 12: mov [abs64],  L-L-L-S, 100 blocks	Latency	867.94	nan
Case 47: mov [basep], i32small,  L-S-S-S, 100 blocks	Latency	331.19	4416064.31
Case 7: cmp [abs32],i8,  L-L-L-S, 200 blocks	Latency	603.88	34454.06
Case 32: cmp [basep+s*index+o8], i16,  L-L-L-S,  200 blocks	Latency	994.2	nan
Case 50: mov [basep+s*index], i32,  L-S-S-S, 200 blocks	Latency	722.26	199.52
Case 42: cmp [rip small], i32,  L-L-L-S, 200 blocks	Latency	666.67	193194.76
Case 19: cmp [basep+o32small], i8,  L-L-L-S, 100 blocks	Latency	422.43	358.3
Case 55: cmp FS:[o32small], i8,  L-S-S-S, 100 blocks	Latency	290.63	8956.79
Case 45: cmp [rip], i32small,  L-L-L-S, 200 blocks	Latency	1069.97	1261792.07
Case 13: cmp [basep], i8,  L-L-L-S, 200 blocks	Latency	403.74	2433.01
Case 13: cmp [basep], i8,  L-L-L-S, 100 blocks	Latency	389.42	2540.16
Case 15: cmp [basep], i32,  L-L-L-S, 200 blocks	Latency	830.81	nan
Case 36: cmp [basep+s*index+o32small], i16,  L-L-L-S,  100 blocks	Latency	1680.07	2554409.24
Case 57: cmp FS:[o32small], i16,  L-L-S-S, 100 blocks	Latency	777.69	57914.91
Case 68: mov [basep+s*index+o32], r,  L-L-L-S, 200 blocks	Latency	826.56	427857.84
Case 14: cmp [basep], i16,  L-L-L-S, 200 blocks	Latency	1112.42	nan
Case 7: cmp [abs32],i8,  L-L-L-S, 100 blocks	Latency	405.13	5238.15
Case 46: cmp [rip], i32,  L-L-L-S, 200 blocks	Latency	666.5	136507.64
Case 3: mov reg64,i64, L-L-L-S, 100 blocks	Latency	1679.37	3101808.78
Case 18: cmp [basep+o8], i32,  L-L-L-S, 200 blocks	Latency	699.14	245764.18
Case 1: mov reg64,i32, S-L-L-L, 200 blocks	Latency	337.11	nan
Case 1: mov reg64,i32, S-L-L-L, 100 blocks	Latency	264.33	5124.14
Case 37: cmp [basep+s*index+o32small], i32,  L-S-S-S,  200 blocks	Latency	471.73	nan
Case 37: cmp [basep+s*index+o32small], i32,  L-S-S-S,  100 blocks	Latency	327.19	368895.72
Case 34: cmp [basep+s*index+o32small], reg,  L-L-L-S,  200 blocks	Latency	1006.85	1286682.63
Case 21: cmp [basep+o32small], i32small,  L-L-L-S, 100 blocks	Latency	449.01	2030.02
Case 48: mov [basep], i32,  L-S-S-S, 100 blocks	Latency	282.71	284776.75
Case 5: mov reg64,i64small, L-L-L-S, 100 blocks	Latency	2191.13	nan
Case 5: mov reg64,i64small, L-L-L-S, 200 blocks	Latency	977.8	103671.7
Case 70: cmp [basep+o32], r / jc o32small;  L-L-S-S, 200 blocks	Latency	447.75	nan
Case 22: cmp [basep+o32small], i32,  L-L-L-S, 100 blocks	Latency	645.82	158856.36
Case 33: cmp [basep+s*index+o8], i32,  L-L-L-S,  200 blocks	Latency	729.83	nan
Case 33: cmp [basep+s*index+o8], i32,  L-L-L-S,  100 blocks	Latency	475.13	740124.29
Case 55: cmp FS:[o32small], i8,  L-S-S-S, 200 blocks	Latency	489.11	nan
Case 69: cmp r,r / jc o32small;  L-L-S-S, 100 blocks	Latency	315.69	nan
Case 54: cmp [rip], i32,  L-S-S-S, 100 blocks	Latency	260.94	4020.46
Case 38: cmp [rip], reg,  L-L-L-S, 100 blocks	Latency	453.87	14039.71
Case 36: cmp [basep+s*index+o32small], i16,  L-L-L-S,  200 blocks	Latency	1055.81	nan
Case 43: cmp [rip], i8,  L-L-L-S, 200 blocks	Latency	738.07	6430.2
Case 58: cmp FS:[o32small], i32small,  L-L-S-S, 200 blocks	Latency	398.67	523821.88
Case 68: mov [basep+s*index+o32], r,  L-L-L-S, 100 blocks	Latency	1461.5	nan
Case 59: cmp FS:[o32small], i32,  L-L-S-S, 100 blocks	Latency	493.6	388507.16
Case 9: cmp [abs32],i32,  L-L-L-S, 200 blocks	Latency	504.65	182447.76
Case 41: cmp [rip small], i32small,  L-L-L-S, 200 blocks	Latency	454.27	13739.58
Case 31: cmp [basep+s*index+o8], i8,  L-L-L-S,  200 blocks	Latency	473.81	1052538.44
Case 28: cmp [basep+s*index], i16,  L-L-L-S,   200 blocks	Latency	956.53	nan
Case 39: cmp [rip small], i8,  L-L-L-S, 200 blocks	Latency	749.68	267136.95
Case 28: cmp [basep+s*index], i16,  L-L-L-S,   100 blocks	Latency	1799.39	3607744.76
Case 67: mov [basep+o32], r,  L-L-L-S, 200 blocks	Latency	1043.16	nan
Case 67: mov [basep+o32], r,  L-L-L-S, 100 blocks	Latency	1222.23	3047766.03
Case 6: cmp [abs32],r,  L-L-L-S, 200 blocks	Latency	647.5	143168.09
Case 66: cmp [basep+s*index+o32], i8,  L-L-L-S, 100 blocks	Latency	483.69	2412.87
Case 29: cmp [basep+s*index], i32,  L-L-L-S,  200 blocks	Latency	697.32	152594.98
Case 11: cmp [abs32+p],i32,  L-L-L-S, 200 blocks	Latency	481.2	119295.41
Case 39: cmp [rip small], i8,  L-L-L-S, 100 blocks	Latency	416.52	768164.6
Case 21: cmp [basep+o32small], i32small,  L-L-L-S, 200 blocks	Latency	713.58	147989.62
Case 24: cmp [basep+o32], i16,  L-L-L-S, 200 blocks	Latency	2192.88	1116822.98
Case 17: cmp [basep+o8], i16,  L-L-L-S, 100 blocks	Latency	1938.31	2273449.64
Case 66: cmp [basep+s*index+o32], i8,  L-L-L-S, 200 blocks	Latency	590.73	924875.1
Case 38: cmp [rip], reg,  L-L-L-S, 200 blocks	Latency	665.63	nan
Case 58: cmp FS:[o32small], i32small,  L-L-S-S, 100 blocks	Latency	340.15	73954.48
Case 32: cmp [basep+s*index+o8], i16,  L-L-L-S,  100 blocks	Latency	2398.33	2334195.36
Case 49: mov [basep+s*index], i32small,  L-S-S-S, 100 blocks	Latency	264.17	7161.36
Case 49: mov [basep+s*index], i32small,  L-S-S-S, 200 blocks	Latency	462.07	nan
Case 23: cmp [basep+o32], i8,  L-L-L-S, 100 blocks	Latency	405.45	47154.12
Case 35: cmp [basep+s*index+o32small], i8,  L-L-L-S,  200 blocks	Latency	668.04	142736.27
Case 53: cmp [rip], i16,  L-S-S-S, 200 blocks	Latency	495.73	607208.54
Case 26: cmp [basep+s*index], reg,  L-L-L-S,  200 blocks	Latency	736.29	9086.62
Case 52: cmp [rip], i8,  L-S-S-S, 200 blocks	Latency	408.29	nan
Case 25: cmp [basep+o32], i32,  L-L-L-S, 200 blocks	Latency	667.8	142664.12
Case 44: cmp [rip], i16,  L-L-L-S, 200 blocks	Latency	677.27	2652107.27
Case 61: roundps xmm,[rip], i8,  L-L-L-S, 200 blocks	Latency	932.79	57955.22
Case 59: cmp FS:[o32small], i32,  L-L-S-S, 200 blocks	Latency	847.18	nan
Case 8: cmp [abs32],i16,  L-L-L-S, 200 blocks	Latency	1108.96	nan
Case 52: cmp [rip], i8,  L-S-S-S, 100 blocks	Latency	408.64	nan
Case 3: mov reg64,i64, L-L-L-S, 200 blocks	Latency	1121.28	nan
Case 2: mov reg64,i64, S-L-L-L, 5 blocks	Latency	913.72	nan
Case 60: roundps xmm,[rip], i8,  L-S-S-S, 200 blocks	Latency	332.8	13082.38
Case 56: cmp FS:[o32small], i8,  L-L-L-S, 200 blocks	Latency	590.33	156315.74
Case 56: cmp FS:[o32small], i8,  L-L-L-S, 100 blocks	Latency	406.15	49439.52
Case 4: mov reg64,i64,  L-S-S-S, 200 blocks	Latency	511.73	6355.59
Case 60: roundps xmm,[rip], i8,  L-S-S-S, 100 blocks	Latency	355.33	nan
Case 61: roundps xmm,[rip], i8,  L-L-L-S, 100 blocks	Latency	1412.32	839082.88
Number of branches 10	Latency	6.06	10.35
Case 1: Tiny loop. Expect loop counter to be used	Latency	1.19	0.43
Number of branches 100	Latency	4.54	2.82
Number of branches 4	Latency	10.52	54.5
Throughput fstp [m80] + fld	Throughput	31.73	3135.58
Throughput fst [m32]	Throughput	1.67	0.0
Throughput fstp [m64] + fld	Throughput	1.07	0.0
Throughput fstp [m32] + fld	Throughput	1.07	0.0
Throughput fst [m64]	Throughput	1.16	0.09
sub r32,r32 (same register)	Latency	0.54	0.0
pcmpgtb r128,r128 (same register)	Latency	0.98	0.0
pcmpgtd r128,r128 (same register)	Latency	1.06	0.0
psubusw r128,r128 (same register) + pmullw	Latency	0.55	0.0
psubusw r65,r65 (different register) + pmullw	Latency	2.97	0.0
xor r64,r64 (different register)	Latency	1.06	0.0
psubusw r128,r128 (same register)	Latency	1.06	0.0
sbb r32,r32 (same register)	Latency	2.2	0.0
sbb r64,r64 (same register) + imul	Latency	3.97	0.0
pcmpgtb r65,r65 (same register) + pmullw	Latency	3.22	0.0
psubq r65,r65 (same register) + pmullw	Latency	0.54	0.0
psubusw r65,r65 (same register)	Latency	1.06	0.0
psubusb r65,r65 (same register)	Latency	1.06	0.0
psubusw r65,r65 (same register) + pmullw	Latency	0.54	0.0
cmp r16,r16 (different register) + imul	Latency	3.33	0.0
psubusb r128,r128 (different register) + pmullw	Latency	3.22	0.0
sub r64,r64 (different register)	Latency	0.98	0.0
psubb r128,r128 (same register) + pmullw	Latency	0.55	0.0
pcmpeqd r128,r128 (same register) + pmullw	Latency	0.5	0.0
sub r16,r16 (same register)	Latency	1.06	0.0
pcmpeqd r128,r128 (different register)	Latency	1.07	0.0
psubusb r65,r65 (different register) + pmullw	Latency	2.97	0.0
sub r8,r8 (different register) + add	Latency	1.07	0.0
psubb r65,r65 (same register) + pmullw	Latency	0.5	0.0
pxor r128,r128 (different register)	Latency	0.98	0.0
pcmpgtw r128,r128 (different register)	Latency	1.07	0.0
sbb r32,r32 (different register) + imul	Latency	2.01	0.0
psubusb r128,r128 (same register)	Latency	1.06	0.0
sbb r64,r64 (same register)	Latency	2.19	0.0
psubusb r128,r128 (same register) + pmullw	Latency	0.5	0.0
cmp r16,r16 (same register)	Latency	0.99	0.0
sub r32,r32 (different register) + imul	Latency	1.49	0.0
cmp r8,r8 (same register)	Latency	1.29	0.4
pandn r65,r65 (same register) + pmullw	Latency	3.22	0.0
pandn r65,r65 (different register) + pmullw	Latency	2.97	0.0
psubsb r65,r65 (same register) + pmullw	Latency	0.54	0.0
pcmpeqq r128,r128 (different register)	Latency	1.07	0.0
sbb r8,r8 (different register) + add	Latency	1.68	0.0
psubd r128,r128 (same register)	Latency	0.98	0.0
xor r32,r32 (same register)	Latency	0.5	0.0
pcmpeqb r128,r128 (same register) + pmullw	Latency	0.5	0.0
psubsw r128,r128 (different register) + pmullw	Latency	3.22	0.0
sub r64,r64 (same register) + imul	Latency	1.08	0.0
xor r16,r16 (same register) + imul	Latency	4.83	0.0
psubsw r65,r65 (different register)	Latency	1.06	0.0
sbb r16,r16 (different register) + imul	Latency	5.41	0.0
pcmpeqb r128,r128 (different register)	Latency	1.06	0.0
xor r64,r64 (different register) + imul	Latency	4.36	0.04
psubsb r128,r128 (same register)	Latency	0.98	0.0
pxor r65,r65 (same register) + pmullw	Latency	0.54	0.0
psubd r128,r128 (different register) + pmullw	Latency	3.29	0.04
psubusb r65,r65 (same register) + pmullw	Latency	0.54	0.0
xor r64,r64 (same register) + imul	Latency	0.99	0.0
psubw r65,r65 (different register)	Latency	1.06	0.0
psubd r128,r128 (different register)	Latency	1.07	0.0
pcmpeqw r128,r128 (same register)	Latency	1.06	0.0
pcmpeqb r128,r128 (same register)	Latency	0.98	0.0
psubw r128,r128 (same register)	Latency	0.98	0.0
psubusw r128,r128 (different register)	Latency	0.98	0.0
pcmpgtw r65,r65 (different register)	Latency	1.06	0.0
pcmpgtd r128,r128 (different register)	Latency	1.06	0.0
psubsb r65,r65 (different register)	Latency	0.98	0.0
pandn r128,r128 (different register)	Latency	1.07	0.0
sbb r32,r32 (different register)	Latency	2.19	0.0
psubusb r128,r128 (different register)	Latency	0.98	0.0
pcmpeqd r128,r128 (same register)	Latency	0.98	0.0
pcmpgtb r65,r65 (different register) + pmullw	Latency	3.22	0.0
cmp r8,r8 (same register) + add	Latency	0.99	0.0
pandn r65,r65 (different register)	Latency	0.98	0.0
psubd r128,r128 (same register) + pmullw	Latency	0.5	0.0
pandn r65,r65 (same register)	Latency	0.98	0.0
pxor r128,r128 (same register) + pmullw	Latency	0.55	0.0
psubsw r65,r65 (same register) + pmullw	Latency	0.5	0.0
pcmpgtb r65,r65 (same register)	Latency	0.98	0.0
sub r64,r64 (same register)	Latency	0.54	0.0
psubw r128,r128 (different register)	Latency	1.06	0.0
psubsw r128,r128 (same register) + pmullw	Latency	0.5	0.0
pcmpgtb r128,r128 (different register) + pmullw	Latency	3.22	0.0
psubw r65,r65 (same register) + pmullw	Latency	0.54	0.0
psubq r128,r128 (same register)	Latency	1.07	0.0
sub r8,r8 (same register) + add	Latency	1.07	0.0
cmp r8,r8 (different register)	Latency	1.07	0.0
psubq r128,r128 (different register) + pmullw	Latency	3.22	0.0
cmp r64,r64 (same register) + imul	Latency	3.23	0.0
psubq r128,r128 (same register) + pmullw	Latency	0.55	0.0
psubsw r65,r65 (different register) + pmullw	Latency	3.22	0.0
pcmpeqw r65,r65 (same register) + pmullw	Latency	0.5	0.0
psubw r128,r128 (different register) + pmullw	Latency	3.22	0.0
pcmpeqd r65,r65 (same register)	Latency	1.06	0.0
pcmpeqb r65,r65 (different register)	Latency	1.06	0.0
xor r64,r64 (same register)	Latency	0.5	0.0
pcmpeqw r128,r128 (different register) + pmullw	Latency	2.97	0.0
pcmpgtd r65,r65 (same register)	Latency	0.98	0.0
xor r8,r8 (same register)	Latency	0.98	0.0
pcmpgtb r128,r128 (different register)	Latency	1.06	0.0
pcmpeqq r128,r128 (same register)	Latency	0.99	0.0
cmp r8,r8 (different register) + add	Latency	0.99	0.0
sbb r16,r16 (same register) + imul	Latency	4.99	0.0
pcmpgtd r65,r65 (same register) + pmullw	Latency	2.97	0.0
pandn r128,r128 (same register)	Latency	0.98	0.0
cmp r16,r16 (different register)	Latency	1.07	0.0
psubsw r128,r128 (different register)	Latency	1.06	0.0
cmp r64,r64 (same register)	Latency	1.07	0.0
xor r16,r16 (different register) + imul	Latency	4.45	0.0
pcmpeqq r128,r128 (different register) + pmullw	Latency	3.22	0.0
pcmpeqw r65,r65 (same register)	Latency	0.98	0.0
psubsb r65,r65 (different register) + pmullw	Latency	2.97	0.0
cmp r64,r64 (different register)	Latency	1.07	0.0
sbb r64,r64 (different register) + imul	Latency	3.67	0.0
xor r16,r16 (different register)	Latency	0.98	0.0
sub r16,r16 (different register) + imul	Latency	4.46	0.0
sub r32,r32 (different register)	Latency	0.98	0.0
pcmpgtw r65,r65 (different register) + pmullw	Latency	3.22	0.0
pandn r128,r128 (same register) + pmullw	Latency	3.22	0.0
psubb r128,r128 (different register)	Latency	1.06	0.0
cmp r32,r32 (same register) + imul	Latency	1.33	0.0
sbb r8,r8 (same register)	Latency	2.19	0.0
psubusb r65,r65 (different register)	Latency	0.98	0.0
xor r32,r32 (same register) + imul	Latency	0.57	0.0
sub r64,r64 (different register) + imul	Latency	3.96	0.0
pcmpgtw r128,r128 (same register)	Latency	1.06	0.0
xor r8,r8 (different register)	Latency	1.06	0.0
psubd r65,r65 (same register) + pmullw	Latency	0.5	0.0
psubd r65,r65 (same register)	Latency	0.98	0.0
psubw r128,r128 (same register) + pmullw	Latency	0.67	0.24
psubq r65,r65 (same register)	Latency	1.06	0.0
sbb r8,r8 (same register) + add	Latency	1.68	0.0
psubq r65,r65 (different register) + pmullw	Latency	3.03	0.04
psubq r65,r65 (different register)	Latency	0.98	0.0
psubq r128,r128 (different register)	Latency	0.98	0.0
sub r16,r16 (different register)	Latency	0.98	0.0
pcmpeqb r128,r128 (different register) + pmullw	Latency	3.22	0.0
cmp r32,r32 (different register) + imul	Latency	1.44	0.0
pcmpeqb r65,r65 (different register) + pmullw	Latency	3.22	0.0
pxor r128,r128 (same register)	Latency	1.06	0.0
xor r32,r32 (different register) + imul	Latency	1.61	0.0
psubusw r128,r128 (different register) + pmullw	Latency	2.97	0.0
pcmpgtb r65,r65 (different register)	Latency	1.06	0.0
pcmpgtw r128,r128 (different register) + pmullw	Latency	3.22	0.0
pcmpgtd r128,r128 (different register) + pmullw	Latency	3.02	0.01
sub r8,r8 (same register)	Latency	1.07	0.0
sbb r16,r16 (same register)	Latency	2.46	0.65
sub r8,r8 (different register)	Latency	0.98	0.0
xor r8,r8 (same register) + add	Latency	0.99	0.0
psubsb r128,r128 (same register) + pmullw	Latency	0.51	0.0
pxor r65,r65 (different register) + pmullw	Latency	2.97	0.0
pcmpeqw r128,r128 (same register) + pmullw	Latency	0.55	0.0
pcmpgtb r128,r128 (same register) + pmullw	Latency	3.22	0.0
pcmpeqb r65,r65 (same register)	Latency	0.98	0.0
psubb r128,r128 (same register)	Latency	0.98	0.0
psubusw r65,r65 (different register)	Latency	0.98	0.0
psubw r65,r65 (different register) + pmullw	Latency	3.22	0.0
pcmpeqd r65,r65 (different register) + pmullw	Latency	3.22	0.0
pcmpeqb r65,r65 (same register) + pmullw	Latency	0.5	0.0
pandn r128,r128 (different register) + pmullw	Latency	2.97	0.0
pxor r65,r65 (same register)	Latency	1.06	0.0
pcmpgtw r128,r128 (same register) + pmullw	Latency	2.97	0.0
psubd r65,r65 (different register) + pmullw	Latency	3.22	0.0
xor r16,r16 (same register)	Latency	0.98	0.0
psubsb r128,r128 (different register) + pmullw	Latency	2.97	0.0
pcmpeqw r65,r65 (different register) + pmullw	Latency	3.22	0.0
psubb r65,r65 (same register)	Latency	1.06	0.0
sbb r8,r8 (different register)	Latency	2.09	0.04
pcmpeqd r65,r65 (different register)	Latency	0.98	0.0
sub r16,r16 (same register) + imul	Latency	4.83	0.0
psubb r128,r128 (different register) + pmullw	Latency	3.22	0.0
cmp r32,r32 (different register)	Latency	0.99	0.0
xor r32,r32 (different register)	Latency	1.06	0.0
psubsw r65,r65 (same register)	Latency	0.98	0.0
cmp r64,r64 (different register) + imul	Latency	2.98	0.0
xor r8,r8 (different register) + add	Latency	0.99	0.0
psubb r65,r65 (different register)	Latency	0.98	0.0
sbb r16,r16 (different register)	Latency	2.26	0.04
pcmpgtd r65,r65 (different register) + pmullw	Latency	3.22	0.0
pcmpeqw r128,r128 (different register)	Latency	0.98	0.0
pcmpgtw r65,r65 (same register)	Latency	0.98	0.0
psubb r65,r65 (different register) + pmullw	Latency	2.97	0.0
pcmpgtd r128,r128 (same register) + pmullw	Latency	2.97	0.0
psubsb r65,r65 (same register)	Latency	1.06	0.0
sbb r32,r32 (same register) + imul	Latency	2.22	0.01
cmp r16,r16 (same register) + imul	Latency	3.59	0.0
pxor r65,r65 (different register)	Latency	0.98	0.0
psubd r65,r65 (different register)	Latency	1.06	0.0
pxor r128,r128 (different register) + pmullw	Latency	2.97	0.0
sbb r64,r64 (different register)	Latency	2.02	0.0
psubsw r128,r128 (same register)	Latency	0.98	0.0
pcmpgtd r65,r65 (different register)	Latency	1.06	0.0
pcmpeqd r65,r65 (same register) + pmullw	Latency	0.54	0.0
pcmpeqd r128,r128 (different register) + pmullw	Latency	3.22	0.0
pcmpeqw r65,r65 (different register)	Latency	1.06	0.0
sub r32,r32 (same register) + imul	Latency	0.61	0.0
pcmpgtw r65,r65 (same register) + pmullw	Latency	3.29	0.04
cmp r32,r32 (same register)	Latency	1.07	0.0
pcmpeqq r128,r128 (same register) + pmullw	Latency	2.97	0.0
psubw r65,r65 (same register)	Latency	0.98	0.0
psubsb r128,r128 (different register)	Latency	0.98	0.0