InstCountCI: Update

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
This commit is contained in:
Alyssa Rosenzweig 2024-08-20 18:33:52 -04:00
parent 4c4c6e7807
commit 75644b33df
5 changed files with 343 additions and 615 deletions

View File

@ -46,13 +46,12 @@
]
},
"vmovups ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b00 0x10 256-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
@ -89,13 +88,12 @@
]
},
"vmovupd ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x10 256-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
@ -156,14 +154,13 @@
]
},
"vmovups [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b00 0x11 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vmovupd [rax], xmm0": {
@ -176,14 +173,13 @@
]
},
"vmovupd [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x11 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vmovss [rax], xmm0": {
@ -272,13 +268,12 @@
]
},
"vmovsldup ymm0, [rax]": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 4,
"Comment": [
"Map 1 0b10 0x12 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x4]",
"ldr q3, [x4, #16]",
"ldp q2, q3, [x4]",
"trn1 v16.4s, v2.4s, v2.4s",
"trn1 v2.4s, v3.4s, v3.4s",
"str q2, [x28, #16]"
@ -297,13 +292,12 @@
]
},
"vmovddup ymm0, [rax]": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 4,
"Comment": [
"Map 1 0b11 0x12 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x4]",
"ldr q3, [x4, #16]",
"ldp q2, q3, [x4]",
"dup v16.2d, v2.d[0]",
"dup v2.2d, v3.d[0]",
"str q2, [x28, #16]"
@ -340,14 +334,13 @@
]
},
"vunpcklps ymm0, ymm1, [rax]": {
"ExpectedInstructionCount": 6,
"ExpectedInstructionCount": 5,
"Comment": [
"Map 1 0b00 0x14 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"ldr q3, [x4]",
"ldr q4, [x4, #16]",
"ldp q3, q4, [x4]",
"zip1 v16.4s, v17.4s, v3.4s",
"zip1 v2.4s, v2.4s, v4.4s",
"str q2, [x28, #16]"
@ -366,14 +359,13 @@
]
},
"vunpcklpd ymm0, ymm1, [rax]": {
"ExpectedInstructionCount": 6,
"ExpectedInstructionCount": 5,
"Comment": [
"Map 1 0b01 0x14 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"ldr q3, [x4]",
"ldr q4, [x4, #16]",
"ldp q3, q4, [x4]",
"zip1 v16.2d, v17.2d, v3.2d",
"zip1 v2.2d, v2.2d, v4.2d",
"str q2, [x28, #16]"
@ -392,14 +384,13 @@
]
},
"vunpckhps ymm0, ymm1, [rax]": {
"ExpectedInstructionCount": 6,
"ExpectedInstructionCount": 5,
"Comment": [
"Map 1 0b00 0x15 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"ldr q3, [x4]",
"ldr q4, [x4, #16]",
"ldp q3, q4, [x4]",
"zip2 v16.4s, v17.4s, v3.4s",
"zip2 v2.4s, v2.4s, v4.4s",
"str q2, [x28, #16]"
@ -418,14 +409,13 @@
]
},
"vunpckhpd ymm0, ymm1, [rax]": {
"ExpectedInstructionCount": 6,
"ExpectedInstructionCount": 5,
"Comment": [
"Map 1 0b01 0x15 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"ldr q3, [x4]",
"ldr q4, [x4, #16]",
"ldp q3, q4, [x4]",
"zip2 v16.2d, v17.2d, v3.2d",
"zip2 v2.2d, v2.2d, v4.2d",
"str q2, [x28, #16]"
@ -479,13 +469,12 @@
]
},
"vmovshdup ymm0, [rax]": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 4,
"Comment": [
"Map 1 0b10 0x16 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x4]",
"ldr q3, [x4, #16]",
"ldp q2, q3, [x4]",
"trn2 v16.4s, v2.4s, v2.4s",
"trn2 v2.4s, v3.4s, v3.4s",
"str q2, [x28, #16]"
@ -1634,33 +1623,25 @@
]
},
"vzeroupper": {
"ExpectedInstructionCount": 17,
"ExpectedInstructionCount": 9,
"Comment": [
"Might be able to use DZ ZVA",
"Map 1 0b01 0x77 L=0"
],
"ExpectedArm64ASM": [
"movi v2.2d, #0x0",
"str q2, [x28, #256]",
"str q2, [x28, #240]",
"str q2, [x28, #224]",
"str q2, [x28, #208]",
"str q2, [x28, #192]",
"str q2, [x28, #176]",
"str q2, [x28, #160]",
"str q2, [x28, #144]",
"str q2, [x28, #128]",
"str q2, [x28, #112]",
"str q2, [x28, #96]",
"str q2, [x28, #80]",
"str q2, [x28, #64]",
"str q2, [x28, #48]",
"str q2, [x28, #32]",
"str q2, [x28, #16]"
"stp q2, q2, [x28, #240]",
"stp q2, q2, [x28, #208]",
"stp q2, q2, [x28, #176]",
"stp q2, q2, [x28, #144]",
"stp q2, q2, [x28, #112]",
"stp q2, q2, [x28, #80]",
"stp q2, q2, [x28, #48]",
"stp q2, q2, [x28, #16]"
]
},
"vzeroall": {
"ExpectedInstructionCount": 32,
"ExpectedInstructionCount": 24,
"Comment": [
"Might be able to use DZ ZVA",
"Map 1 0b01 0x77 L=1"
@ -1682,22 +1663,14 @@
"movi v29.2d, #0x0",
"movi v30.2d, #0x0",
"movi v31.2d, #0x0",
"str q31, [x28, #256]",
"str q31, [x28, #240]",
"str q31, [x28, #224]",
"str q31, [x28, #208]",
"str q31, [x28, #192]",
"str q31, [x28, #176]",
"str q31, [x28, #160]",
"str q31, [x28, #144]",
"str q31, [x28, #128]",
"str q31, [x28, #112]",
"str q31, [x28, #96]",
"str q31, [x28, #80]",
"str q31, [x28, #64]",
"str q31, [x28, #48]",
"str q31, [x28, #32]",
"str q31, [x28, #16]"
"stp q31, q31, [x28, #240]",
"stp q31, q31, [x28, #208]",
"stp q31, q31, [x28, #176]",
"stp q31, q31, [x28, #144]",
"stp q31, q31, [x28, #112]",
"stp q31, q31, [x28, #80]",
"stp q31, q31, [x28, #48]",
"stp q31, q31, [x28, #16]"
]
},
"vcmpps xmm0, xmm1, xmm2, 0x00": {
@ -2631,13 +2604,12 @@
]
},
"vmovaps ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b00 0x28 256-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
@ -2675,13 +2647,12 @@
]
},
"vmovapd ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x28 256-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
@ -2717,14 +2688,13 @@
]
},
"vmovaps [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b00 0x29 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vmovapd [rax], xmm0": {
@ -2737,14 +2707,13 @@
]
},
"vmovapd [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x29 256-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vcvtsi2ss xmm0, xmm1, eax": {
@ -3161,13 +3130,12 @@
]
},
"vcvtpd2ps xmm0, yword [rax]": {
"ExpectedInstructionCount": 8,
"ExpectedInstructionCount": 7,
"Comment": [
"Map 1 0b01 0x5a 128-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x4]",
"ldr q3, [x4, #16]",
"ldp q2, q3, [x4]",
"fcvtn v2.2s, v2.2d",
"fcvtn v3.2s, v3.2d",
"mov v16.16b, v2.16b",
@ -4005,47 +3973,43 @@
]
},
"vmovdqa ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x7f 128-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
"vmovdqa [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b01 0x7f 128-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vmovdqu ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b10 0x7f 128-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},
"vmovdqu [rax], ymm0": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b10 0x7f 128-bit"
],
"ExpectedArm64ASM": [
"ldr q2, [x28, #16]",
"str q16, [x4]",
"str q2, [x4, #16]"
"stp q16, q2, [x4]"
]
},
"vaddsubpd xmm0, xmm1, xmm2": {
@ -5178,13 +5142,12 @@
]
},
"vlddqu ymm0, [rax]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"Comment": [
"Map 1 0b11 0xf0 256-bit"
],
"ExpectedArm64ASM": [
"ldr q16, [x4]",
"ldr q2, [x4, #16]",
"ldp q16, q2, [x4]",
"str q2, [x28, #16]"
]
},

View File

@ -1054,101 +1054,83 @@
]
},
"vmovdqu ymm7,yword [rsi+0x60]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q23, [x10, #96]",
"ldr q2, [x10, #112]",
"ldp q23, q2, [x10, #96]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi+0x120]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q23, [x10, #288]",
"ldr q2, [x10, #304]",
"ldp q23, q2, [x10, #288]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi-0x60]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldur q23, [x10, #-96]",
"ldur q2, [x10, #-80]",
"ldp q23, q2, [x10, #-96]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi-0x400]": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"mov x20, #0xfffffffffffffc00",
"ldr q23, [x10, x20, sxtx]",
"mov x20, #0xfffffffffffffc10",
"ldr q2, [x10, x20, sxtx]",
"ldp q23, q2, [x10, #-1024]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi-0x420]": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 3,
"ExpectedArm64ASM": [
"mov x20, #0xfffffffffffffbe0",
"ldr q23, [x10, x20, sxtx]",
"mov x20, #0xfffffffffffffbf0",
"ldr q2, [x10, x20, sxtx]",
"sub x20, x10, #0x420 (1056)",
"ldp q23, q2, [x20]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi+0x3d0]": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q23, [x10, #976]",
"ldr q2, [x10, #992]",
"ldp q23, q2, [x10, #976]",
"str q2, [x28, #128]"
]
},
"vmovdqu ymm7,yword [rsi+0x400]": {
"ExpectedInstructionCount": 3,
"ExpectedArm64ASM": [
"ldr q23, [x10, #1024]",
"ldr q2, [x10, #1040]",
"add x20, x10, #0x400 (1024)",
"ldp q23, q2, [x20]",
"str q2, [x28, #128]"
]
},
"vmovdqa yword [rcx+0x60],ymm1": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"str q17, [x5, #96]",
"str q2, [x5, #112]"
"stp q17, q2, [x5, #96]"
]
},
"vmovdqa yword [rcx+0x3d0],ymm1": {
"ExpectedInstructionCount": 3,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"str q17, [x5, #976]",
"str q2, [x5, #992]"
"stp q17, q2, [x5, #976]"
]
},
"vmovdqa yword [rcx-0x3d0],ymm1": {
"ExpectedInstructionCount": 5,
"ExpectedInstructionCount": 2,
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"mov x20, #0xfffffffffffffc30",
"str q17, [x5, x20, sxtx]",
"mov x20, #0xfffffffffffffc40",
"str q2, [x5, x20, sxtx]"
"stp q17, q2, [x5, #-976]"
]
},
"vmovdqa yword [rcx+rsi-0x3d0],ymm1": {
"ExpectedInstructionCount": 7,
"ExpectedInstructionCount": 3,
"ExpectedArm64ASM": [
"ldr q2, [x28, #32]",
"add x20, x5, x10",
"mov x21, #0xfffffffffffffc30",
"str q17, [x20, x21, sxtx]",
"add x20, x5, x10",
"mov x21, #0xfffffffffffffc40",
"str q2, [x20, x21, sxtx]"
"stp q17, q2, [x20, #-976]"
]
}
}

View File

@ -429,7 +429,7 @@
]
},
"glibc AVX memcpy block 1": {
"ExpectedInstructionCount": 43,
"ExpectedInstructionCount": 26,
"x86Insts": [
"vmovdqu ymm5,yword [rsi+0x20]",
"vmovdqu ymm6,yword [rsi+0x40]",
@ -453,53 +453,36 @@
"cmp rdi,rcx"
],
"ExpectedArm64ASM": [
"ldr q21, [x10, #32]",
"ldr q2, [x10, #48]",
"ldr q22, [x10, #64]",
"ldr q3, [x10, #80]",
"ldp q21, q2, [x10, #32]",
"ldp q22, q3, [x10, #64]",
"sub x20, x11, #0x81 (129)",
"add x5, x20, x6",
"ldr q23, [x10, #96]",
"ldr q4, [x10, #112]",
"ldp q23, q4, [x10, #96]",
"add x20, x10, x6",
"ldur q24, [x20, #-32]",
"add x20, x10, x6",
"ldur q5, [x20, #-16]",
"ldp q24, q5, [x20, #-32]",
"sub x10, x10, x11",
"and x5, x5, #0xffffffffffffffe0",
"add x10, x10, x5",
"ldr q17, [x10, #96]",
"ldr q6, [x10, #112]",
"ldr q18, [x10, #64]",
"ldr q7, [x10, #80]",
"ldr q19, [x10, #32]",
"ldr q8, [x10, #48]",
"ldr q20, [x10]",
"ldr q9, [x10, #16]",
"ldp q17, q6, [x10, #96]",
"ldp q18, q7, [x10, #64]",
"ldp q19, q8, [x10, #32]",
"ldp q20, q9, [x10]",
"sub x10, x10, #0x80 (128)",
"str q17, [x5, #96]",
"str q6, [x5, #112]",
"str q18, [x5, #64]",
"str q7, [x5, #80]",
"str q19, [x5, #32]",
"str q8, [x5, #48]",
"str q20, [x5]",
"str q9, [x5, #16]",
"stp q17, q6, [x5, #96]",
"stp q18, q7, [x5, #64]",
"stp q19, q8, [x5, #32]",
"stp q20, q9, [x5]",
"sub x5, x5, #0x80 (128)",
"eor w27, w11, w5",
"subs x26, x11, x5",
"str q5, [x28, #144]",
"str q4, [x28, #128]",
"str q3, [x28, #112]",
"str q2, [x28, #96]",
"str q9, [x28, #80]",
"str q8, [x28, #64]",
"str q7, [x28, #48]",
"str q6, [x28, #32]"
"stp q4, q5, [x28, #128]",
"stp q2, q3, [x28, #96]",
"stp q8, q9, [x28, #64]",
"stp q6, q7, [x28, #32]"
]
},
"glibc AVX memcpy block 2": {
"ExpectedInstructionCount": 51,
"ExpectedInstructionCount": 31,
"x86Insts": [
"vmovdqu ymm5,yword [rsi+rdx*1-0x20]",
"vmovdqu ymm6,yword [rsi+rdx*1-0x40]",
@ -526,56 +509,36 @@
],
"ExpectedArm64ASM": [
"add x20, x10, x6",
"ldur q21, [x20, #-32]",
"ldp q21, q2, [x20, #-32]",
"add x20, x10, x6",
"ldur q2, [x20, #-16]",
"add x20, x10, x6",
"ldur q22, [x20, #-64]",
"add x20, x10, x6",
"ldur q3, [x20, #-48]",
"ldp q22, q3, [x20, #-64]",
"mov x5, x11",
"orr x11, x11, #0x1f",
"add x20, x10, x6",
"ldur q23, [x20, #-96]",
"ldp q23, q4, [x20, #-96]",
"add x20, x10, x6",
"ldur q4, [x20, #-80]",
"add x20, x10, x6",
"ldur q24, [x20, #-128]",
"add x20, x10, x6",
"ldur q5, [x20, #-112]",
"ldp q24, q5, [x20, #-128]",
"sub x10, x10, x5",
"add x11, x11, #0x1 (1)",
"add x10, x10, x11",
"sub x20, x5, #0x80 (128)",
"add x6, x20, x6",
"ldr q17, [x10]",
"ldr q6, [x10, #16]",
"ldr q18, [x10, #32]",
"ldr q7, [x10, #48]",
"ldr q19, [x10, #64]",
"ldr q8, [x10, #80]",
"ldr q20, [x10, #96]",
"ldr q9, [x10, #112]",
"ldp q17, q6, [x10]",
"ldp q18, q7, [x10, #32]",
"ldp q19, q8, [x10, #64]",
"ldp q20, q9, [x10, #96]",
"add x10, x10, #0x80 (128)",
"str q17, [x11]",
"str q6, [x11, #16]",
"str q18, [x11, #32]",
"str q7, [x11, #48]",
"str q19, [x11, #64]",
"str q8, [x11, #80]",
"str q20, [x11, #96]",
"str q9, [x11, #112]",
"stp q17, q6, [x11]",
"stp q18, q7, [x11, #32]",
"stp q19, q8, [x11, #64]",
"stp q20, q9, [x11, #96]",
"add x11, x11, #0x80 (128)",
"eor w27, w6, w11",
"subs x26, x6, x11",
"str q5, [x28, #144]",
"str q4, [x28, #128]",
"str q3, [x28, #112]",
"str q2, [x28, #96]",
"str q9, [x28, #80]",
"str q8, [x28, #64]",
"str q7, [x28, #48]",
"str q6, [x28, #32]"
"stp q4, q5, [x28, #128]",
"stp q2, q3, [x28, #96]",
"stp q8, q9, [x28, #64]",
"stp q6, q7, [x28, #32]"
]
},
"bytemark strsift": {

View File

@ -1216,7 +1216,7 @@
]
},
"fxsave [rax]": {
"ExpectedInstructionCount": 52,
"ExpectedInstructionCount": 39,
"Comment": "GROUP15 0x0F 0xAE /0",
"ExpectedArm64ASM": [
"ldrh w20, [x28, #1296]",
@ -1235,42 +1235,29 @@
"ldrb w20, [x28, #1298]",
"strb w20, [x4, #4]",
"ldr q2, [x28, #1040]",
"str q2, [x4, #32]",
"ldr q2, [x28, #1056]",
"str q2, [x4, #48]",
"ldr q3, [x28, #1056]",
"stp q2, q3, [x4, #32]",
"ldr q2, [x28, #1072]",
"str q2, [x4, #64]",
"ldr q2, [x28, #1088]",
"str q2, [x4, #80]",
"ldr q3, [x28, #1088]",
"stp q2, q3, [x4, #64]",
"ldr q2, [x28, #1104]",
"str q2, [x4, #96]",
"ldr q2, [x28, #1120]",
"str q2, [x4, #112]",
"ldr q3, [x28, #1120]",
"stp q2, q3, [x4, #96]",
"ldr q2, [x28, #1136]",
"str q2, [x4, #128]",
"ldr q2, [x28, #1152]",
"str q2, [x4, #144]",
"str q16, [x4, #160]",
"str q17, [x4, #176]",
"str q18, [x4, #192]",
"str q19, [x4, #208]",
"str q20, [x4, #224]",
"str q21, [x4, #240]",
"str q22, [x4, #256]",
"str q23, [x4, #272]",
"str q24, [x4, #288]",
"str q25, [x4, #304]",
"str q26, [x4, #320]",
"str q27, [x4, #336]",
"str q28, [x4, #352]",
"str q29, [x4, #368]",
"str q30, [x4, #384]",
"str q31, [x4, #400]",
"ldr q3, [x28, #1152]",
"stp q2, q3, [x4, #128]",
"stp q16, q17, [x4, #160]",
"stp q18, q19, [x4, #192]",
"stp q20, q21, [x4, #224]",
"stp q22, q23, [x4, #256]",
"stp q24, q25, [x4, #288]",
"stp q26, q27, [x4, #320]",
"stp q28, q29, [x4, #352]",
"stp q30, q31, [x4, #384]",
"ldr w20, [x28, #940]",
"and w20, w20, #0xffc0",
"str w20, [x4, #24]",
"mov w20, #0xffff",
"str w20, [x4, #28]"
"mov w21, #0xffff",
"stp w20, w21, [x4, #24]"
]
},
"rdfsbase eax": {
@ -1288,7 +1275,7 @@
]
},
"fxrstor [rax]": {
"ExpectedInstructionCount": 58,
"ExpectedInstructionCount": 46,
"Comment": "GROUP15 0x0F 0xAE /1",
"ExpectedArm64ASM": [
"ldrh w20, [x4]",
@ -1305,30 +1292,18 @@
"strb w23, [x28, #1018]",
"strb w20, [x28, #1022]",
"ldrb w20, [x4, #4]",
"ldr q2, [x4, #32]",
"ldr q3, [x4, #48]",
"ldr q4, [x4, #64]",
"ldr q5, [x4, #80]",
"ldr q6, [x4, #96]",
"ldr q7, [x4, #112]",
"ldr q8, [x4, #128]",
"ldr q9, [x4, #144]",
"ldr q16, [x4, #160]",
"ldr q17, [x4, #176]",
"ldr q18, [x4, #192]",
"ldr q19, [x4, #208]",
"ldr q20, [x4, #224]",
"ldr q21, [x4, #240]",
"ldr q22, [x4, #256]",
"ldr q23, [x4, #272]",
"ldr q24, [x4, #288]",
"ldr q25, [x4, #304]",
"ldr q26, [x4, #320]",
"ldr q27, [x4, #336]",
"ldr q28, [x4, #352]",
"ldr q29, [x4, #368]",
"ldr q30, [x4, #384]",
"ldr q31, [x4, #400]",
"ldp q2, q3, [x4, #32]",
"ldp q4, q5, [x4, #64]",
"ldp q6, q7, [x4, #96]",
"ldp q8, q9, [x4, #128]",
"ldp q16, q17, [x4, #160]",
"ldp q18, q19, [x4, #192]",
"ldp q20, q21, [x4, #224]",
"ldp q22, q23, [x4, #256]",
"ldp q24, q25, [x4, #288]",
"ldp q26, q27, [x4, #320]",
"ldp q28, q29, [x4, #352]",
"ldp q30, q31, [x4, #384]",
"ldr w21, [x4, #24]",
"and w21, w21, #0xffc0",
"str w21, [x28, #940]",
@ -1422,12 +1397,12 @@
]
},
"xsave [rax]": {
"ExpectedInstructionCount": 98,
"ExpectedInstructionCount": 69,
"Comment": "GROUP15 0x0F 0xAE /4",
"ExpectedArm64ASM": [
"ubfx x20, x4, #0, #1",
"cbnz x20, #+0x8",
"b #+0x80",
"b #+0x70",
"ldrh w20, [x28, #1296]",
"strh w20, [x4]",
"ldrb w20, [x28, #1019]",
@ -1444,83 +1419,54 @@
"ldrb w20, [x28, #1298]",
"strb w20, [x4, #4]",
"ldr q2, [x28, #1040]",
"str q2, [x4, #32]",
"ldr q2, [x28, #1056]",
"str q2, [x4, #48]",
"ldr q3, [x28, #1056]",
"stp q2, q3, [x4, #32]",
"ldr q2, [x28, #1072]",
"str q2, [x4, #64]",
"ldr q2, [x28, #1088]",
"str q2, [x4, #80]",
"ldr q3, [x28, #1088]",
"stp q2, q3, [x4, #64]",
"ldr q2, [x28, #1104]",
"str q2, [x4, #96]",
"ldr q2, [x28, #1120]",
"str q2, [x4, #112]",
"ldr q3, [x28, #1120]",
"stp q2, q3, [x4, #96]",
"ldr q2, [x28, #1136]",
"str q2, [x4, #128]",
"ldr q2, [x28, #1152]",
"str q2, [x4, #144]",
"ldr q3, [x28, #1152]",
"stp q2, q3, [x4, #128]",
"ubfx x20, x4, #1, #1",
"cbnz x20, #+0x8",
"b #+0x44",
"str q16, [x4, #160]",
"str q17, [x4, #176]",
"str q18, [x4, #192]",
"str q19, [x4, #208]",
"str q20, [x4, #224]",
"str q21, [x4, #240]",
"str q22, [x4, #256]",
"str q23, [x4, #272]",
"str q24, [x4, #288]",
"str q25, [x4, #304]",
"str q26, [x4, #320]",
"str q27, [x4, #336]",
"str q28, [x4, #352]",
"str q29, [x4, #368]",
"str q30, [x4, #384]",
"str q31, [x4, #400]",
"b #+0x24",
"stp q16, q17, [x4, #160]",
"stp q18, q19, [x4, #192]",
"stp q20, q21, [x4, #224]",
"stp q22, q23, [x4, #256]",
"stp q24, q25, [x4, #288]",
"stp q26, q27, [x4, #320]",
"stp q28, q29, [x4, #352]",
"stp q30, q31, [x4, #384]",
"ubfx x20, x4, #2, #1",
"cbnz x20, #+0x8",
"b #+0x84",
"ldr q2, [x28, #16]",
"str q2, [x4, #576]",
"ldr q2, [x28, #32]",
"str q2, [x4, #592]",
"ldr q2, [x28, #48]",
"str q2, [x4, #608]",
"ldr q2, [x28, #64]",
"str q2, [x4, #624]",
"ldr q2, [x28, #80]",
"str q2, [x4, #640]",
"ldr q2, [x28, #96]",
"str q2, [x4, #656]",
"ldr q2, [x28, #112]",
"str q2, [x4, #672]",
"ldr q2, [x28, #128]",
"str q2, [x4, #688]",
"ldr q2, [x28, #144]",
"str q2, [x4, #704]",
"ldr q2, [x28, #160]",
"str q2, [x4, #720]",
"ldr q2, [x28, #176]",
"str q2, [x4, #736]",
"ldr q2, [x28, #192]",
"str q2, [x4, #752]",
"ldr q2, [x28, #208]",
"str q2, [x4, #768]",
"ldr q2, [x28, #224]",
"str q2, [x4, #784]",
"ldr q2, [x28, #240]",
"str q2, [x4, #800]",
"ldr q2, [x28, #256]",
"str q2, [x4, #816]",
"b #+0x44",
"ldp q2, q3, [x28, #16]",
"stp q2, q3, [x4, #576]",
"ldp q2, q3, [x28, #48]",
"stp q2, q3, [x4, #608]",
"ldp q2, q3, [x28, #80]",
"stp q2, q3, [x4, #640]",
"ldp q2, q3, [x28, #112]",
"stp q2, q3, [x4, #672]",
"ldp q2, q3, [x28, #144]",
"stp q2, q3, [x4, #704]",
"ldp q2, q3, [x28, #176]",
"stp q2, q3, [x4, #736]",
"ldp q2, q3, [x28, #208]",
"stp q2, q3, [x4, #768]",
"ldp q2, q3, [x28, #240]",
"stp q2, q3, [x4, #800]",
"ubfx x20, x4, #1, #2",
"cbnz x20, #+0x8",
"b #+0x18",
"b #+0x14",
"ldr w20, [x28, #940]",
"and w20, w20, #0xffc0",
"str w20, [x4, #24]",
"mov w20, #0xffff",
"str w20, [x4, #28]",
"mov w21, #0xffff",
"stp w20, w21, [x4, #24]",
"ubfx x20, x4, #0, #3",
"str x20, [x4, #512]"
]
@ -1533,14 +1479,14 @@
]
},
"xrstor [rax]": {
"ExpectedInstructionCount": 166,
"ExpectedInstructionCount": 130,
"Comment": "GROUP15 0x0F 0xAE /5",
"ExpectedArm64ASM": [
"sub sp, sp, #0x40 (64)",
"ldr x20, [x4, #512]",
"ubfx x20, x20, #0, #1",
"cbnz x20, #+0x8",
"b #+0x84",
"b #+0x74",
"ldrh w20, [x4]",
"strh w20, [x28, #1296]",
"ldrh w20, [x4, #2]",
@ -1555,14 +1501,10 @@
"strb w23, [x28, #1018]",
"strb w20, [x28, #1022]",
"ldrb w20, [x4, #4]",
"ldr q2, [x4, #32]",
"ldr q3, [x4, #48]",
"ldr q4, [x4, #64]",
"ldr q5, [x4, #80]",
"ldr q6, [x4, #96]",
"ldr q7, [x4, #112]",
"ldr q8, [x4, #128]",
"ldr q9, [x4, #144]",
"ldp q2, q3, [x4, #32]",
"ldp q4, q5, [x4, #64]",
"ldp q6, q7, [x4, #96]",
"ldp q8, q9, [x4, #128]",
"strb w20, [x28, #1298]",
"str q9, [x28, #1152]",
"str q8, [x28, #1136]",
@ -1593,23 +1535,15 @@
"ldr x20, [x4, #512]",
"ubfx x20, x20, #1, #1",
"cbnz x20, #+0x8",
"b #+0x48",
"ldr q16, [x4, #160]",
"ldr q17, [x4, #176]",
"ldr q18, [x4, #192]",
"ldr q19, [x4, #208]",
"ldr q20, [x4, #224]",
"ldr q21, [x4, #240]",
"ldr q22, [x4, #256]",
"ldr q23, [x4, #272]",
"ldr q24, [x4, #288]",
"ldr q25, [x4, #304]",
"ldr q26, [x4, #320]",
"ldr q27, [x4, #336]",
"ldr q28, [x4, #352]",
"ldr q29, [x4, #368]",
"ldr q30, [x4, #384]",
"ldr q31, [x4, #400]",
"b #+0x28",
"ldp q16, q17, [x4, #160]",
"ldp q18, q19, [x4, #192]",
"ldp q20, q21, [x4, #224]",
"ldp q22, q23, [x4, #256]",
"ldp q24, q25, [x4, #288]",
"ldp q26, q27, [x4, #320]",
"ldp q28, q29, [x4, #352]",
"ldp q30, q31, [x4, #384]",
"b #+0x44",
"movi v31.2d, #0x0",
"mov v30.16b, v31.16b",
@ -1630,61 +1564,37 @@
"ldr x20, [x4, #512]",
"ubfx x20, x20, #2, #1",
"cbnz x20, #+0x8",
"b #+0x98",
"ldr q2, [x4, #576]",
"ldr q3, [x4, #592]",
"ldr q4, [x4, #608]",
"ldr q5, [x4, #624]",
"ldr q6, [x4, #640]",
"ldr q7, [x4, #656]",
"ldr q8, [x4, #672]",
"ldr q9, [x4, #688]",
"ldr q10, [x4, #704]",
"ldr q11, [x4, #720]",
"ldr q12, [x4, #736]",
"ldr q13, [x4, #752]",
"ldr q14, [x4, #768]",
"ldr q15, [x4, #784]",
"b #+0x58",
"ldp q2, q3, [x4, #576]",
"ldp q4, q5, [x4, #608]",
"ldp q6, q7, [x4, #640]",
"ldp q8, q9, [x4, #672]",
"ldp q10, q11, [x4, #704]",
"ldp q12, q13, [x4, #736]",
"ldp q14, q15, [x4, #768]",
"str q2, [sp]",
"ldr q2, [x4, #800]",
"str q3, [sp, #32]",
"ldr q3, [x4, #816]",
"str q3, [x28, #256]",
"str q2, [x28, #240]",
"str q15, [x28, #224]",
"str q14, [x28, #208]",
"str q13, [x28, #192]",
"str q12, [x28, #176]",
"str q11, [x28, #160]",
"str q10, [x28, #144]",
"str q9, [x28, #128]",
"str q8, [x28, #112]",
"str q7, [x28, #96]",
"str q6, [x28, #80]",
"str q5, [x28, #64]",
"str q4, [x28, #48]",
"ldr q2, [sp, #32]",
"str q2, [x28, #32]",
"ldp q2, q3, [x4, #800]",
"stp q2, q3, [x28, #240]",
"stp q14, q15, [x28, #208]",
"stp q12, q13, [x28, #176]",
"stp q10, q11, [x28, #144]",
"stp q8, q9, [x28, #112]",
"stp q6, q7, [x28, #80]",
"stp q4, q5, [x28, #48]",
"ldr q2, [sp]",
"str q2, [x28, #16]",
"b #+0x48",
"ldr q3, [sp, #32]",
"stp q2, q3, [x28, #16]",
"b #+0x28",
"movi v2.2d, #0x0",
"str q2, [x28, #256]",
"str q2, [x28, #240]",
"str q2, [x28, #224]",
"str q2, [x28, #208]",
"str q2, [x28, #192]",
"str q2, [x28, #176]",
"str q2, [x28, #160]",
"str q2, [x28, #144]",
"str q2, [x28, #128]",
"str q2, [x28, #112]",
"str q2, [x28, #96]",
"str q2, [x28, #80]",
"str q2, [x28, #64]",
"str q2, [x28, #48]",
"str q2, [x28, #32]",
"str q2, [x28, #16]",
"stp q2, q2, [x28, #240]",
"stp q2, q2, [x28, #208]",
"stp q2, q2, [x28, #176]",
"stp q2, q2, [x28, #144]",
"stp q2, q2, [x28, #112]",
"stp q2, q2, [x28, #80]",
"stp q2, q2, [x28, #48]",
"stp q2, q2, [x28, #16]",
"ldr x20, [x4, #512]",
"ubfx x20, x20, #1, #2",
"cbnz x20, #+0x8",

View File

@ -1406,7 +1406,7 @@
]
},
"fxsave [rax]": {
"ExpectedInstructionCount": 52,
"ExpectedInstructionCount": 39,
"Comment": "GROUP15 0x0F 0xAE /0",
"ExpectedArm64ASM": [
"ldrh w20, [x28, #1296]",
@ -1425,42 +1425,29 @@
"ldrb w20, [x28, #1298]",
"strb w20, [x4, #4]",
"ldr q2, [x28, #1040]",
"str q2, [x4, #32]",
"ldr q2, [x28, #1056]",
"str q2, [x4, #48]",
"ldr q3, [x28, #1056]",
"stp q2, q3, [x4, #32]",
"ldr q2, [x28, #1072]",
"str q2, [x4, #64]",
"ldr q2, [x28, #1088]",
"str q2, [x4, #80]",
"ldr q3, [x28, #1088]",
"stp q2, q3, [x4, #64]",
"ldr q2, [x28, #1104]",
"str q2, [x4, #96]",
"ldr q2, [x28, #1120]",
"str q2, [x4, #112]",
"ldr q3, [x28, #1120]",
"stp q2, q3, [x4, #96]",
"ldr q2, [x28, #1136]",
"str q2, [x4, #128]",
"ldr q2, [x28, #1152]",
"str q2, [x4, #144]",
"str q16, [x4, #160]",
"str q17, [x4, #176]",
"str q18, [x4, #192]",
"str q19, [x4, #208]",
"str q20, [x4, #224]",
"str q21, [x4, #240]",
"str q22, [x4, #256]",
"str q23, [x4, #272]",
"str q24, [x4, #288]",
"str q25, [x4, #304]",
"str q26, [x4, #320]",
"str q27, [x4, #336]",
"str q28, [x4, #352]",
"str q29, [x4, #368]",
"str q30, [x4, #384]",
"str q31, [x4, #400]",
"ldr q3, [x28, #1152]",
"stp q2, q3, [x4, #128]",
"stp q16, q17, [x4, #160]",
"stp q18, q19, [x4, #192]",
"stp q20, q21, [x4, #224]",
"stp q22, q23, [x4, #256]",
"stp q24, q25, [x4, #288]",
"stp q26, q27, [x4, #320]",
"stp q28, q29, [x4, #352]",
"stp q30, q31, [x4, #384]",
"ldr w20, [x28, #940]",
"and w20, w20, #0xffc0",
"str w20, [x4, #24]",
"mov w20, #0xffff",
"str w20, [x4, #28]"
"mov w21, #0xffff",
"stp w20, w21, [x4, #24]"
]
},
"rdfsbase eax": {
@ -1478,7 +1465,7 @@
]
},
"fxrstor [rax]": {
"ExpectedInstructionCount": 58,
"ExpectedInstructionCount": 46,
"Comment": "GROUP15 0x0F 0xAE /1",
"ExpectedArm64ASM": [
"ldrh w20, [x4]",
@ -1495,30 +1482,18 @@
"strb w23, [x28, #1018]",
"strb w20, [x28, #1022]",
"ldrb w20, [x4, #4]",
"ldr q2, [x4, #32]",
"ldr q3, [x4, #48]",
"ldr q4, [x4, #64]",
"ldr q5, [x4, #80]",
"ldr q6, [x4, #96]",
"ldr q7, [x4, #112]",
"ldr q8, [x4, #128]",
"ldr q9, [x4, #144]",
"ldr q16, [x4, #160]",
"ldr q17, [x4, #176]",
"ldr q18, [x4, #192]",
"ldr q19, [x4, #208]",
"ldr q20, [x4, #224]",
"ldr q21, [x4, #240]",
"ldr q22, [x4, #256]",
"ldr q23, [x4, #272]",
"ldr q24, [x4, #288]",
"ldr q25, [x4, #304]",
"ldr q26, [x4, #320]",
"ldr q27, [x4, #336]",
"ldr q28, [x4, #352]",
"ldr q29, [x4, #368]",
"ldr q30, [x4, #384]",
"ldr q31, [x4, #400]",
"ldp q2, q3, [x4, #32]",
"ldp q4, q5, [x4, #64]",
"ldp q6, q7, [x4, #96]",
"ldp q8, q9, [x4, #128]",
"ldp q16, q17, [x4, #160]",
"ldp q18, q19, [x4, #192]",
"ldp q20, q21, [x4, #224]",
"ldp q22, q23, [x4, #256]",
"ldp q24, q25, [x4, #288]",
"ldp q26, q27, [x4, #320]",
"ldp q28, q29, [x4, #352]",
"ldp q30, q31, [x4, #384]",
"ldr w21, [x4, #24]",
"and w21, w21, #0xffc0",
"str w21, [x28, #940]",
@ -1612,12 +1587,12 @@
]
},
"xsave [rax]": {
"ExpectedInstructionCount": 98,
"ExpectedInstructionCount": 69,
"Comment": "GROUP15 0x0F 0xAE /4",
"ExpectedArm64ASM": [
"ubfx x20, x4, #0, #1",
"cbnz x20, #+0x8",
"b #+0x80",
"b #+0x70",
"ldrh w20, [x28, #1296]",
"strh w20, [x4]",
"ldrb w20, [x28, #1019]",
@ -1634,83 +1609,54 @@
"ldrb w20, [x28, #1298]",
"strb w20, [x4, #4]",
"ldr q2, [x28, #1040]",
"str q2, [x4, #32]",
"ldr q2, [x28, #1056]",
"str q2, [x4, #48]",
"ldr q3, [x28, #1056]",
"stp q2, q3, [x4, #32]",
"ldr q2, [x28, #1072]",
"str q2, [x4, #64]",
"ldr q2, [x28, #1088]",
"str q2, [x4, #80]",
"ldr q3, [x28, #1088]",
"stp q2, q3, [x4, #64]",
"ldr q2, [x28, #1104]",
"str q2, [x4, #96]",
"ldr q2, [x28, #1120]",
"str q2, [x4, #112]",
"ldr q3, [x28, #1120]",
"stp q2, q3, [x4, #96]",
"ldr q2, [x28, #1136]",
"str q2, [x4, #128]",
"ldr q2, [x28, #1152]",
"str q2, [x4, #144]",
"ldr q3, [x28, #1152]",
"stp q2, q3, [x4, #128]",
"ubfx x20, x4, #1, #1",
"cbnz x20, #+0x8",
"b #+0x44",
"str q16, [x4, #160]",
"str q17, [x4, #176]",
"str q18, [x4, #192]",
"str q19, [x4, #208]",
"str q20, [x4, #224]",
"str q21, [x4, #240]",
"str q22, [x4, #256]",
"str q23, [x4, #272]",
"str q24, [x4, #288]",
"str q25, [x4, #304]",
"str q26, [x4, #320]",
"str q27, [x4, #336]",
"str q28, [x4, #352]",
"str q29, [x4, #368]",
"str q30, [x4, #384]",
"str q31, [x4, #400]",
"b #+0x24",
"stp q16, q17, [x4, #160]",
"stp q18, q19, [x4, #192]",
"stp q20, q21, [x4, #224]",
"stp q22, q23, [x4, #256]",
"stp q24, q25, [x4, #288]",
"stp q26, q27, [x4, #320]",
"stp q28, q29, [x4, #352]",
"stp q30, q31, [x4, #384]",
"ubfx x20, x4, #2, #1",
"cbnz x20, #+0x8",
"b #+0x84",
"ldr q2, [x28, #16]",
"str q2, [x4, #576]",
"ldr q2, [x28, #32]",
"str q2, [x4, #592]",
"ldr q2, [x28, #48]",
"str q2, [x4, #608]",
"ldr q2, [x28, #64]",
"str q2, [x4, #624]",
"ldr q2, [x28, #80]",
"str q2, [x4, #640]",
"ldr q2, [x28, #96]",
"str q2, [x4, #656]",
"ldr q2, [x28, #112]",
"str q2, [x4, #672]",
"ldr q2, [x28, #128]",
"str q2, [x4, #688]",
"ldr q2, [x28, #144]",
"str q2, [x4, #704]",
"ldr q2, [x28, #160]",
"str q2, [x4, #720]",
"ldr q2, [x28, #176]",
"str q2, [x4, #736]",
"ldr q2, [x28, #192]",
"str q2, [x4, #752]",
"ldr q2, [x28, #208]",
"str q2, [x4, #768]",
"ldr q2, [x28, #224]",
"str q2, [x4, #784]",
"ldr q2, [x28, #240]",
"str q2, [x4, #800]",
"ldr q2, [x28, #256]",
"str q2, [x4, #816]",
"b #+0x44",
"ldp q2, q3, [x28, #16]",
"stp q2, q3, [x4, #576]",
"ldp q2, q3, [x28, #48]",
"stp q2, q3, [x4, #608]",
"ldp q2, q3, [x28, #80]",
"stp q2, q3, [x4, #640]",
"ldp q2, q3, [x28, #112]",
"stp q2, q3, [x4, #672]",
"ldp q2, q3, [x28, #144]",
"stp q2, q3, [x4, #704]",
"ldp q2, q3, [x28, #176]",
"stp q2, q3, [x4, #736]",
"ldp q2, q3, [x28, #208]",
"stp q2, q3, [x4, #768]",
"ldp q2, q3, [x28, #240]",
"stp q2, q3, [x4, #800]",
"ubfx x20, x4, #1, #2",
"cbnz x20, #+0x8",
"b #+0x18",
"b #+0x14",
"ldr w20, [x28, #940]",
"and w20, w20, #0xffc0",
"str w20, [x4, #24]",
"mov w20, #0xffff",
"str w20, [x4, #28]",
"mov w21, #0xffff",
"stp w20, w21, [x4, #24]",
"ubfx x20, x4, #0, #3",
"str x20, [x4, #512]"
]
@ -1723,14 +1669,14 @@
]
},
"xrstor [rax]": {
"ExpectedInstructionCount": 166,
"ExpectedInstructionCount": 130,
"Comment": "GROUP15 0x0F 0xAE /5",
"ExpectedArm64ASM": [
"sub sp, sp, #0x40 (64)",
"ldr x20, [x4, #512]",
"ubfx x20, x20, #0, #1",
"cbnz x20, #+0x8",
"b #+0x84",
"b #+0x74",
"ldrh w20, [x4]",
"strh w20, [x28, #1296]",
"ldrh w20, [x4, #2]",
@ -1745,14 +1691,10 @@
"strb w23, [x28, #1018]",
"strb w20, [x28, #1022]",
"ldrb w20, [x4, #4]",
"ldr q2, [x4, #32]",
"ldr q3, [x4, #48]",
"ldr q4, [x4, #64]",
"ldr q5, [x4, #80]",
"ldr q6, [x4, #96]",
"ldr q7, [x4, #112]",
"ldr q8, [x4, #128]",
"ldr q9, [x4, #144]",
"ldp q2, q3, [x4, #32]",
"ldp q4, q5, [x4, #64]",
"ldp q6, q7, [x4, #96]",
"ldp q8, q9, [x4, #128]",
"strb w20, [x28, #1298]",
"str q9, [x28, #1152]",
"str q8, [x28, #1136]",
@ -1783,23 +1725,15 @@
"ldr x20, [x4, #512]",
"ubfx x20, x20, #1, #1",
"cbnz x20, #+0x8",
"b #+0x48",
"ldr q16, [x4, #160]",
"ldr q17, [x4, #176]",
"ldr q18, [x4, #192]",
"ldr q19, [x4, #208]",
"ldr q20, [x4, #224]",
"ldr q21, [x4, #240]",
"ldr q22, [x4, #256]",
"ldr q23, [x4, #272]",
"ldr q24, [x4, #288]",
"ldr q25, [x4, #304]",
"ldr q26, [x4, #320]",
"ldr q27, [x4, #336]",
"ldr q28, [x4, #352]",
"ldr q29, [x4, #368]",
"ldr q30, [x4, #384]",
"ldr q31, [x4, #400]",
"b #+0x28",
"ldp q16, q17, [x4, #160]",
"ldp q18, q19, [x4, #192]",
"ldp q20, q21, [x4, #224]",
"ldp q22, q23, [x4, #256]",
"ldp q24, q25, [x4, #288]",
"ldp q26, q27, [x4, #320]",
"ldp q28, q29, [x4, #352]",
"ldp q30, q31, [x4, #384]",
"b #+0x44",
"movi v31.2d, #0x0",
"mov v30.16b, v31.16b",
@ -1820,61 +1754,37 @@
"ldr x20, [x4, #512]",
"ubfx x20, x20, #2, #1",
"cbnz x20, #+0x8",
"b #+0x98",
"ldr q2, [x4, #576]",
"ldr q3, [x4, #592]",
"ldr q4, [x4, #608]",
"ldr q5, [x4, #624]",
"ldr q6, [x4, #640]",
"ldr q7, [x4, #656]",
"ldr q8, [x4, #672]",
"ldr q9, [x4, #688]",
"ldr q10, [x4, #704]",
"ldr q11, [x4, #720]",
"ldr q12, [x4, #736]",
"ldr q13, [x4, #752]",
"ldr q14, [x4, #768]",
"ldr q15, [x4, #784]",
"b #+0x58",
"ldp q2, q3, [x4, #576]",
"ldp q4, q5, [x4, #608]",
"ldp q6, q7, [x4, #640]",
"ldp q8, q9, [x4, #672]",
"ldp q10, q11, [x4, #704]",
"ldp q12, q13, [x4, #736]",
"ldp q14, q15, [x4, #768]",
"str q2, [sp]",
"ldr q2, [x4, #800]",
"str q3, [sp, #32]",
"ldr q3, [x4, #816]",
"str q3, [x28, #256]",
"str q2, [x28, #240]",
"str q15, [x28, #224]",
"str q14, [x28, #208]",
"str q13, [x28, #192]",
"str q12, [x28, #176]",
"str q11, [x28, #160]",
"str q10, [x28, #144]",
"str q9, [x28, #128]",
"str q8, [x28, #112]",
"str q7, [x28, #96]",
"str q6, [x28, #80]",
"str q5, [x28, #64]",
"str q4, [x28, #48]",
"ldr q2, [sp, #32]",
"str q2, [x28, #32]",
"ldp q2, q3, [x4, #800]",
"stp q2, q3, [x28, #240]",
"stp q14, q15, [x28, #208]",
"stp q12, q13, [x28, #176]",
"stp q10, q11, [x28, #144]",
"stp q8, q9, [x28, #112]",
"stp q6, q7, [x28, #80]",
"stp q4, q5, [x28, #48]",
"ldr q2, [sp]",
"str q2, [x28, #16]",
"b #+0x48",
"ldr q3, [sp, #32]",
"stp q2, q3, [x28, #16]",
"b #+0x28",
"movi v2.2d, #0x0",
"str q2, [x28, #256]",
"str q2, [x28, #240]",
"str q2, [x28, #224]",
"str q2, [x28, #208]",
"str q2, [x28, #192]",
"str q2, [x28, #176]",
"str q2, [x28, #160]",
"str q2, [x28, #144]",
"str q2, [x28, #128]",
"str q2, [x28, #112]",
"str q2, [x28, #96]",
"str q2, [x28, #80]",
"str q2, [x28, #64]",
"str q2, [x28, #48]",
"str q2, [x28, #32]",
"str q2, [x28, #16]",
"stp q2, q2, [x28, #240]",
"stp q2, q2, [x28, #208]",
"stp q2, q2, [x28, #176]",
"stp q2, q2, [x28, #144]",
"stp q2, q2, [x28, #112]",
"stp q2, q2, [x28, #80]",
"stp q2, q2, [x28, #48]",
"stp q2, q2, [x28, #16]",
"ldr x20, [x4, #512]",
"ubfx x20, x20, #1, #2",
"cbnz x20, #+0x8",