SQRTSD (XMM, XMM)
Summary:
"Compute Square Root of Scalar Double-Precision Floating-Point Value"
Reference:
https://www.felixcloutier.com/x86/SQRTSD.html
Extension:
SSE2
Category:
SSE
ISA-Set:
SSE2
CPL:
3
iform:
SQRTSD_XMMsd_XMMsd
iclass:
SQRTSD
ASM:
SQRTSD
Operands
Operand 1 (r/w): Register (XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15)
Operand 2 (r): Register (XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7, XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15)
Available performance data
Alder Lake-P
Alder Lake-E
Rocket Lake
Tiger Lake
Ice Lake
Cascade Lake
Cannon Lake
Skylake-X
Coffee Lake
Kaby Lake
Skylake
Broadwell
Haswell
Ivy Bridge
Sandy Bridge
Westmere
Nehalem
Wolfdale
Conroe
Tremont
Goldmont Plus
Goldmont
Airmont
Bonnell
AMD Zen 4
AMD Zen 3
AMD Zen 2
AMD Zen+
Alder Lake-P
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Alder Lake-E
Measurements
Latencies
Latency operand 1 → 1:
≤17
Latency operand 2 → 1:
≤17
Throughput
Measured (loop):
12.00
Measured (unrolled):
12.00
Number of μops
Executed: 1
Microcode Sequencer (MS): 0
Rocket Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Tiger Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Ice Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Cascade Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Cannon Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Skylake-X
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
6.00
Number of μops:
1
Port usage:
1*p0
IACA 3.0
Throughput
Computed from the port usage: 1.00
IACA:
5.92
Number of μops:
1
Port usage:
1*p0
Coffee Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Kaby Lake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
Skylake
Measurements
Latencies
Latency operand 1 → 1:
≤13
Latency operand 2 → 1:
≤13
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.50
Measured (unrolled):
4.50
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
6.00
Number of μops:
1
Port usage:
1*p0
IACA 3.0
Throughput
Computed from the port usage: 1.00
IACA:
5.92
Number of μops:
1
Port usage:
1*p0
Broadwell
Measurements
Latencies
Latency operand 1 → 1:
≤10
Latency operand 2 → 1:
≤10
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.00
Measured (unrolled):
4.00
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
13.00 (with the -no_interiteration flag: 13.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
13.00
Number of μops:
1
Port usage:
1*p0
IACA 3.0
Throughput
Computed from the port usage: 1.00
IACA:
12.80
Number of μops:
1
Port usage:
1*p0
Haswell
Measurements
Latencies
Latency operand 1 → 1:
≤10
Latency operand 2 → 1:
≤10
Throughput
Computed from the port usage: 1.00
Measured (loop):
8.02
Measured (unrolled):
8.03
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.1
Latency:
20
Throughput
Computed from the port usage: 1.00
IACA:
14.00 (with the -no_interiteration flag: 14.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
14.00 (with the -no_interiteration flag: 14.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
14.00
Number of μops:
1
Port usage:
1*p0
IACA 3.0
Throughput
Computed from the port usage: 1.00
IACA:
13.81
Number of μops:
1
Port usage:
1*p0
Ivy Bridge
Measurements
Latencies
Latency operand 1 → 1:
≤11
Latency operand 2 → 1:
≤10
Throughput
Computed from the port usage: 1.00
Measured (loop):
8.00
Measured (unrolled):
8.00
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.1
Latency:
20
Throughput
Computed from the port usage: 1.00
IACA:
14.00 (with the -no_interiteration flag: 14.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
14.00 (with the -no_interiteration flag: 14.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
14.00
Number of μops:
1
Port usage:
1*p0
Sandy Bridge
Measurements
Latencies
Latency operand 1 → 1:
≤11
Latency operand 2 → 1:
≤10
Throughput
Computed from the port usage: 1.00
Measured (loop):
10.00
Measured (unrolled):
10.00
Number of μops
Executed: 1
Retire slots: 1
Decoded (MITE): 1
Microcode Sequencer (MS): 0
Port usage:
1*p0
IACA 2.1
Latency:
21
Throughput
Computed from the port usage: 1.00
IACA:
21.00 (with the -no_interiteration flag: 21.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
21.00 (with the -no_interiteration flag: 21.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.3
Throughput
Computed from the port usage: 1.00
IACA:
21.00
Number of μops:
1
Port usage:
1*p0
Westmere
Measurements
Latencies
Latency operand 1 → 1:
≤194
Latency operand 2 → 1:
≤7
Throughput
Computed from the port usage: 1.00
Measured (loop):
7.00
Measured (unrolled):
7.00
Number of μops
Executed: 1
Retire slots: 1
Microcode Sequencer (MS): 0
Requires the complex decoder
Port usage:
1*p0
IACA 2.1
Latency:
32
Throughput
Computed from the port usage: 1.00
IACA:
32.00 (with the -no_interiteration flag: 32.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
32.00 (with the -no_interiteration flag: 32.00)
Number of μops:
1
Port usage:
1*p0
Nehalem
Measurements
Latencies
Latency operand 1 → 1:
≤196
Latency operand 2 → 1:
≤7
Throughput
Computed from the port usage: 1.00
Measured (loop):
7.00
Measured (unrolled):
7.00
Number of μops
Executed: 1
Retire slots: 1
Microcode Sequencer (MS): 0
Requires the complex decoder
Port usage:
1*p0
IACA 2.1
Latency:
32
Throughput
Computed from the port usage: 1.00
IACA:
32.00 (with the -no_interiteration flag: 32.00)
Number of μops:
1
Port usage:
1*p0
IACA 2.2
Throughput
Computed from the port usage: 1.00
IACA:
32.00 (with the -no_interiteration flag: 32.00)
Number of μops:
1
Port usage:
1*p0
Wolfdale
Measurements
Latencies
Latency operand 1 → 1:
≤6
Latency operand 2 → 1:
≤6
Throughput
Computed from the port usage: 1.00
Measured (loop):
5.00
Measured (unrolled):
5.00
Number of μops
Executed: 1
Port usage:
1*p0
Conroe
Measurements
Latencies
Latency operand 1 → 1:
≤200
Latency operand 2 → 1:
≤6
Throughput
Computed from the port usage: 1.00
Measured (loop):
5.00
Measured (unrolled):
5.00
Number of μops
Executed: 1
Port usage:
1*p0
Tremont
Measurements
Latencies
Latency operand 1 → 1:
≤17
Latency operand 2 → 1:
≤17
Throughput
Measured (loop):
12.00
Measured (unrolled):
12.00
Number of μops
Executed: 1
Microcode Sequencer (MS): 0
Goldmont Plus
Measurements
Latencies
Latency operand 1 → 1:
≤12
Latency operand 2 → 1:
≤18
Throughput
Measured (loop):
14.00
Measured (unrolled):
14.00
Number of μops
Executed: 1
Microcode Sequencer (MS): 0
Goldmont
Measurements
Latencies
Latency operand 1 → 1:
≤230
Latency operand 2 → 1:
≤35
Throughput
Measured (loop):
34.00
Measured (unrolled):
34.00
Number of μops
Executed: 1
Microcode Sequencer (MS): 0
Airmont
Measurements
Latencies
Latency operand 1 → 1:
≤207
Latency operand 2 → 1:
≤35
Throughput
Measured (loop):
33.00
Measured (unrolled):
33.00
Number of μops
Executed: 1
Microcode Sequencer (MS): 0
Bonnell
Measurements
Latencies
Latency operand 1 → 1:
≤16
Latency operand 2 → 1:
≤60
Throughput
Measured (loop):
60.00
Measured (unrolled):
60.00
Number of μops
Executed: 3
Microcode Sequencer (MS): 3
Requires the complex decoder
AMD Zen 4
Measurements
Latencies
Latency operand 1 → 1:
≤21
Latency operand 2 → 1:
≤21
Throughput
Computed from the port usage: 0.50
Measured (loop):
8.40
Measured (unrolled):
8.40
Number of μops
Executed: 1
Port usage:
1*FP01
AMD Zen 3
Measurements
Latencies
Latency operand 1 → 1:
≤20
Latency operand 2 → 1:
≤20
Throughput
Computed from the port usage: 0.50
Measured (loop):
8.50
Measured (unrolled):
8.50
Number of μops
Executed: 1
Port usage:
1*FP01
Documentation
Latency: 20
Throughput: 20.00
Number of μops: 1
Port usage: FP3
AMD Zen 2
Measurements
Latencies
Latency operand 1 → 1:
≤20
Latency operand 2 → 1:
≤20
Throughput
Computed from the port usage: 1.00
Measured (loop):
8.50
Measured (unrolled):
8.50
Number of μops
Executed: 1
Port usage:
1*FP3
Documentation
Latency: 20
Throughput: 20.00
Number of μops: 1
Port usage: FP3
AMD Zen+
Measurements
Latencies
Latency operand 1 → 1:
≤8
Latency operand 2 → 1:
≤8
Throughput
Computed from the port usage: 1.00
Measured (loop):
4.00
Measured (unrolled):
4.00
Number of μops
Executed: 1
Port usage:
1*FP3
Documentation
Latency: 20
Throughput: 20.00
Number of μops: 1
Port usage: FP3