2017-04-24 05:00:25 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
2017-08-18 23:08:30 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=x86-64 -mattr=+sse4.2,+pclmul | FileCheck %s --check-prefix=CHECK --check-prefix=GENERIC
|
2017-04-24 05:00:25 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=slm | FileCheck %s --check-prefix=CHECK --check-prefix=SLM
|
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=sandybridge | FileCheck %s --check-prefix=CHECK --check-prefix=SANDY
|
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=ivybridge | FileCheck %s --check-prefix=CHECK --check-prefix=SANDY
|
|
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=haswell | FileCheck %s --check-prefix=CHECK --check-prefix=HASWELL
|
2017-10-17 21:45:39 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=broadwell | FileCheck %s --check-prefix=CHECK --check-prefix=BROADWELL
|
2017-08-30 16:08:50 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=skylake | FileCheck %s --check-prefix=CHECK --check-prefix=SKYLAKE
|
2017-10-06 21:40:29 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=skx | FileCheck %s --check-prefix=CHECK --check-prefix=SKX
|
2017-04-24 05:00:25 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=btver2 | FileCheck %s --check-prefix=CHECK --check-prefix=BTVER2
|
2017-07-19 10:45:14 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -print-schedule -mcpu=znver1 | FileCheck %s --check-prefix=CHECK --check-prefix=ZNVER1
|
2017-04-24 05:00:25 +08:00
|
|
|
|
|
|
|
|
define i32 @crc32_32_8(i32 %a0, i8 %a1, i8 *%a2) {
|
|
|
|
|
; GENERIC-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; GENERIC-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; GENERIC-NEXT: movl %edi, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; SLM-NEXT: crc32b (%rdx), %edi # sched: [6:1.00]
|
|
|
|
|
; SLM-NEXT: movl %edi, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movl %edi, %eax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; SKX-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; BTVER2-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl %edi, %eax # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: crc32_32_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; ZNVER1-NEXT: crc32b (%rdx), %edi # sched: [10:1.00]
|
|
|
|
|
; ZNVER1-NEXT: movl %edi, %eax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i32 @llvm.x86.sse42.crc32.32.8(i32 %a0, i8 %a1)
|
|
|
|
|
%2 = load i8, i8 *%a2
|
|
|
|
|
%3 = call i32 @llvm.x86.sse42.crc32.32.8(i32 %1, i8 %2)
|
|
|
|
|
ret i32 %3
|
|
|
|
|
}
|
|
|
|
|
declare i32 @llvm.x86.sse42.crc32.32.8(i32, i8) nounwind
|
|
|
|
|
|
|
|
|
|
define i32 @crc32_32_16(i32 %a0, i16 %a1, i16 *%a2) {
|
|
|
|
|
; GENERIC-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
2017-08-13 21:59:24 +08:00
|
|
|
; GENERIC-NEXT: crc32w (%rdx), %edi # sched: [7:1.00]
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: movl %edi, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
|
|
|
|
; SLM-NEXT: crc32w (%rdx), %edi # sched: [6:1.00]
|
|
|
|
|
; SLM-NEXT: movl %edi, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
2017-08-13 21:59:24 +08:00
|
|
|
; SANDY-NEXT: crc32w (%rdx), %edi # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movl %edi, %eax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: crc32w (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: crc32w (%rdx), %edi # sched: [8:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: crc32w (%rdx), %edi # sched: [8:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: crc32w (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; SKX-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
|
|
|
|
; BTVER2-NEXT: crc32w (%rdx), %edi # sched: [8:1.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl %edi, %eax # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: crc32_32_16:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: crc32w %si, %edi # sched: [3:1.00]
|
|
|
|
|
; ZNVER1-NEXT: crc32w (%rdx), %edi # sched: [10:1.00]
|
|
|
|
|
; ZNVER1-NEXT: movl %edi, %eax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i32 @llvm.x86.sse42.crc32.32.16(i32 %a0, i16 %a1)
|
|
|
|
|
%2 = load i16, i16 *%a2
|
|
|
|
|
%3 = call i32 @llvm.x86.sse42.crc32.32.16(i32 %1, i16 %2)
|
|
|
|
|
ret i32 %3
|
|
|
|
|
}
|
|
|
|
|
declare i32 @llvm.x86.sse42.crc32.32.16(i32, i16) nounwind
|
|
|
|
|
|
|
|
|
|
define i32 @crc32_32_32(i32 %a0, i32 %a1, i32 *%a2) {
|
|
|
|
|
; GENERIC-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; GENERIC-NEXT: crc32l (%rdx), %edi # sched: [7:1.00]
|
|
|
|
|
; GENERIC-NEXT: movl %edi, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; SLM-NEXT: crc32l (%rdx), %edi # sched: [6:1.00]
|
|
|
|
|
; SLM-NEXT: movl %edi, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; SANDY-NEXT: crc32l (%rdx), %edi # sched: [7:1.00]
|
|
|
|
|
; SANDY-NEXT: movl %edi, %eax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: crc32l (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: crc32l (%rdx), %edi # sched: [8:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: crc32l (%rdx), %edi # sched: [8:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: crc32l (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; SKX-NEXT: movl %edi, %eax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; BTVER2-NEXT: crc32l (%rdx), %edi # sched: [8:1.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl %edi, %eax # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: crc32_32_32:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: crc32l %esi, %edi # sched: [3:1.00]
|
|
|
|
|
; ZNVER1-NEXT: crc32l (%rdx), %edi # sched: [10:1.00]
|
|
|
|
|
; ZNVER1-NEXT: movl %edi, %eax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i32 @llvm.x86.sse42.crc32.32.32(i32 %a0, i32 %a1)
|
|
|
|
|
%2 = load i32, i32 *%a2
|
|
|
|
|
%3 = call i32 @llvm.x86.sse42.crc32.32.32(i32 %1, i32 %2)
|
|
|
|
|
ret i32 %3
|
|
|
|
|
}
|
|
|
|
|
declare i32 @llvm.x86.sse42.crc32.32.32(i32, i32) nounwind
|
|
|
|
|
|
|
|
|
|
define i64 @crc32_64_8(i64 %a0, i8 %a1, i8 *%a2) nounwind {
|
|
|
|
|
; GENERIC-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; GENERIC-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; GENERIC-NEXT: movq %rdi, %rax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; SLM-NEXT: crc32b (%rdx), %edi # sched: [6:1.00]
|
|
|
|
|
; SLM-NEXT: movq %rdi, %rax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movq %rdi, %rax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
|
|
|
|
; SKX-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; BTVER2-NEXT: crc32b (%rdx), %edi # sched: [8:1.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movq %rdi, %rax # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: crc32_64_8:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: crc32b %sil, %edi # sched: [3:1.00]
|
|
|
|
|
; ZNVER1-NEXT: crc32b (%rdx), %edi # sched: [10:1.00]
|
|
|
|
|
; ZNVER1-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i64 @llvm.x86.sse42.crc32.64.8(i64 %a0, i8 %a1)
|
|
|
|
|
%2 = load i8, i8 *%a2
|
|
|
|
|
%3 = call i64 @llvm.x86.sse42.crc32.64.8(i64 %1, i8 %2)
|
|
|
|
|
ret i64 %3
|
|
|
|
|
}
|
|
|
|
|
declare i64 @llvm.x86.sse42.crc32.64.8(i64, i8) nounwind
|
|
|
|
|
|
|
|
|
|
define i64 @crc32_64_64(i64 %a0, i64 %a1, i64 *%a2) {
|
|
|
|
|
; GENERIC-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
2017-08-13 21:59:24 +08:00
|
|
|
; GENERIC-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: movq %rdi, %rax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
|
|
|
|
; SLM-NEXT: crc32q (%rdx), %rdi # sched: [6:1.00]
|
|
|
|
|
; SLM-NEXT: movq %rdi, %rax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
2017-08-13 21:59:24 +08:00
|
|
|
; SANDY-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movq %rdi, %rax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
|
|
|
|
; SKX-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
|
|
|
|
; BTVER2-NEXT: crc32q (%rdx), %rdi # sched: [8:1.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movq %rdi, %rax # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: crc32_64_64:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: crc32q %rsi, %rdi # sched: [3:1.00]
|
|
|
|
|
; ZNVER1-NEXT: crc32q (%rdx), %rdi # sched: [10:1.00]
|
|
|
|
|
; ZNVER1-NEXT: movq %rdi, %rax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i64 @llvm.x86.sse42.crc32.64.64(i64 %a0, i64 %a1)
|
|
|
|
|
%2 = load i64, i64 *%a2
|
|
|
|
|
%3 = call i64 @llvm.x86.sse42.crc32.64.64(i64 %1, i64 %2)
|
|
|
|
|
ret i64 %3
|
|
|
|
|
}
|
|
|
|
|
declare i64 @llvm.x86.sse42.crc32.64.64(i64, i64) nounwind
|
|
|
|
|
|
|
|
|
|
define i32 @test_pcmpestri(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: pcmpestri $7, %xmm1, %xmm0 # sched: [4:2.67]
|
|
|
|
|
; GENERIC-NEXT: movl %ecx, %esi # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: pcmpestri $7, (%rdi), %xmm0 # sched: [4:2.33]
|
2017-12-07 18:40:31 +08:00
|
|
|
; GENERIC-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: movl $7, %edx # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpestri $7, %xmm1, %xmm0 # sched: [21:21.00]
|
|
|
|
|
; SLM-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: movl $7, %edx # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: movl %ecx, %esi # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpestri $7, (%rdi), %xmm0 # sched: [21:21.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SLM-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: leal (%rcx,%rsi), %eax # sched: [1:1.00]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [4:2.67]
|
|
|
|
|
; SANDY-NEXT: movl %ecx, %esi # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [4:2.33]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SANDY-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; HASWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-08-28 18:04:16 +08:00
|
|
|
; HASWELL-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [18:4.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl %ecx, %esi # sched: [1:0.25]
|
|
|
|
|
; HASWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; HASWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [24:4.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; HASWELL-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [18:4.00]
|
|
|
|
|
; BROADWELL-NEXT: movl %ecx, %esi # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [23:4.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; BROADWELL-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [18:4.00]
|
|
|
|
|
; SKYLAKE-NEXT: movl %ecx, %esi # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [24:4.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SKYLAKE-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [18:4.00]
|
|
|
|
|
; SKX-NEXT: movl %ecx, %esi # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [24:4.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SKX-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: movl $7, %edx # sched: [1:0.50]
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [14:10.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: movl $7, %edx # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: movl %ecx, %esi # sched: [1:0.50]
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [19:10.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; BTVER2-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pcmpestri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; ZNVER1-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpestri $7, %xmm1, %xmm0 # sched: [100:?]
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; ZNVER1-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; ZNVER1-NEXT: movl %ecx, %esi # sched: [1:0.25]
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpestri $7, (%rdi), %xmm0 # sched: [100:?]
|
2017-12-07 18:40:31 +08:00
|
|
|
; ZNVER1-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: leal (%rcx,%rsi), %eax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %a1, i32 7, i8 7)
|
|
|
|
|
%2 = load <16 x i8>, <16 x i8> *%a2, align 16
|
|
|
|
|
%3 = call i32 @llvm.x86.sse42.pcmpestri128(<16 x i8> %a0, i32 7, <16 x i8> %2, i32 7, i8 7)
|
|
|
|
|
%4 = add i32 %1, %3
|
|
|
|
|
ret i32 %4
|
|
|
|
|
}
|
|
|
|
|
declare i32 @llvm.x86.sse42.pcmpestri128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @test_pcmpestrm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: pcmpestrm $7, %xmm1, %xmm0 # sched: [11:2.67]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: pcmpestrm $7, (%rdi), %xmm0 # sched: [11:2.33]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: movl $7, %edx # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpestrm $7, %xmm1, %xmm0 # sched: [17:17.00]
|
|
|
|
|
; SLM-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: movl $7, %edx # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpestrm $7, (%rdi), %xmm0 # sched: [17:17.00]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [11:2.67]
|
|
|
|
|
; SANDY-NEXT: movl $7, %eax # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: movl $7, %edx # sched: [1:0.33]
|
|
|
|
|
; SANDY-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [11:2.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; HASWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-08-28 18:04:16 +08:00
|
|
|
; HASWELL-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [19:4.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; HASWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [25:4.00]
|
|
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [19:4.00]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; BROADWELL-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [24:4.00]
|
|
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [19:4.00]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKYLAKE-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [25:4.00]
|
|
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: movl $7, %edx # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [19:4.00]
|
|
|
|
|
; SKX-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; SKX-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [25:4.00]
|
|
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: movl $7, %edx # sched: [1:0.50]
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [14:10.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl $7, %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: movl $7, %edx # sched: [1:0.50]
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [19:10.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pcmpestrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; ZNVER1-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpestrm $7, %xmm1, %xmm0 # sched: [100:?]
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: movl $7, %eax # sched: [1:0.25]
|
|
|
|
|
; ZNVER1-NEXT: movl $7, %edx # sched: [1:0.25]
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpestrm $7, (%rdi), %xmm0 # sched: [100:?]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %a0, i32 7, <16 x i8> %a1, i32 7, i8 7)
|
|
|
|
|
%2 = load <16 x i8>, <16 x i8> *%a2, align 16
|
|
|
|
|
%3 = call <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8> %1, i32 7, <16 x i8> %2, i32 7, i8 7)
|
|
|
|
|
ret <16 x i8> %3
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse42.pcmpestrm128(<16 x i8>, i32, <16 x i8>, i32, i8) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define i32 @test_pcmpistri(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: pcmpistri $7, %xmm1, %xmm0 # sched: [11:3.00]
|
|
|
|
|
; GENERIC-NEXT: movl %ecx, %eax # sched: [1:0.33]
|
|
|
|
|
; GENERIC-NEXT: pcmpistri $7, (%rdi), %xmm0 # sched: [17:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; GENERIC-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: pcmpistri $7, %xmm1, %xmm0 # sched: [17:17.00]
|
|
|
|
|
; SLM-NEXT: movl %ecx, %eax # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpistri $7, (%rdi), %xmm0 # sched: [17:17.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SLM-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: leal (%rcx,%rax), %eax # sched: [1:1.00]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [11:3.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: movl %ecx, %eax # sched: [1:0.33]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [17:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SANDY-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; SANDY-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [11:3.00]
|
|
|
|
|
; HASWELL-NEXT: movl %ecx, %eax # sched: [1:0.25]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [17:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; HASWELL-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [11:3.00]
|
|
|
|
|
; BROADWELL-NEXT: movl %ecx, %eax # sched: [1:0.25]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [16:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; BROADWELL-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [10:3.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: movl %ecx, %eax # sched: [1:0.25]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [16:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SKYLAKE-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [10:3.00]
|
|
|
|
|
; SKX-NEXT: movl %ecx, %eax # sched: [1:0.25]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [16:3.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; SKX-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [7:2.00]
|
2017-12-07 19:19:49 +08:00
|
|
|
; BTVER2-NEXT: movl %ecx, %eax # sched: [1:0.50]
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [12:2.00]
|
2017-12-07 18:40:31 +08:00
|
|
|
; BTVER2-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pcmpistri:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpistri $7, %xmm1, %xmm0 # sched: [100:?]
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: movl %ecx, %eax # sched: [1:0.25]
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpistri $7, (%rdi), %xmm0 # sched: [100:?]
|
2017-12-07 18:40:31 +08:00
|
|
|
; ZNVER1-NEXT: # kill: def %ecx killed %ecx def %rcx
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: leal (%rcx,%rax), %eax # sched: [1:0.25]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %a1, i8 7)
|
|
|
|
|
%2 = load <16 x i8>, <16 x i8> *%a2, align 16
|
|
|
|
|
%3 = call i32 @llvm.x86.sse42.pcmpistri128(<16 x i8> %a0, <16 x i8> %2, i8 7)
|
|
|
|
|
%4 = add i32 %1, %3
|
|
|
|
|
ret i32 %4
|
|
|
|
|
}
|
|
|
|
|
declare i32 @llvm.x86.sse42.pcmpistri128(<16 x i8>, <16 x i8>, i8) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <16 x i8> @test_pcmpistrm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: pcmpistrm $7, %xmm1, %xmm0 # sched: [11:3.00]
|
|
|
|
|
; GENERIC-NEXT: pcmpistrm $7, (%rdi), %xmm0 # sched: [17:3.00]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: pcmpistrm $7, %xmm1, %xmm0 # sched: [13:13.00]
|
|
|
|
|
; SLM-NEXT: pcmpistrm $7, (%rdi), %xmm0 # sched: [13:13.00]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [11:3.00]
|
|
|
|
|
; SANDY-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [17:3.00]
|
|
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-08-28 18:04:16 +08:00
|
|
|
; HASWELL-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [11:3.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [17:3.00]
|
|
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [11:3.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [16:3.00]
|
|
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [10:3.00]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [16:3.00]
|
|
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [10:3.00]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [16:3.00]
|
|
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-11-27 17:58:00 +08:00
|
|
|
; BTVER2-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [8:2.00]
|
|
|
|
|
; BTVER2-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [13:2.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pcmpistrm:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-07-27 02:55:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpistrm $7, %xmm1, %xmm0 # sched: [100:?]
|
|
|
|
|
; ZNVER1-NEXT: vpcmpistrm $7, (%rdi), %xmm0 # sched: [100:?]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %a0, <16 x i8> %a1, i8 7)
|
|
|
|
|
%2 = load <16 x i8>, <16 x i8> *%a2, align 16
|
|
|
|
|
%3 = call <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8> %1, <16 x i8> %2, i8 7)
|
|
|
|
|
ret <16 x i8> %3
|
|
|
|
|
}
|
|
|
|
|
declare <16 x i8> @llvm.x86.sse42.pcmpistrm128(<16 x i8>, <16 x i8>, i8) nounwind readnone
|
|
|
|
|
|
|
|
|
|
define <2 x i64> @test_pcmpgtq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-01 23:14:35 +08:00
|
|
|
; GENERIC-NEXT: pcmpgtq %xmm1, %xmm0 # sched: [5:1.00]
|
|
|
|
|
; GENERIC-NEXT: pcmpgtq (%rdi), %xmm0 # sched: [11:1.00]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-04-24 05:23:27 +08:00
|
|
|
; SLM-NEXT: pcmpgtq %xmm1, %xmm0 # sched: [1:0.50]
|
|
|
|
|
; SLM-NEXT: pcmpgtq (%rdi), %xmm0 # sched: [4:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
This patch completely replaces the scheduling information for the SandyBridge architecture target by modifying the file X86SchedSandyBridge.td located under the X86 Target.
The SandyBridge architects have provided us with a more accurate information about each instruction latency, number of uOPs and used ports and I used it to replace the existing estimated SNB instructions scheduling and to add missing scheduling information.
Please note that the patch extensively affects the X86 MC instr scheduling for SNB.
Also note that this patch will be followed by additional patches for the remaining target architectures HSW, IVB, BDW, SKL and SKX.
The updated and extended information about each instruction includes the following details:
•static latency of the instruction
•number of uOps from which the instruction consists of
•all ports used by the instruction's' uOPs
For example, the following code dictates that instructions, ADC64mr, ADC8mr, SBB64mr, SBB8mr have a static latency of 9 cycles. Each of these instructions is decoded into 6 micro operations which use ports 4, ports 2 or 3 and port 0 and ports 0 or 1 or 5:
def SBWriteResGroup94 : SchedWriteRes<[SBPort4,SBPort23,SBPort0,SBPort015]> {
let Latency = 9;
let NumMicroOps = 6;
let ResourceCycles = [1,2,2,1];
}
def: InstRW<[SBWriteResGroup94], (instregex "ADC64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "ADC8mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB64mr")>;
def: InstRW<[SBWriteResGroup94], (instregex "SBB8mr")>;
Note that apart for the header, most of the X86SchedSandyBridge.td file was generated by a script.
Reviewers: zvi, chandlerc, RKSimon, m_zuckerman, craig.topper, igorb
Differential Revision: https://reviews.llvm.org/D35019#inline-304691
llvm-svn: 307529
2017-07-10 17:53:16 +08:00
|
|
|
; SANDY-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
|
|
|
|
|
; SANDY-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [11:1.00]
|
|
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-04-24 05:00:25 +08:00
|
|
|
; HASWELL-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [11:1.00]
|
|
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [10:1.00]
|
|
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [3:1.00]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [9:1.00]
|
|
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2018-01-10 02:14:22 +08:00
|
|
|
; SKX-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [3:1.00]
|
|
|
|
|
; SKX-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [9:1.00]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-04-24 05:23:27 +08:00
|
|
|
; BTVER2-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
|
|
|
|
|
; BTVER2-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [6:1.00]
|
2017-04-24 05:00:25 +08:00
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
2017-07-19 10:45:14 +08:00
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pcmpgtq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
|
2017-07-19 10:45:14 +08:00
|
|
|
; ZNVER1-NEXT: vpcmpgtq (%rdi), %xmm0, %xmm0 # sched: [8:0.50]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-04-24 05:00:25 +08:00
|
|
|
%1 = icmp sgt <2 x i64> %a0, %a1
|
|
|
|
|
%2 = sext <2 x i1> %1 to <2 x i64>
|
|
|
|
|
%3 = load <2 x i64>, <2 x i64>*%a2, align 16
|
|
|
|
|
%4 = icmp sgt <2 x i64> %2, %3
|
|
|
|
|
%5 = sext <2 x i1> %4 to <2 x i64>
|
|
|
|
|
ret <2 x i64> %5
|
|
|
|
|
}
|
2017-08-18 23:08:30 +08:00
|
|
|
|
|
|
|
|
define <2 x i64> @test_pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> *%a2) {
|
|
|
|
|
; GENERIC-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; GENERIC: # %bb.0:
|
2017-08-18 23:08:30 +08:00
|
|
|
; GENERIC-NEXT: pclmulqdq $0, %xmm1, %xmm0 # sched: [14:6.00]
|
|
|
|
|
; GENERIC-NEXT: pclmulqdq $0, (%rdi), %xmm0 # sched: [14:5.67]
|
|
|
|
|
; GENERIC-NEXT: retq # sched: [1:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SLM-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SLM: # %bb.0:
|
2017-08-18 23:08:30 +08:00
|
|
|
; SLM-NEXT: pclmulqdq $0, %xmm1, %xmm0 # sched: [10:10.00]
|
|
|
|
|
; SLM-NEXT: pclmulqdq $0, (%rdi), %xmm0 # sched: [10:10.00]
|
|
|
|
|
; SLM-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; SANDY-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SANDY: # %bb.0:
|
2017-08-18 23:08:30 +08:00
|
|
|
; SANDY-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [14:6.00]
|
|
|
|
|
; SANDY-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [14:5.67]
|
|
|
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
|
|
|
;
|
|
|
|
|
; HASWELL-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; HASWELL: # %bb.0:
|
2017-08-28 18:04:16 +08:00
|
|
|
; HASWELL-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [11:2.00]
|
2017-12-08 17:48:44 +08:00
|
|
|
; HASWELL-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [17:2.00]
|
|
|
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
2017-08-18 23:08:30 +08:00
|
|
|
;
|
2017-10-17 21:45:39 +08:00
|
|
|
; BROADWELL-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BROADWELL: # %bb.0:
|
2017-10-25 04:19:47 +08:00
|
|
|
; BROADWELL-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
|
|
|
|
|
; BROADWELL-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [10:1.00]
|
|
|
|
|
; BROADWELL-NEXT: retq # sched: [7:1.00]
|
2017-10-17 21:45:39 +08:00
|
|
|
;
|
2017-08-30 16:08:50 +08:00
|
|
|
; SKYLAKE-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKYLAKE: # %bb.0:
|
2017-09-19 14:19:27 +08:00
|
|
|
; SKYLAKE-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [6:1.00]
|
2017-10-17 14:47:04 +08:00
|
|
|
; SKYLAKE-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [12:1.00]
|
|
|
|
|
; SKYLAKE-NEXT: retq # sched: [7:1.00]
|
2017-08-30 16:08:50 +08:00
|
|
|
;
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; SKX: # %bb.0:
|
2017-10-06 21:40:29 +08:00
|
|
|
; SKX-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [6:1.00]
|
2017-10-08 20:52:54 +08:00
|
|
|
; SKX-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [12:1.00]
|
|
|
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
2017-10-06 21:40:29 +08:00
|
|
|
;
|
2017-08-18 23:08:30 +08:00
|
|
|
; BTVER2-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; BTVER2: # %bb.0:
|
2017-08-18 23:08:30 +08:00
|
|
|
; BTVER2-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
|
|
|
|
|
; BTVER2-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [7:1.00]
|
|
|
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
|
|
|
;
|
|
|
|
|
; ZNVER1-LABEL: test_pclmulqdq:
|
2017-12-05 01:18:51 +08:00
|
|
|
; ZNVER1: # %bb.0:
|
2017-08-18 23:08:30 +08:00
|
|
|
; ZNVER1-NEXT: vpclmulqdq $0, %xmm1, %xmm0, %xmm0 # sched: [100:?]
|
|
|
|
|
; ZNVER1-NEXT: vpclmulqdq $0, (%rdi), %xmm0, %xmm0 # sched: [100:?]
|
AMD family 17h (znver1) scheduler model update.
Summary:
This patch enables the following:
1) Regex based Instruction itineraries for integer instructions.
2) The instructions are grouped as per the nature of the instructions
(move, arithmetic, logic, Misc, Control Transfer).
3) FP instructions and their itineraries are added which includes values
for SSE4A, BMI, BMI2 and SHA instructions.
Patch by Ganesh Gopalasubramanian
Reviewers: RKSimon, craig.topper
Subscribers: vprasad, shivaram, ddibyend, andreadb, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D36617
llvm-svn: 312237
2017-08-31 20:38:35 +08:00
|
|
|
; ZNVER1-NEXT: retq # sched: [1:0.50]
|
2017-08-18 23:08:30 +08:00
|
|
|
%1 = load <2 x i64>, <2 x i64> *%a2, align 16
|
|
|
|
|
%2 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %a0, <2 x i64> %a1, i8 0)
|
|
|
|
|
%3 = call <2 x i64> @llvm.x86.pclmulqdq(<2 x i64> %1, <2 x i64> %2, i8 0)
|
|
|
|
|
ret <2 x i64> %3
|
|
|
|
|
}
|
|
|
|
|
declare <2 x i64> @llvm.x86.pclmulqdq(<2 x i64>, <2 x i64>, i8)
|