[X86] Removing 'TuningSlow3OpsLEA' from ICL config

[goldstein.w.n]

Summary

According to https://uops.info/ ICL and newer have fast 3-term LEA.

[pengfei]

I'm not sure of that. There's no description in Intel SOM. I also googled about it when writting #60043 and just found LEA was improved in Golden Cove, e.g., https://www.hardwaretimes.com/intel-golden-cove-core-architecture-deep-dive-vs-zen-3-and-sunny-cove/

[craig.topper]

https://uops.info/table.html?search=lea&cb_lat=on&cb_tp=on&cb_uops=on&cb_ports=on&cb_CLX=on&cb_ICL=on&cb_measurements=on&cb_base=on

There are no 3 cycle port 1 R32/R64 LEAs on Icelake. They are now single cycle port 1 and 5. And some cases that were 1 cycle port 1 and 5 before are now port 0/1/5/6.

[goldstein.w.n]

In D141974#4060943, @pengfei wrote:

I'm not sure of that. There's no description in Intel SOM. I also googled about it when writting #60043 and just found LEA was improved in Golden Cove, e.g., https://www.hardwaretimes.com/intel-golden-cove-core-architecture-deep-dive-vs-zen-3-and-sunny-cove/

Fairly certain its been changed. uops.info is generally reliable also tested just now on ICX:

	.global	_start
	.p2align 6
	.text
_start:
	movl	$10000000, %eax

	xorl	%edx, %edx
loop:
	leaq	1(%rdx, %rax, 8), %rdx
	decl	%eax
	jnz	loop


	movl	$60, %eax
	xorl	%edi, %edi
	syscall

Results in:

10,002,046      cycles                                                      
 4,678,897      p0                                                          
 4,678,955      p1                                                          
 5,321,396      p5                                                          
 5,321,559      p6

Should be 30,000,000 cycles if was 3c latency.

[pengfei]

LGTM. Thanks for the information!

llvm/lib/Target/X86/X86.td

list<SubtargetFeature> ICLAdditionalFeatures = [FeatureBITALG,
                                                   FeatureVNNI,
                                                   FeatureVPCLMULQDQ,
                                                   FeatureVPOPCNTDQ,
                                                   FeatureGFNI,
                                                   FeatureRDPID,
                                                   FeatureFSRM];
   list<SubtargetFeature> ICLTuning = [TuningFastGather,
                                       TuningMacroFusion,
-                                      TuningSlow3OpsLEA,
                                       TuningSlowDivide64,
                                       TuningFastScalarFSQRT,
                                       TuningFastVectorFSQRT,
                                       TuningFastSHLDRotate,
                                       TuningFast15ByteNOP,
                                       TuningFastVariableCrossLaneShuffle,
                                       TuningFastVariablePerLaneShuffle,
                                       TuningPrefer256Bit,