diff --git a/llvm/lib/Target/X86/X86CallingConv.td b/llvm/lib/Target/X86/X86CallingConv.td
--- a/llvm/lib/Target/X86/X86CallingConv.td
+++ b/llvm/lib/Target/X86/X86CallingConv.td
@@ -1160,7 +1160,7 @@
 def CSR_64_HHVM : CalleeSavedRegs<(add R12)>;
 
 // Register calling convention preserves few GPR and XMM8-15
-def CSR_32_RegCall_NoSSE : CalleeSavedRegs<(add ESI, EDI, EBX, EBP, ESP)>;
+def CSR_32_RegCall_NoSSE : CalleeSavedRegs<(add ESI, EDI, EBX, EBP)>;
 def CSR_32_RegCall       : CalleeSavedRegs<(add CSR_32_RegCall_NoSSE,
                                            (sequence "XMM%u", 4, 7))>;
 def CSR_Win32_CFGuard_Check_NoSSE : CalleeSavedRegs<(add CSR_32_RegCall_NoSSE, ECX)>;
diff --git a/llvm/test/CodeGen/X86/avx512-regcall-Mask.ll b/llvm/test/CodeGen/X86/avx512-regcall-Mask.ll
--- a/llvm/test/CodeGen/X86/avx512-regcall-Mask.ll
+++ b/llvm/test/CodeGen/X86/avx512-regcall-Mask.ll
@@ -283,8 +283,7 @@
 define dso_local x86_regcallcc i32 @test_argv32i1(<32 x i1> %x0, <32 x i1> %x1, <32 x i1> %x2)  {
 ; X32-LABEL: test_argv32i1:
 ; X32:       # %bb.0: # %entry
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $72, %esp
+; X32-NEXT:    subl $76, %esp
 ; X32-NEXT:    vmovups %xmm7, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm6, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm5, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
@@ -303,8 +302,7 @@
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm5 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm6 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm7 # 16-byte Reload
-; X32-NEXT:    addl $72, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $76, %esp
 ; X32-NEXT:    vzeroupper
 ; X32-NEXT:    retl
 ;
@@ -518,8 +516,7 @@
 define dso_local x86_regcallcc i16 @test_argv16i1(<16 x i1> %x0, <16 x i1> %x1, <16 x i1> %x2)  {
 ; X32-LABEL: test_argv16i1:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $72, %esp
+; X32-NEXT:    subl $76, %esp
 ; X32-NEXT:    vmovups %xmm7, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm6, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm5, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
@@ -539,8 +536,7 @@
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm5 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm6 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm7 # 16-byte Reload
-; X32-NEXT:    addl $72, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $76, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_argv16i1:
@@ -752,8 +748,7 @@
 define dso_local x86_regcallcc i8 @test_argv8i1(<8 x i1> %x0, <8 x i1> %x1, <8 x i1> %x2)  {
 ; X32-LABEL: test_argv8i1:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $72, %esp
+; X32-NEXT:    subl $76, %esp
 ; X32-NEXT:    vmovups %xmm7, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm6, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovups %xmm5, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
@@ -773,8 +768,7 @@
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm5 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm6 # 16-byte Reload
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm7 # 16-byte Reload
-; X32-NEXT:    addl $72, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $76, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_argv8i1:
diff --git a/llvm/test/CodeGen/X86/avx512-regcall-NoMask.ll b/llvm/test/CodeGen/X86/avx512-regcall-NoMask.ll
--- a/llvm/test/CodeGen/X86/avx512-regcall-NoMask.ll
+++ b/llvm/test/CodeGen/X86/avx512-regcall-NoMask.ll
@@ -30,12 +30,10 @@
 define dso_local x86_regcallcc i1 @test_CallargReti1(i1 %a)  {
 ; X32-LABEL: test_CallargReti1:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    incb %al
 ; X32-NEXT:    movzbl %al, %eax
 ; X32-NEXT:    calll _test_argReti1
 ; X32-NEXT:    incb %al
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargReti1:
@@ -96,12 +94,10 @@
 define dso_local x86_regcallcc i8 @test_CallargReti8(i8 %a)  {
 ; X32-LABEL: test_CallargReti8:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    incb %al
 ; X32-NEXT:    movzbl %al, %eax
 ; X32-NEXT:    calll _test_argReti8
 ; X32-NEXT:    incb %al
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargReti8:
@@ -162,13 +158,11 @@
 define dso_local x86_regcallcc i16 @test_CallargReti16(i16 %a)  {
 ; X32-LABEL: test_CallargReti16:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    incl %eax
 ; X32-NEXT:    calll _test_argReti16
 ; X32-NEXT:    # kill: def $ax killed $ax def $eax
 ; X32-NEXT:    incl %eax
 ; X32-NEXT:    # kill: def $ax killed $ax killed $eax
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargReti16:
@@ -228,11 +222,9 @@
 define dso_local x86_regcallcc i32 @test_CallargReti32(i32 %a)  {
 ; X32-LABEL: test_CallargReti32:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    incl %eax
 ; X32-NEXT:    calll _test_argReti32
 ; X32-NEXT:    incl %eax
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargReti32:
@@ -291,13 +283,11 @@
 define dso_local x86_regcallcc i64 @test_CallargReti64(i64 %a)  {
 ; X32-LABEL: test_CallargReti64:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    addl $1, %eax
 ; X32-NEXT:    adcl $0, %ecx
 ; X32-NEXT:    calll _test_argReti64
 ; X32-NEXT:    addl $1, %eax
 ; X32-NEXT:    adcl $0, %ecx
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargReti64:
@@ -353,16 +343,14 @@
 define dso_local x86_regcallcc float @test_CallargRetFloat(float %a)  {
 ; X32-LABEL: test_CallargRetFloat:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $24, %esp
+; X32-NEXT:    subl $28, %esp
 ; X32-NEXT:    vmovups %xmm4, (%esp) # 16-byte Spill
 ; X32-NEXT:    vmovss {{.*#+}} xmm4 = mem[0],zero,zero,zero
 ; X32-NEXT:    vaddss %xmm4, %xmm0, %xmm0
 ; X32-NEXT:    calll _test_argRetFloat
 ; X32-NEXT:    vaddss %xmm4, %xmm0, %xmm0
 ; X32-NEXT:    vmovups (%esp), %xmm4 # 16-byte Reload
-; X32-NEXT:    addl $24, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $28, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRetFloat:
@@ -433,16 +421,14 @@
 define dso_local x86_regcallcc double @test_CallargRetDouble(double %a)  {
 ; X32-LABEL: test_CallargRetDouble:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $24, %esp
+; X32-NEXT:    subl $28, %esp
 ; X32-NEXT:    vmovups %xmm4, (%esp) # 16-byte Spill
 ; X32-NEXT:    vmovsd {{.*#+}} xmm4 = mem[0],zero
 ; X32-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
 ; X32-NEXT:    calll _test_argRetDouble
 ; X32-NEXT:    vaddsd %xmm4, %xmm0, %xmm0
 ; X32-NEXT:    vmovups (%esp), %xmm4 # 16-byte Reload
-; X32-NEXT:    addl $24, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $28, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRetDouble:
@@ -544,11 +530,9 @@
 define x86_regcallcc x86_fp80 @test_CallargRetf80(x86_fp80 %a)  {
 ; X32-LABEL: test_CallargRetf80:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    fadd %st, %st(0)
 ; X32-NEXT:    calll _test_argRetf80
 ; X32-NEXT:    fadd %st, %st(0)
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRetf80:
@@ -583,11 +567,9 @@
 define dso_local x86_regcallcc double @test_CallargParamf80(x86_fp80 %a)  {
 ; X32-LABEL: test_CallargParamf80:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    fadd %st, %st(0)
 ; X32-NEXT:    calll _test_argParamf80
 ; X32-NEXT:    vaddsd %xmm0, %xmm0, %xmm0
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargParamf80:
@@ -645,11 +627,9 @@
 define dso_local x86_regcallcc [4 x i32]* @test_CallargRetPointer([4 x i32]* %a)  {
 ; X32-LABEL: test_CallargRetPointer:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
 ; X32-NEXT:    incl %eax
 ; X32-NEXT:    calll _test_argRetPointer
 ; X32-NEXT:    incl %eax
-; X32-NEXT:    popl %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRetPointer:
@@ -715,8 +695,7 @@
 define dso_local x86_regcallcc <4 x i32> @test_CallargRet128Vector(<4 x i1> %x, <4 x i32> %a)  {
 ; X32-LABEL: test_CallargRet128Vector:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $40, %esp
+; X32-NEXT:    subl $44, %esp
 ; X32-NEXT:    vmovups %xmm4, {{[-0-9]+}}(%e{{[sb]}}p) # 16-byte Spill
 ; X32-NEXT:    vmovdqa %xmm1, %xmm4
 ; X32-NEXT:    vpslld $31, %xmm0, %xmm1
@@ -728,8 +707,7 @@
 ; X32-NEXT:    kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k1 # 2-byte Reload
 ; X32-NEXT:    vmovdqa32 %xmm4, %xmm0 {%k1}
 ; X32-NEXT:    vmovups {{[-0-9]+}}(%e{{[sb]}}p), %xmm4 # 16-byte Reload
-; X32-NEXT:    addl $40, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $44, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRet128Vector:
@@ -812,8 +790,7 @@
 define dso_local x86_regcallcc <8 x i32> @test_CallargRet256Vector(<8 x i1> %x, <8 x i32> %a)  {
 ; X32-LABEL: test_CallargRet256Vector:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $88, %esp
+; X32-NEXT:    subl $92, %esp
 ; X32-NEXT:    vmovdqu %ymm0, {{[-0-9]+}}(%e{{[sb]}}p) # 32-byte Spill
 ; X32-NEXT:    kmovd %eax, %k1
 ; X32-NEXT:    kmovw %k1, {{[-0-9]+}}(%e{{[sb]}}p) # 2-byte Spill
@@ -822,8 +799,7 @@
 ; X32-NEXT:    kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k1 # 2-byte Reload
 ; X32-NEXT:    vmovdqu {{[-0-9]+}}(%e{{[sb]}}p), %ymm1 # 32-byte Reload
 ; X32-NEXT:    vmovdqa32 %ymm1, %ymm0 {%k1}
-; X32-NEXT:    addl $88, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $92, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRet256Vector:
@@ -898,8 +874,7 @@
 define dso_local x86_regcallcc <16 x i32> @test_CallargRet512Vector(<16 x i1> %x, <16 x i32> %a)  {
 ; X32-LABEL: test_CallargRet512Vector:
 ; X32:       # %bb.0:
-; X32-NEXT:    pushl %esp
-; X32-NEXT:    subl $184, %esp
+; X32-NEXT:    subl $188, %esp
 ; X32-NEXT:    vmovdqu64 %zmm0, {{[-0-9]+}}(%e{{[sb]}}p) # 64-byte Spill
 ; X32-NEXT:    kmovd %eax, %k1
 ; X32-NEXT:    kmovw %k1, {{[-0-9]+}}(%e{{[sb]}}p) # 2-byte Spill
@@ -908,8 +883,7 @@
 ; X32-NEXT:    kmovw {{[-0-9]+}}(%e{{[sb]}}p), %k1 # 2-byte Reload
 ; X32-NEXT:    vmovdqu64 {{[-0-9]+}}(%e{{[sb]}}p), %zmm1 # 64-byte Reload
 ; X32-NEXT:    vmovdqa32 %zmm1, %zmm0 {%k1}
-; X32-NEXT:    addl $184, %esp
-; X32-NEXT:    popl %esp
+; X32-NEXT:    addl $188, %esp
 ; X32-NEXT:    retl
 ;
 ; WIN64-LABEL: test_CallargRet512Vector: