Loading src/lisp/x86-assem.S +34 −12 Changes for src/lisp/x86-assem.S: 34 added lines, 12 removed lines. Original line number Diff line number Diff line Loading @@ -404,22 +404,39 @@ FUNCDEF(alloc_overflow_sse2) ENDFUNC(alloc_overflow_sse2) #else FUNCDEF(alloc_overflow_sse2) # Need 512 bytes for the fpu save area, space to save ecx and edx, # space for mxcsr, a temp, and one arg to pass to alloc. That's # 512 + 20. But the save area needs to be 16-byte aligned, so # allocate 512 + 32 bytes. The fpu area will be at offset 32. # Need 8*16 bytes for the xmm registers, and space to save ecx # and edx, space for mxcsr, a temp, and one arg to pass to alloc. # That's 8*16 + 5*4 = 148 bytes. Might as well have a few # more so the xmm0 area is 16-byte aligned. That makes it 160 # bytes. # # Stack looks like: # # +544 -> end # +32 -> fpu save # +160 # +144 -> xmm7 # +128 -> xmm6 # +112 -> xmm5 # +96 -> xmm4 # +80 -> xmm3 # +64 -> xmm2 # +48 -> xmm1 # +32 -> xmm0 # +20 -> unused # +16 -> temp # +12 -> mxcsr # + 8 -> save ecx # + 4 -> save edx # esp + 0 -> arg for alloc STACK_PROLOGUE(32+512) STACK_PROLOGUE(160) movapd %xmm0, (32 + 0*16)(%esp) movapd %xmm1, (32 + 1*16)(%esp) movapd %xmm2, (32 + 2*16)(%esp) movapd %xmm3, (32 + 3*16)(%esp) movapd %xmm4, (32 + 4*16)(%esp) movapd %xmm5, (32 + 5*16)(%esp) movapd %xmm6, (32 + 6*16)(%esp) movapd %xmm7, (32 + 7*16)(%esp) movl %ecx, 8(%esp) # Save ecx and edx registers movl %edx, 4(%esp) stmxcsr 12(%esp) # Save MXCSR Loading @@ -430,16 +447,21 @@ FUNCDEF(alloc_overflow_sse2) ldmxcsr 16(%esp) # Get new mxcsr value movl %eax, (%esp) # Put size on stack for first arg to alloc() # Save all FPU regs because we don't know what's in use by lisp. fxsave 32(%esp) call GNAME(alloc) fxrstor 32(%esp) movl 4(%esp), %edx # Restore edx and ecx registers. eax has the return value. movl 8(%esp), %ecx ldmxcsr 12(%esp) movapd (32 + 0*16)(%esp), %xmm0 movapd (32 + 1*16)(%esp), %xmm1 movapd (32 + 2*16)(%esp), %xmm2 movapd (32 + 3*16)(%esp), %xmm3 movapd (32 + 4*16)(%esp), %xmm4 movapd (32 + 5*16)(%esp), %xmm5 movapd (32 + 6*16)(%esp), %xmm6 movapd (32 + 7*16)(%esp), %xmm7 STACK_EPILOGUE ret ENDFUNC(alloc_overflow_sse2) Loading Loading
src/lisp/x86-assem.S +34 −12 Changes for src/lisp/x86-assem.S: 34 added lines, 12 removed lines. Original line number Diff line number Diff line Loading @@ -404,22 +404,39 @@ FUNCDEF(alloc_overflow_sse2) ENDFUNC(alloc_overflow_sse2) #else FUNCDEF(alloc_overflow_sse2) # Need 512 bytes for the fpu save area, space to save ecx and edx, # space for mxcsr, a temp, and one arg to pass to alloc. That's # 512 + 20. But the save area needs to be 16-byte aligned, so # allocate 512 + 32 bytes. The fpu area will be at offset 32. # Need 8*16 bytes for the xmm registers, and space to save ecx # and edx, space for mxcsr, a temp, and one arg to pass to alloc. # That's 8*16 + 5*4 = 148 bytes. Might as well have a few # more so the xmm0 area is 16-byte aligned. That makes it 160 # bytes. # # Stack looks like: # # +544 -> end # +32 -> fpu save # +160 # +144 -> xmm7 # +128 -> xmm6 # +112 -> xmm5 # +96 -> xmm4 # +80 -> xmm3 # +64 -> xmm2 # +48 -> xmm1 # +32 -> xmm0 # +20 -> unused # +16 -> temp # +12 -> mxcsr # + 8 -> save ecx # + 4 -> save edx # esp + 0 -> arg for alloc STACK_PROLOGUE(32+512) STACK_PROLOGUE(160) movapd %xmm0, (32 + 0*16)(%esp) movapd %xmm1, (32 + 1*16)(%esp) movapd %xmm2, (32 + 2*16)(%esp) movapd %xmm3, (32 + 3*16)(%esp) movapd %xmm4, (32 + 4*16)(%esp) movapd %xmm5, (32 + 5*16)(%esp) movapd %xmm6, (32 + 6*16)(%esp) movapd %xmm7, (32 + 7*16)(%esp) movl %ecx, 8(%esp) # Save ecx and edx registers movl %edx, 4(%esp) stmxcsr 12(%esp) # Save MXCSR Loading @@ -430,16 +447,21 @@ FUNCDEF(alloc_overflow_sse2) ldmxcsr 16(%esp) # Get new mxcsr value movl %eax, (%esp) # Put size on stack for first arg to alloc() # Save all FPU regs because we don't know what's in use by lisp. fxsave 32(%esp) call GNAME(alloc) fxrstor 32(%esp) movl 4(%esp), %edx # Restore edx and ecx registers. eax has the return value. movl 8(%esp), %ecx ldmxcsr 12(%esp) movapd (32 + 0*16)(%esp), %xmm0 movapd (32 + 1*16)(%esp), %xmm1 movapd (32 + 2*16)(%esp), %xmm2 movapd (32 + 3*16)(%esp), %xmm3 movapd (32 + 4*16)(%esp), %xmm4 movapd (32 + 5*16)(%esp), %xmm5 movapd (32 + 6*16)(%esp), %xmm6 movapd (32 + 7*16)(%esp), %xmm7 STACK_EPILOGUE ret ENDFUNC(alloc_overflow_sse2) Loading